Adversarial Examples

Neural networks, both convolution or transformer based, are essential for modern computer vision systems. However, they are vulnerable to small perturbations, almost imperceptible to humans, which significantly alter the model's prediction. These adversarial attacks are often considered to be a significant threat to the implementation of neural networks in safety-critical applications. Most attacks utilize the white-box threat model and therefore require full access to the target model, making them unrealistic to use in practice. We propose a novel approach under the more realistic black-box threat model that utilizes concepts from reinforcement learning to optimize perturbations with a non-differentiable target model. Reinforcement learning algorithms have already been optimized to be query efficient, making them an ideal starting point when designing black-box adversarial attacks. We show the success of our reinforcement learning inspired black-box adversarial attack (RIBA) in generating adversarial perturbations using only a small number of queries to the target model, by comparing it to state of the art attacks on different models on the Cifar10 and ImageNet data sets. RIBA takes $25.4\%$ fewer median queries to generate attacked images against a ResNet-18 on Cifar10 and $22.5\%$ fewer median queries to fool a Vit-B/16 model on ImageNet. Additionally, we demonstrate that RIBA can match the performance of white-box attacks on an adversarially trained model.

With face-recognition models now embedded in everyday authentication and surveillance, recent works have pinpointed a critical weakness: these models remain acutely vulnerable to adversarial semantic edits. I.e., adversarially produced semantic alterations to the input, such as slight aging or pose changes, can induce misclassifications. Certain existing attacks are powerful, but they can be computationally costly, rendering them inadequate for developing defenses (e.g., through adversarial training). To fill the gap, we introduce BoundStyle, a potent semantic attack operating in StyleGAN's rich latent space to maximize misclassification rates. Notably, BoundStyle achieves high attack success rates while being ${\sim}{\times}9.5$ faster than existing state-of-the-art attacks, making it suitable for adversarial training. Building on BoundStyle, we develop StyleAT, an efficient adversarial training scheme that incorporates low-budget attack variants yet defends against stronger and unseen semantic attacks. We evaluate on two datasets unseen during training and seven models, and find that StyleAT boosts robust accuracy against state-of-the-art attacks and outperforms common defenses in various settings.

Iris presentation attack detection (PAD) is security-critical when a subsystem that appears reliable during development encounters presentation attack instruments (PAIs) or acquisition conditions absent from validation data. We benchmark three compact scratch-trained computer-vision models, each with at most approximately 0.26 million trainable parameters, on the Notre Dame subset of LivDet-Iris 2017 under PAI-driven domain shift and environmental degradation. All models are trained without external pretraining or data augmentation and evaluated over five seeds. A validation-selected threshold is transferred unchanged to the known-attack, unknown-attack, corrupted, and pooled test partitions. From known to unknown attack presentations, Attack Presentation Classification Error Rate (APCER) increases by 17.11-30.47 percentage points and Detection Equal Error Rate (D-EER) increases by 7.38-12.73 percentage points. At the validation-selected threshold, ZACH-ViT obtains the lowest unknown-attack APCER (47.69 +/- 4.84%) and D-EER (38.87 +/- 0.93%), while Compact-TransMIL obtains the lowest Bona Fide Presentation Classification Error Rate (BPCER). ZACH-ViT also gives the lowest unknown-attack BPCER at an APCER limit of 10% (81.29 +/- 1.95%). The high absolute errors show that the comparative advantage of the best compact model does not constitute deployment readiness under unknown PAIs.

As Large Language Models (LLMs) increasingly serve as primary knowledge retrieval interfaces, their robustness against \textit{persuasion attacks}---attempts to inject misinformation or enforce counterfactuals---has become a critical safety concern. Existing red-teaming frameworks typically evaluate models in multi-turn dialogues where the target model retains full conversation history. We identify a critical flaw in this setting termed \textbf{Refusal Inertia''}: a model's initial refusal often propagates through subsequent turns largely to maintain contextual consistency, thereby masking its true vulnerability to sophisticated, isolated persuasion attempts. To rigorously evaluate the cold-start'' defense capabilities of SOTA models, we introduce the \textbf{SAST-IR} (Stateful Attacker, Stateless Target - Iterative Refinement) framework. By enforcing a memory wipe on the target while retaining the attacker's history, we simulate a worst-case adversarial setting using \textbf{multi-turn} (stateless) iterations. Leveraging \textbf{CP-Agent} (Cognitive Persuasion Agent), an enhanced diagnosis-guided agent, our experiments on the custom \textsc{CounterFact-Strict} dataset ($N=50$) yield alarming results: simple, diverse attack strategies achieved a staggering \textbf{96%} success rate, exposing severe brittleness in memory-less defense. Furthermore, we reveal a \textbf{``Complexity Paradox''}: while complex, iteratively refined attacks are effective, they often trigger defensive compliance, whereas simple strategies achieve a higher rate of genuine persuasion (\textbf{84.7%}). Our code and dataset are available at GitHub, https://github.com/cza1006/llm-persuasion-defense.

This paper presents an end-to-end evaluation framework for image-triggered command injection against computer-use agents (CUAs). The goal is to test whether a local visual patch can induce verifiable environmental consequences along the full chain of screenshot input, VLM generation, action parsing, and environment execution. We train and deploy patches on author-controlled GitHub Pages pages and a locally deployed CSDN clone, and evaluate them in real environments across five open-source or publicly available GUI-agent or vision-language-model (VLM) backends. Our experiment aggregates 600 instance-level online cases, with T-ASR, TAPR, and E2E-ASR reaching 84.5%, 47.0%, and 20.3%, respectively. Trajectory analysis further shows that in some successful cases the agent first executes a malicious terminal command and then continues the original benign task. These results indicate that optimized local visual signals can affect not only VLM outputs but also propagate through the execution pipeline of open CUAs and create real environmental risk.

Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and transferred to a target model, unknown to the attacker. Yet how source--target compatibility shapes attack success remains poorly understood. Prior studies evaluate limited detector pools and rarely disentangle architectural from training factors. We conduct a controlled evaluation of adversarial transferability across 60 detectors spanning six backbones, two pretraining regimes, and five training-data configurations, using two attack procedures: AutoAttack (AA) and the Carlini--Wagner attack with Expectation over Transformation (CW--EOT). Matched comparisons reveal significantly higher transfer when source and target share an exact backbone, architecture family, pretraining regime, or training data. This compatibility structure is attack-dependent: exact backbone compatibility has the largest effect under AA, whereas shared pretraining and training data have the largest effects under CW--EOT. When transfer is averaged across non-target sources, mean attack success rate (ASR) is $7.21\%$ under AA and $19.52\%$ under CW--EOT. By contrast, a multi-source oracle combining both attacks attains a $64.48\%$ mean ASR after excluding exact backbone and training-data matches, showing that source averaging can substantially understate target vulnerability. We release 240,000 adversarially perturbed images, complete pairwise transfer results, detector configurations, and evaluation code. These findings establish source--target compatibility and source-model selection as central dimensions of credible transfer-based black-box robustness evaluation.

Human pose estimation and keypoint-based action recognition models are increasingly deployed as components of video understanding pipelines, yet their vulnerability to adversarial attacks remains insufficiently studied. Temporally coherent black-box attacks have been previously studied in visual object tracking, where the attack feedback can be defined using bounding-box overlap measures such as Intersection over Union (IoU). However, human pose estimation produces keypoint configurations rather than enclosing boxes, making box-level similarity poorly suited for measuring pose degradation. We propose OKS Attack, a decision-based black-box attack that uses Object Keypoint Similarity (OKS) as the attack feedback signal, directly targeting the spatial structure of human poses rather than their enclosing boxes. Experiments on the Penn Action dataset show that OKS Attack consistently reduces pose quality across evaluated pose estimators, with mean OKS decreases ranging from 0.0802 to 0.1494. In a downstream cross-dataset action-recognition evaluation, the attack reduces accuracy by 6.18 to 13.86 percentage points and outperforms query-matched random-noise perturbations. The attack is effective across both top-down and single-stage pose estimation models. The source code will be made publicly available at https://github.com/KacperM33/OKS_attack

Training-free collaborative pipelines that integrate Vision Foundation Models such as CLIP, SAM, and DINO achieve strong open-vocabulary dense prediction and are increasingly deployed in safety-critical applications. The security of these systems is commonly assumed to follow from the robustness of their individual models. We challenge this assumption. We identify a vulnerability shared by every collaborative pipeline: each model consumes the intermediate output of another without verifying semantic consistency, an unverified premise that we term the semantic-spatial alignment dependency. Existing adversarial attacks target a single model and overlook this premise, leaving the inter-model interface entirely unguarded. We propose CrACK (Cross-model Adversarial Consistency attack), an inference-time attack that exploits this interface without modifying any input pixel, model weight, or training data. CrACK operates in two stages: Adversarial Affinity Contradiction Injection corrupts the cross-modal affinity matrix by inverting SAM encoder features under the guidance of CLIP patch-level semantics, and Semantic Interface Poisoning steers the prediction through a max-distance label permutation derived from CLIP text embeddings. Experiments on four collaborative pipelines across eight benchmarks show that CrACK causes catastrophic degradation while every individual model continues to produce its unchanged standalone output, rendering per-model defenses structurally blind. The corruption further cascades into large vision-language model reasoning, driving models such as LLaVA to produce erroneous responses from visually intact inputs. Our results show that the security of a collaborative AI system cannot be reduced to the robustness of its components, and that inter-model feature interfaces must be treated as first-class security boundaries.

Multimodal large language models (MLLMs) have extended the capability of large language models (LLMs) to process more contextual multimodal information, showing remarkable progress in diverse realistic multimodal applications. Despite their strong perception and reasoning abilities, recent studies reveal that MLLMs remain highly vulnerable to adversarial inputs, especially those targeting visual components. However, existing attacks mainly focus on global perturbations, lacking an understanding of how MLLMs internally interpret visual structures. In this paper, we make the attempt to investigate the intrinsic focus of MLLMs in the frequency domain and discover that their predictions are particularly sensitive to phase information, which encodes essential structural and semantic cues. Based on this observation, we propose a novel phase-aware adversarial attack framework that explicitly restricts adversarial perturbations to structure-relevant phase regions to suppress the MLLMs' focus for effective and imperceptible attacks. To further amplify the structural influence, we also introduce an auxiliary adversarial prompt learning module to guide multimodal misalignment around phase-sensitive regions, misleading the MLLM's attention toward targeted structural patterns. Extensive experiments on multiple representative MLLM models and datasets demonstrate the superior effectiveness of our method compared to existing attacks.

Thermal Infrared detection is widely used in autonomous driving, medical AI, etc., but its security has only attracted attention recently. We propose infrared adversarial clothing designed to evade thermal person detectors in real-world scenarios. The design of the adversarial clothing is based on 3D modeling, which makes it easier to simulate multiangle scenes near the real world compared to 2D modeling. We optimized the black patch layout pattern of 3D clothing based on the adversarial example technique and made physical adversarial clothing using the aerogel. The idea is to paste a set of square aerogel patches, which display black squares in thermal images, in the inner side of clothing at specific locations with specific orientations. To enhance realism, we propose a method to build infrared 3D models with real infrared photos and develop texture maps for 3D models to simulate varied infrared characteristics over time and location. In physical attacks, we achieved an attack success rate of 80.11% indoors and 76.85% outdoors against YOLOv9. In contrast, randomly placed patches yielded much lower success rates (26.53% indoors and 23.03% outdoors). The adversarial clothing also showed good transferability to unknown detectors with an ensemble attack method, demonstrating the effectiveness of our approach.

Face recognition systems are increasingly deployed in security-critical applications, yet they remain vulnerable to presentation and morph attacks. Presentation attack detection (PAD) and morphing attack detection (MAD) are therefore essential components of trustworthy face biometrics. Despite advancements in PAD and MAD methods, existing detectors suffer from limited generalization and degrade in cross-dataset evaluation. In this paper, we systematically investigate whether general-purpose foundation models (FMs) and multimodal large language models (MLLMs) encode PAD-relevant and MAD-relevant information, and how such models can best be deployed for both tasks. We study five approaches with increasing access to the internal information of the model: (i) zero-shot prompting of off-the-shelf MLLMs; (ii) training a shallow model on the next-token logit probabilities at the output of the MLLM; (iii) parameter-efficient fine-tuning on task-specific question-answer data, yielding two specialized MLLMs, called PADLLM and MADLLM, which additionally provide textual reasoning for their decisions; (iv) linear probing of frozen vision encoders; and (v) fine-tuning of vision encoders of FMs and MLLMs. We benchmark 16 open-weight MLLMs and 30 vision encoder backbones on four PAD datasets (MSU-MFSD, CASIA-FASD, Replay-Attack, and OULU-NPU) and four MAD datasets (FFHQ, FRGC, FRLL, and FERET). Our experiments show that FMs and MLLMs can achieve significant performance for PAD and MAD. In addition, the fine-tuned models achieve state-of-the-art detection performance in cross-dataset evaluation, indicating that general-purpose pretrained representations carry substantial attack-relevant information. Source code of all our experiments will be publicly released.

Post-deployment changes to large language models can alter behavior while leaving routine outputs largely unchanged, creating a challenge for AI governance when model weights are proprietary. We present a privacy-preserving zk-SNARK-based audit framework that searches for probes designed in the spirit of adversarial examples to amplify logit drift between an approved model and a modified deployment. Our framework explores complementary probe families under different access models. Token-based probes operate in a black-box setting and require only the input interface, tokenizer, and vocabulary. Embedding-based probes require gray-box access to the embedding interface. Stress probes rely on additional interface capabilities but do not require full white-box access to model weights or architecture. This range allows probe selection to balance sensitivity, access requirements, and deployment cost. We evaluate probe constructions across LLM architectures, model-tampering scenarios representative of post-deployment attacks, and GPU platforms. Importantly, our experimental results demonstrate that token-based probes consistently deliver the strongest mean sensitivity across models and GPU platforms, although operating in a black-box setting. Our Groth16 zk-SNARK workflow remains practical as the probe set scales from 1 to 50, where proving time increases from 1.02 to 1.78 seconds, verification remains near 0.84 seconds, and proof size remains constant.

We revisit the problem of learning predictors robust to adversarial examples at test-time. We prove that VC classes are adversarially robustly learnable with sample complexity linear in the VC dimension $d$, providing an exponential improvement over the previous upper bound of Montasser, Hanneke, and Srebro (2019). Remarkably, this result is achieved with a simple improper algorithm that combines the classic heuristic bagging (bootstrap aggregation) of Breiman (1996) with robust empirical risk minimization (RERM). Our algorithm computes RERMs on $O(d^\star)$ independent bootstrap samples and outputs their majority vote, where $d^\star$ denotes the dual VC dimension. We complement this result with a lower bound showing that this is unavoidable: in general, any learner in this oracle model requires $Ω(d^\star)$ calls to an RERM oracle, even when given arbitrarily many training examples.

Vision-Language-Action (VLA) models have emerged as generalist robotic policies capable of following diverse language instructions and performing a wide range of manipulation tasks. However, their direct control over embodied agents also exposes them to adversarial interference that may cause unsafe physical behaviors. Existing attacks on robotic policies are typically optimized for a single task or instruction, leaving the cross-task vulnerabilities of multitask VLAs largely unexplored. We introduce UniTexture, a cross-task universal adversarial texture attack that uses a single textured 3D object to induce targeted deviations in VLA action predictions across multiple tasks. UniTexture backpropagates gradients from the policy's action outputs to surface texture parameters through a differentiable renderer. It jointly optimizes the shared texture over a distribution of tasks, instructions, states, and viewpoints using a targeted action-space objective, steering predicted actions toward attacker-defined targets without optimizing a separate texture for each task. We evaluate UniTexture on OpenVLA and $π_{0.5}$ across diverse manipulation tasks and multiple evaluation settings. UniTexture reduces the mean task success rate from 90.0% under benign conditions to 48.4% under attack, induces target-aligned action shifts, and further exhibits cross-suite and cross-model transfer without re-optimization. Together, these findings reveal shared cross-task vulnerabilities in multitask VLAs that can be systematically exploited through a single adversarial surface texture.

Existing global optimization benchmark suites are of a moderate size and are based on a small number of analytical functions that date back even to the 1970s. This causes a risk of biasing the development of global optimization methods. We argue that the tasks related to the black-box adversarial attack (BBAA) can serve as valuable global optimization benchmark in many-dimensional space. We demonstrate the efficiency of several types of evolutionary algorithms and other metaheuristics in solving example BBAA problems. Thus, we take a step towards convergence of global optimization methods to the challenges and needs that arise in the modern machine learning field.

Deep learning models are widely used for time series analysis in domains such as healthcare, finance, energy systems, and environmental monitoring. However, these models remain vulnerable to adversarial attacks, where small input perturbations cause severe degradation in predictive performance. Commonly used gradient-based attacks, iterative first-order methods, are computationally burdensome, as they repeatedly backpropagate through the victim model to compute input gradients during a number of iterative refinement steps. We propose a GENerative ADversarial Attack (GENADA) that learns a generative model to produce deceptive perturbations directly in a single forward pass and a procedure to train it. Variants include single-step and iterative generative attack schemes. The validation considers attacks on several neural models and datasets in the time-series domain, a controlled, low-dimensional setting. Empirically, GENADA achieves comparable attack quality to strong baselines while requiring less time to generate perturbations during inference.

Vision-Language-Action (VLA) models have shown strong capabilities in controlling robots across diverse manipulation tasks. However, their adversarial robustness remains largely underexplored, and exploiting this weakness can lead to physical-world harm. Existing attacks on VLA models often rely on pixel-space perturbations or white-box access, resulting in noticeable artifacts and limited deployability in real-world robotic systems. In this work, we propose DURA, a diffusion-based unrestricted robotic attack that generates visually natural adversarial patches for VLA models. DURA supports both white-box and black-box attack settings, where the black-box setting requires only the predicted actions of the victim model. By optimizing along the latent trajectory of a pretrained diffusion model, DURA generates visually natural patches while steering the robot toward attacker-specified target actions. Extensive experiments in both simulation and the real physical world show that DURA consistently outperforms existing methods. Our findings expose a safety risk for physically deployed VLA models and call for stronger defenses.

Contrastive learning and Siamese embedding models have become the foundation of modern verification systems, where decisions are governed not by discrete classification boundaries, but by relational geometry in embedding space. However, existing adversarial attacks remain fundamentally classification-centric, overlooking the vulnerability of relational geometry. In this paper, we introduce a geometry-aware adversarial attack framework that reformulates attacks on contrastive systems as manifold-level relational corruption. Instead of targeting individual predictions, the proposed framework systematically distorts similarity organization within the embedding manifold by pushing positive pairs apart while simultaneously pulling negative pairs closer, ultimately collapsing and inverting pairwise similarity structure. To enable scalable deployment, we shift iterative online optimization into an offline adversarial geometry deformation prior learning stage and train a lightweight feed-forward generator that learns generalized geometry deformation patterns from the victim model. Once trained, the generator produces adversarial perturbations through a single forward pass without requiring online gradient computation, enabling real-time online attacks against similarity-based verification systems. Experimental results across multiple verification architectures demonstrate substantial degradation of verification performance together with severe manifold-level relational corruption. On the Markmatch verification system, the proposed attack reduces accuracy from 95.4% to 38.6% while completely reversing the positive-negative similarity structure.

Despite the success of convolutional neural networks in image classification tasks and their general application in multi-modal models, their susceptibility to out-of-distribution and adversarial attack samples raises concerns regarding trustworthiness and safety. Among the approaches to tackle such issues, detection methods that analyze the model's intermediate activations to estimate a confidence score are a promising family that evaluates the decision process, relying on a dimensionality reduction step to enable efficient downstream processing of the high-dimensional activations. However, when considering convolutional layers, the dimensionality reduction methods in the literature either lack a mechanism to control the compression/information-loss trade-off or yield large representations. In this paper, we carefully analyze two state-of-the-art detection methods and their dimensionality reductions for convolutional layers and develop a novel reduction method with a controllable high-compression level. We extend these two state-of-the-art detection methods, enabling the usage of any dimensionality reduction, and evaluate their performance on out-of-distribution and adversarial attack detection. Results show that the detection methods with the proposed dimensionality reduction consistently perform better than, or comparable to, the strongest alternative. Furthermore, the proposed method is shown to reduce computation and memory footprints, given that it has the highest compression among the compared methods.

Digital watermarking has emerged as a critical technique for provenance and copyright attribution in AI-generated imagery, yet its robustness against realistic, model-agnostic removal attacks remains poorly explored. Existing attacks either succeed only against specific generative models or achieve removal at the cost of severe visual degradation. In this paper, we propose MarkNull, a model-agnostic watermark removal attack via on-manifold latent manipulation. MarkNull is grounded in a key observation: watermarked images exhibit a strong statistical dependency between the generated latent representation and the embedded initial noise. To quantify this dependency, we introduce the Noise-Latent Alignment Score (NLAS) and formulate an optimization objective that selectively decorrelates the latent representation from the embedded watermark while preserving semantic fidelity. Extensive evaluations across different categories of watermarking paradigms, including post-hoc, fine-tuning-based, and initial-noise-based schemes, demonstrate that MarkNull reduces average bit accuracy to 53.14%, approaching random-guessing (50%), without perceptible image degradation. To further improve scalability, we propose MarkNull-A, an amortized, optimization-free variant that distills the attack into a single forward pass, achieving 0.50 s/image with modest computational overhead. Notably, our attacks successfully compromise Google's SynthID-Image system while preserving high visual quality and transfer effectively to video watermarking. Finally, we present an attack detection mechanism as a defensive counterpart to MarkNull and MarkNull-A, highlighting the necessity of developing watermark designs resilient to model-agnostic latent-space attacks.

Detecting machine-generated disinformation on social media is increasingly difficult as large language models (LLMs) make it easier to generate and rewrite misleading content at scale. Static benchmark evaluations, measuring detector performance on fixed held-out datasets, do not capture how detectors behave when posts are deliberately transformed to evade classification. This paper adapts the Build it, Break it, Fix it framework into Build it, Break it, Repeat (BiBiR): iterative sessions designed to stress-test detectors' robustness under iterative adversarial conditions, evaluating whether models remain reliable when disinformation posts are systematically transformed to evade classification. Across five iterations, the findings show that the best adversarial breakers' transformations came from a combination of back-translation and LLM persona-based rewriting, with the best performing technique achieving a 95% label flip rate (LFR), whilst still preserving the meaning of the original posts. The best builders' model was a triplet contrastive model with a dynamic anchor switching (DASS) architecture, which achieved an average accuracy of 72.68%, outperforming the strong baseline (a fine-tuned e5-small-LoRA) by 15 percentage points on the most robust set of breakers' adversarial attacks. The results demonstrate that an iterative framework best exposes detector weaknesses and pushes robustness improvements; however, it may still require semantic preservation analysis to distinguish valid adversarial evasion from transformations that changed the original disinformation claims' meaning.

In a federated learning setup for GANs, several adversarial attacks are possible. One such attack is label flipping, in which malicious clients deliberately alter label information during local training in order to manipulate the global generator. The objective of this attack is to skew the learned generation distribution so that samples conditioned on a target label are instead mapped to a source class. In this work, we investigate the effectiveness of label flipping attacks in federated GANs through both theoretical analysis and empirical evaluation. We further consider an oversampling based variant, in which malicious clients upweight poisoned samples during local training to amplify their influence on the aggregated global model. We quantify the resulting distributional shift by computing the Kullback Leibler divergence between the clean and poisoned class conditional distributions, and show both analytically and on FEMNIST, MNIST, and CIFAR10 that the semantic damage of the attack grows linearly in the effective poisoning strength while deviation from the true target distribution grows only quadratically, making the attack effective yet difficult to detect from label agnostic metrics.

Reliable evaluation of tool routing is critical as Large Language Models increasingly operate as autonomous agents. Current benchmarks face three structural limitations: data distributions that follow a power law leave rare scenarios underrepresented; the absence of adversarial hard negatives obscures performance differences across models; and annotation pipelines depend on LLM judgments that have not been validated through execution. In this paper, we introduce PluginEval, a benchmark constructed through a two-stage framework that systematically mitigates these limitations. First, we formulate tool routing as a sequence of three decisions and separate generation from verification. LLMs propose candidate calls, while deterministic validation and real API execution provide reliable quality signals. Second, we decompose each plugin by capability, intent, and boundary to identify trigger and exclusion scenarios. We then generate queries at different difficulty levels to fill coverage gaps, including adversarial negatives targeting three failure modes, and return them to the first stage for annotation. This process creates a closed loop that iterates until coverage converges. For evaluation, we move beyond aggregate accuracy. An LLM judge anchored to gold annotations classifies failures as missed calls, spurious calls, or parameter errors, producing a detailed error profile for each model. We evaluate five model families, including proprietary models and models with open weights, analyze their performance across difficulty levels and error categories, and validate the judge through agreement with human annotations.

AI-generated image (AIGI) detection has become increasingly challenging due to the rapid advancement of generative models and the diminishing gap between synthetic and authentic content. Existing vision transformer-based detectors commonly rely on weighted-sum strategies to aggregate intermediate representations across transformer layers, often overlooking the inherently ordered semantic progression of hierarchical features from shallow texture cues to deep semantic representations. In this work, we propose \textbf{PE-Mamba}, a novel framework built upon a pre-trained PE-Core vision transformer with lightweight LoRA adaptation that introduces three complementary components for cross-layer feature aggregation and fusion. First, a bidirectional selective aggregator (BSA) processes layer-wise classification tokens through forward and backward selective scans, where the forward scan progressively accumulates shallow-to-deep forensic evidence, and the backward scan performs deep-to-shallow contextual refinement to reinterpret low-level cues in light of high-level semantic context. Second, a softmax-weighted aggregator (SWA) computes a learned global summary of all layer tokens as a complementary aggregation path. Third, a sigmoid-gated blend (SGA) adaptively fuses the BSA and SWA outputs via a learnable scalar gate, allowing the model to dynamically balance directional sequential evidence and global layer-wise aggregation. Extensive experiments on UniversalFakeDetect (96.6% mACC, 99.5% mAP) and AIGCDetect (95.3% mACC, 98.1% mAP) demonstrate that \methodname{} outperforms 18 detectors with superior generalization across diverse generative models, while training only 1.3% of total parameters (0.13% for LoRA alone).

Deep-OCR (DeepSeek-OCR) advances document recognition by treating the visual modality as an optical compression medium, enabling long-context OCR at low token cost. However, its increased complexity may introduce new security vulnerabilities. In this paper, we present, to the best of our knowledge, the first pure black-box adversarial attack against a generative OCR vision-language model, where only the decoded string can be queried and no gradients, logits, or model internals are available. We recast the attack as a zeroth-order optimization problem driven by a bounded scalar loss defined directly on the string output via sequence similarity, and estimate the gradient with a random-direction finite-difference scheme whose query cost is independent of the image dimension. An Adam update with ell_infinity projection yields imperceptible perturbations for both untargeted and targeted objectives. Pilot experiments on Deep-OCR validate the string-only attack and evaluation pipeline and expose severe qualitative decoder failures, including repetition, truncation, and prompt leakage. They also show that controlled targeted rewriting remains substantially harder than untargeted degradation; we avoid claiming targeted success until the pre-registered evaluation is complete.

Split Federated Learning (SFL) facilitates privacy-preserving collaborative training with reduced client-side overhead. However, its split architecture introduces unique attack surfaces, rendering it vulnerable to diverse poisoning attacks. Most existing defenses fail to exploit the split paradigm, limiting their ability to detect and contain malicious behaviors at an early stage. To bridge this gap, we propose Target-Oriented Feature Decoupling (TOFD), a unified framework that jointly enables proactive detection and robust optimization against a wide range of poisoning attacks. TOFD operates in three stages: (1) Target Inference, which identifies potential attack targets by refining class-wise safe zones via class-specific Margin Perturbation (MP); (2) Sample Purification, which adaptively filters poisoned smashed data using thresholds calibrated through cross-class min-max normalization of MP; and (3) Decoupling Optimization, which leverages an adversarial guidance model to capture attack-induced patterns and decouple their influence during optimization, thereby suppressing residual adversarial effects. We provide theoretical guarantees for the convergence of TOFD. Extensive experiments on five datasets demonstrate that TOFD consistently outperforms state-of-the-art defenses under diverse attack scenarios, achieving superior robustness with low computational overhead suitable for practical deployment.

Physical adversarial attacks against person detectors have evolved from localized patches to full-body textures. However, achieving both visual naturalness and strong attack effectiveness remains challenging. Existing natural-looking methods typically optimize camouflage textures as a whole, limiting the flexibility to refine local adversarial patterns and their spatial arrangement. To address this issue, we propose AdvTiles, a physical adversarial camouflage framework built from learnable tiles, enabling strong attack performance while preserving a natural camouflage appearance. Specifically, we use a Straight-through (ST) Gumbel-Softmax estimator for differentiable tile selection, enabling joint optimization of tile patterns and spatial layouts. This design provides fine-grained control over adversarial texture generation. To improve robustness in diverse physical conditions, we further optimize the camouflage through differentiable 3D Gaussian Splatting rendering with variations in viewpoints, scales, illuminations and backgrounds. Extensive experiments across multiple detectors demonstrate that AdvTiles achieves an average ASR of 86.2%, outperforming existing state-of-the-art attack methods. We further fabricate the optimized camouflage into wearable adversarial clothing, validating its effectiveness in real-world scenarios across diverse distances, angles and backgrounds.

Adversarial vulnerabilities remain a major concern for the safe deployment of neural networks, particularly in object detection, a core task embedded in many safety-critical systems. Detection transformers have emerged as leading object detectors, yet their adversarial robustness remains comparatively underexplored. Most existing attacks target the detection output rather than the attention mechanism that makes these models distinctive. In this paper, we introduce the first attack that directly optimizes an encoder-attention objective under an imperceptible, bounded $\ell_\infty$ perturbation. Rather than introducing an attacker-owned sink token through a visible patch, it drives the model's own attention toward a corrupted target. We argue that encoder attention concentrates the model's spatial reasoning, so corrupting it propagates through the detection pipeline more disruptively than perturbing the detection output alone. Our attack reduces DETR-R50 mAP on COCO from 42.1 to 0.97, a $\sim 4\times$ reduction in resulting mAP over the strongest existing attack under an identical perturbation budget and iteration count. We further show that this vulnerability is not specific to a particular corruption objective: across four qualitatively distinct targets, dispersion, re-ranking, permutation, and peak-suppression, detection consistently drops below 3 mAP, suggesting that the weakness arises from disrupting the attention structure itself rather than from any single target. Finally, we demonstrate that the attack generalizes across attention formulations, reducing DINO-Swin-L from 56.8 to 1.44 mAP against 7.3 for the strongest prior attack, establishing state-of-the-art on both dense and deformable attention.

Although deep neural network-based remote sensing object detectors have achieved strong performance, they remain vulnerable to adversarial perturbations. Existing studies mainly focus on digital or white-box settings, whereas black-box physical attacks remain underexplored. These attacks are often constrained by limited physical feasibility and inefficient optimization in high-dimensional search spaces. To address these challenges, this paper proposes ColorFD, a black-box physical attack based on multiple pure-color patches. The patch positions and color parameters are jointly optimized using Differential Evolution (DE). A target-wise fitness and selection mechanism evaluates the attack state of each target and preserves target-specific improvements during evolution. Two guidance strategies further constrain the patch search space. Key-region localization identifies sensitive regions through finite-difference color probing. Common-feature extraction provides category-level spatial priors and avoids repeated localization. Although evaluated on aircraft, the formulation is not inherently restricted to this category. Experiments on YOLOv3u, YOLOv5u, and Faster R-CNN show that ColorFD outperforms the tested black-box patch method across all evaluated detectors and remains competitive with strong white-box baselines. Physical-world experiments further demonstrate that the optimized pure-color patches can be transferred from the digital domain to real imaging conditions.

Transfer-based adversarial attacks often transfer poorly across heterogeneous architectures because CNNs favor local textures while Vision Transformers (ViTs) rely on global shapes. We propose Season, a spectrum-aware orthogonal gradient refinement framework for L-infinity transfer attacks against black-box target models on ImageNet, using a white-box surrogate. Season decomposes each update into a low-frequency branch capturing structural cues and a high-frequency branch capturing textures. A low-saliency guidance scheme reallocates high-frequency energy to background regions, preserving foreground structures that ViTs depend on. An orthogonal projection then forces the textural update to lie in the orthogonal complement of the structural direction, mitigating feature interference. As a training-free plug-and-play wrapper, Season enhances eight gradient-stabilization and input-enhancement attacks without modifying their cores. Across eight CNN, ViT, and MLP targets, Season improves transfer success rate by 6.6 percentage points on average and up to 16.0 points over strong baselines under a unified protocol.

Once visual content enters an AI pipeline, its owner often retains little technical control over how it is used. Legal and regulatory remedies can address misuse, but many technical interventions must be applied earlier, when content is released or accessed. This survey examines the protective paradigm that has grown around this intervention point, which we call \emph{adversarial attacks for good}. Perturbations and structured signals long studied as attacks on learned models are instead applied by data owners, creators, platforms, or auditors to disrupt unauthorized automation or support later accountability. Five research communities have arrived at this inversion largely independently, each addressing a different stage of a visual asset's lifecycle: privacy filters against unwanted recognition at sharing time, unlearnable examples against unauthorized training, generative safeguards against malicious editing or imitation, adversarial CAPTCHAs for access control against automated agents, and provenance mechanisms for post-circulation attribution. Although developed in separate venues with incompatible success criteria, many of these methods exploit persistent gaps between human perception, semantic interpretation, and machine inference, suggesting that the paradigm remains relevant as visual pipelines evolve toward multimodal models and autonomous agents. To make their claims comparable, we evaluate all five families along shared axes of transferability, adaptability, and deployment readiness. Across the lifecycle, we find that most protections are still validated mainly against static or weakly adaptive adversaries, while evidence beyond controlled benchmarks remains scarce. We close by consolidating cross-stage countermeasures and open problems for robust, composable, and deployable owner-side protection.

Large language models (LLMs) are often used in conjunction with external knowledge sources to improve their factual accuracy and decrease hallucinations, through methods such as Retrieval-Augmented Generation (RAG). However, these systems remain susceptible to intrinsic hallucinations, where the model generates unfaithful or fabricated information that is not supported by the retrieved evidence. We propose a novel framework to assess model robustness against this phenomenon by stress-testing using natural, semantically equivalent variations of a user query found via adversarial optimization methods. We apply our framework, which enforces strict semantic equivalence constraints and an intrinsic hallucination objective, to a range of adversarial attack techniques across white-box, gray-box, and black-box adversarial settings. Evaluating these attacks on 5 open-source and 5 closed-source generator models across 3 datasets, we demonstrate that even state-of-the-art models are highly susceptible to meaning-preserving perturbations, which significantly degrade contextual faithfulness (by up to 50% for GPT-5-mini). Our findings indicate that faithful use of in-context evidence remains fragile even in state-of-the-art LLMs, motivating architectures and training objectives that enforce robust grounding independent of surface query form. Code is available at: https://github.com/atriviveksharma/intrinsic_hall

Recent GUI visual grounding models generate screen coordinates as sequences of digit tokens that are parsed into numerical values and mapped to executable clicks. The security implications of this coordinate generation process have been largely overlooked. We observe that each coordinate digit is predicted as a categorical token, yet after parsing, changing a hundreds-place digit by one changes the corresponding numerical coordinate component by 100 units, which can induce a large displacement of the executed click. This observation motivates attack objectives that account for the numerical and place-value structure of coordinate outputs rather than treating them as ordinary text. Moreover, untargeted and targeted attacks impose different success conditions--displacing the click outside the correct region versus into an attacker-specified region--and therefore benefit from different objectives. We propose MissClick, a simple and effective white-box adversarial attack with two goal-specific objectives: MissClick-U maximizes soft-coordinate displacement for untargeted disruption, while MissClick-T minimizes a place-weighted target-digit loss for targeted hijacking. Compared with existing attacks against GUI grounding models on OS-Atlas and UGround across desktop, web, and mobile platforms, MissClick-U achieves untargeted success rates of 75.07% and 72.93% (+16.62 and +30.72 pp), and MissClick-T achieves targeted success rates of 44.86% and 62.67% (+31.73 and +47.06 pp). Attack objective comparison further shows that soft-coordinate displacement yields the highest untargeted attack success rate, whereas place-weighted target-digit optimization yields the highest targeted attack success rate, revealing distinct objective preferences for the two attack goals.

Flow-matching vision-language-action (VLA) models such as pi0 generate robot actions by integrating a learned denoising velocity field, and have been reported to resist adversarial perturbations that readily fool autoregressive VLAs. We show that this robustness is largely illusory: it stems from prior attacks ignoring the multi-step denoising ODE. We introduce DRIFT (Denoising Redirection via Input perturbation of the Flow-matching Trajectory), a test-time universal adversarial patch placed on the robot's gripper that attacks the denoising velocity field of an off-the-shelf policy. Our central finding is counterintuitive: attacking only the first denoising step is both stronger and cheaper than attacking a wider window of steps, which we explain through a gradient conflict unique to input-space optimization and which is exactly opposite to the training-time backdoor regime. On pi0 and pi0.5 across four LIBERO suites, DRIFT breaks essentially all originally-solvable tasks with a small single patch, far exceeding action- and embedding-space attack baselines.

Rapidly evolving Generative AI enables sophisticated visual text manipulations that increasingly evade current forensic detectors. Existing discriminative models often overfit specific forgery patterns, limiting their generalization to unseen, open-set attacks. To address this challenge, we propose a generative detector that localizes tampering by estimating the local restoration cost required to align a query image with authentic visual-text statistics, rather than by learning forgery-specific decision boundaries. Specifically, we introduce Sparse-Constraint Rectified Flow (SC-RF), a detector-oriented adaptation of Flow Matching for spatially sparse anomaly localization. We further mitigate data scarcity via self-supervised Artifact Injection and preserve high-frequency forensic traces using a pixel-space Forensic-DiT. Extensive experiments on three benchmarks show that our method achieves state-of-the-art performance, surpassing the runner-up by 3.2 and 4.8 percentage points in F1 and IoU, respectively. In particular, the proposed detector demonstrates strong zero-shot performance on challenging unseen text editing patterns. We further provide an auxiliary stress-test analysis showing that local harmonization produced by our model can weaken the statistical cues relied upon by existing detectors, offering a complementary vulnerability-analysis perspective.

With the rapid release of open-weight large foundation models, safety threats are shifting from black-box jailbreaks to neuron-level white-box attacks that directly identify and manipulate safety-related neurons. Existing alignment methods often investigate the safety behavior on a small number of neurons, creating fragile single point of failure with limited redundancy. To address this issue, we propose distributed safety alignment (DSA), which redundantly encodes safety capabilities across multiple computational neurons, ensuring that the model maintains its safety baseline even when critical safety neurons are disrupted. Specifically, we localize the intervention to the inputs of the down-projection layers in language-side feed-forward networks and treat each feature coordinate as the activation of an individual neuron. DSA then combines neuron activations with loss gradients to compute a direction-aware first-order Taylor score that globally identifies the neurons that contribute most to the current refusal behavior of the model. Finally, targeted disruption via deterministic masking and stochastic dropout is coupled, forcing the model to abandon narrow safety neurons and redundantly encode safety behavior across multiple compensatory neurons. Extensive experiments show that DSA substantially improves robustness against white-box neuron-level safety attacks while preserving the model's general language and multimodal utility.

The rapid advancement of image generation models has made it increasingly difficult for people to distinguish AI-generated images from real ones. To prevent the potential risks associated with the misuse of fake images, AI-generated image detection has gained significant attention. Existing methods neglect the inherent differences between real and fake images, thus lacking robustness and generalization ability. In this work, we innovatively investigate AI-generated image detection using bit-planes, and introduce the bit-reversed image. We propose a simple yet effective pipeline consisting of construction of bit-reversed images, gradient-based patch selection and a convolutional classifier. Besides, we provide a theoretical analysis from the mathematical perspective to demonstrate the validity of our approach. We also introduce two challenging datasets for AI-generated image detection. Extensive experiments verify the effectiveness of our approach across different settings, including cross-generator generalization, cross-dataset generalization and zero-shot performance. Without bells and whistles, our approach outperforms existing methods on over 40 benchmarks, and is nearly 100 times faster than counterparts. The code is at https://github.com/renxi-seu/RAID.

Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space. However, the decision boundaries of deep face recognition (FR) systems are often sufficiently narrow that they can be conflated, rendering the models vulnerable to adversarial attacks. In such scenarios, the FR system fails to distinguish between an authentic source and a meticulously crafted adversarial face. Existing adversarial methods targeting facial biometrics are limited in both performance and their ability to generate high-quality images that are imperceptible to humans. Moreover, these methods often fail when the source and target images belong to different demographic groups or genders. To address these limitations, we present a novel approach for adversarial face generation via latent-space optimization. We leverage latent diffusion models directly to guide generation toward target identity embeddings, as measured by a face recognition model. Our proposed \textbf{DiffAttack} framework has been evaluated on standard benchmarks, such as the FFHQ and CelebA-HQ datasets. DiffAttack significantly outperforms existing adversarial techniques, achieving a high average attack success rate of 84.86% across multiple face recognition models (e.g., FaceNet). Notably, DiffAttack demonstrates superior transferability, surpassing traditional noise-based methods by over 15.28% and semantic-based approaches by approximately 5.21% on benchmark datasets like FFHQ and CelebA-HQ.

With the promising performance of deep neural networks on image-based tasks, different real-world applications such as autonomous driving and motion detection have become increasingly mature and relevant to human lives. In particular, Optical Flow Estimation Networks (OFENs), as upstream models, play a critical role in different domains. Its outputs are heavily assumed and adopted for different downstream tasks, and it is essential to test its robustness to prevent safety accidents. We present an approach for real-time attacks on OFENs in the physical world, leveraging infrared lights for their stealthiness. By generating a large number of Adversarial Examples in advance, our approach computes AEs in real time and dynamically displays them, which allows our method to facilitate precise and targeted attacks without modifying the victim system. Unlike previous digital-to-physical attack techniques, our method directly attacks victim models within the physical world, thereby overcoming the limitations associated with the ineffectiveness of AEs. Experimental results demonstrate the efficacy of our approach in compromising OFENs across diverse lighting conditions, varying object motion velocities, and different object placements, ultimately impairing the network's ability to accurately estimate optical flow.

Recent diffusion models have achieved remarkable realism in facial image synthesis, posing growing challenges to artificial intelligence-generated content (AIGC) forensic detectors.Existing evasion methods typically perturb pre-generated images or require detector-aware training, which may introduce visible or statistical artifacts and limit applicability when the diffusion model must remain frozen and the target detector is accessible only through black-box queries. We propose Trajectory-Injected Generative Attack (TIGA), a source-image-free and training free framework that generates detector-evasive images within a single diffusion sampling trajectory. TIGA steers the latent Denoising Diffusion Implicit Model (DDIM) trajectory so that adversarial properties emerge during generation rather than being added afterward. TIGA first aggregates gradients from multiple white-box surrogate detectors to form a transferable, sign-aware prior, and then performs anisotropic directional search with symmetric finite-difference queries to estimate the black-box target response. The estimated directions are stabilized by decayed momentum and injected according to the DDIM noise schedule, with frequency-domain reshaping to suppress high frequency artifacts. Experiments on surrogate and unseen specialized forensic detectors show that TIGA achieves strong blackbox attack performance, transferability, and high robustness under common post-processing operations without source images or diffusion-model retraining, while preserving high perceptual quality.

This paper describes the participation of team "Go To Germany" in the ImageCLEF 2026 Deepfake Detection and Generation Task. For the image generation task, we employ FLUX.1-dev with PuLID for identity-preserving face synthesis, combined with a multi-model PGD adversarial attack targeting 12 detectors simultaneously (DiffJPEG-in-loop, MI/DI/EoT, adaptive weighting, two-stage warm-start). Our approach achieved 90% evasion against organizer detectors and 57.6% against participant detectors, with a final generation score of 0.4170. For the image detection task, we combine two complementary detectors - SigLIP+DINOv2 for AI-generated images and GenD-DINOv3 for face manipulations - in a max-probability ensemble, achieving 99.4% accuracy on baseline deepfakes but suffering from high false-positive rates on real images, resulting in a final detection score of 0.6986. Beyond the official submission, we conducted a self-initiated investigation of purification-based adversarial detection, comparing three families of detection signals across six detectors that share a CLIP ViT-L/14 backbone. We find that raw $|Δ\text{logit}|$ under median-3 purification, applied through the EFFORT detector, separates adversarial inputs from clean inputs with AUROC 0.81-0.98 across four adversarial source types - a finding that refutes the simple backbone-preservation hypothesis and exposes a sharp JPEG-quality cliff at Q70 where the signal collapses.

The emergence of the recent outstanding capabilities of Arabic Language Models has opened doors for exposing their vulnerabilities. One of the major security risks associated with such Natural Language Processing models is adversarial attacks. These attacks can deceive the model into the wrong prediction, raising critical model security and safety concerns. This study aims to assess the robustness of five state-of-the-art Arabic Language Models under a distinct set of Arabic adversarial attacks applied at various levels of granularity and using different example generation strategies. We also explore a defense technique based on adversarial training to enhance model robustness. The results show that insertion of diacritics can reduce the accuracy of some models by 92% while maintaining a low perturbation distance. For word-level attacks, manipulating Arabic conjunctions preserves high semantic similarity scores, low perturbation distance, and leads to an accuracy degradation of up to 58%. For sentence-level attacks, paraphrasing proves its effectiveness by an average reduction of 76% in the victim models' performance. While adversarial training improves overall resilience, with MARBERT being the most robust and AraBERT showing the greatest relative gains, challenges persist, particularly against character-level noise. These findings highlight both the potential and limitations of current defense strategies in morphologically rich languages like Arabic.

The rapid advancement of video generation models has led to the increasing misuse of image-to-video (I2V) models. Although substantial progress has been made in detecting AI-generated videos, proactive defenses against I2V models remain underexplored. In particular, current proactive defenses against I2V models predominantly rely on gradient-based adversarial attacks, which require defenders to possess GPUs with substantial memory resources (VRAM) to generate adversarial examples. To address this issue, we propose I2VShield, a privacy protection method based on generative adversarial attacks tailored to Diffusion Transformer (DiT)-based I2V models. The proposed method primarily consists of two components: (1) a text-adaptive perturbation generation framework integrating adversarial learning to mitigate computational overhead while maintaining visual imperceptibility; and (2) an untargeted Multimodal Attention Disruption (MAD) attack that exploits the inherent vulnerabilities of DiT-based I2V models, maximizing the deviation of the internal attention features from their clean states. Extensive experiments demonstrate that our approach achieves highly competitive protection performance across various datasets and mainstream DiT-based I2V models, particularly in disrupting spatiotemporal coherence, while substantially reducing computational costs.

Deep learning-based visual-infrared fused face detection models are increasingly deployed across a wide range of applications, yet they remain susceptible to adversarial patch attacks. Most prior attacks target either the visual or the infrared image alone in the digital domain, which renders them ineffective against fused models in the physical world. Moreover, many of these methods are readily noticeable, as their patch patterns deviate substantially from those seen in the real world. In this paper, we introduce VIPatch (Visual-Infrared Patch), a novel physical adversarial patch attack that produces inconspicuous, realistic, and natural-looking patches for facial images. Specifically, VIPatch crafts a gradient-color mask together with a band-aid sticker across both the visual and infrared images, and jointly optimizes these two elements; the resulting digital patches further guide the fabrication of their physical counterparts. Experimental results show that VIPatch achieves competitive attack success rates (over 90%) in both the digital and physical domains, while keeping the patches unobtrusive to human observers.

The rapid advancement of generative models has spurred the critical need to evaluate the worst-case robustness of deepfake detectors. In this paper, we reveal a fundamental blind spot in current forensic paradigms: while existing detectors excel at capturing digital synthesis artifacts, their effectiveness drops drastically when AI-generated content is cloaked in authentic physical imaging characteristics. We posit that genuine photographs inherently possess hardware-intrinsic statistical signatures, which are imperceptible footprints imprinted by optical sensors and Image Signal Processing (ISP) pipelines, and are fundamentally absent in purely data-driven generative models. Driven by this insight, we propose ISPCloak, a novel optimization-free adversarial attack framework that explicitly weaponizes the ISP pipeline to mislead the judgment of deepfake detectors. Rather than relying on computationally expensive gradient perturbations, our method first employs an Invertible ISP network to project images into the RAW domain. Then, we seamlessly imprint the complex statistical priors of real cameras onto AI-generated images by injecting realistic Poisson-Gaussian sensor noise and conducting forward ISP reconstruction. Synergized with generative artifact suppression and adaptive masking, this streamlined physical simulation enables ultra-fast generation of adversarial examples. Extensive experiments show that embedding authentic physical perturbations fundamentally disrupts a broad range of current detection mechanisms, yielding universally evasive adversarial examples with imperceptible visual alterations.

AI-enabled visual perception systems are increasingly deployed in intelligent transportation infrastructure and autonomous vehicle related applications. However, physically realizable adversarial appearances pose a significant reliability challenge for these safety-critical systems. Adversarial training is effective, but repeated co-occurrence between adversarial texture and positive person instances can cause detectors to treat the texture itself as evidence of object presence, forming a patch texture shortcut. The detector may then treat texture as evidence for the target, causing false detections on texture-only inputs and weakening cross attack generalisation. We propose InsCAT, an instance-level contrastive adversarial training framework that prevents detectors from using adversarial texture as an independent decision cue. SICA aligns adversarial person features with matched clean features and separates them from texture-only negatives, while ROPO and Guard maintain online attack pressure and coordinate training. We evaluate eight independently generated attack textures on rendered nuScenes, INRIAPerson, printed garments, and three detector families. InsCAT achieves an average attack AP of 82.3% on rendered nuScenes, exceeding the strongest baseline by 11.1 points.Relative to AT-Mix, texture FPR decreases from 46.9% to 7.3%. Physical tests yield an F1 score of 96.6% and an FPR of 1.8%. Consistent gains across separately trained detectors demonstrate applicability across architectures with direct inference. The findings show that robust physical detection depends on preserving target related evidence while preventing adversarial texture from becoming an independent decision cu

With the increasing diversity of spoofing attacks, there is a growing demand for unified Face Anti-Spoofing (FAS) models capable of detecting both physical and digital threats. While existing Vision-Language Models (VLMs) demonstrate high generalization in this context, they heavily rely on complex multimodal fusion and external text encoders. In this paper, we propose DINO-VPT, a lightweight, vision-only framework leveraging hierarchical visual prompt tuning. By dynamically injecting prompts conditioned on input features via a Prompt Routing Network (PRN), our method effectively disentangles diverse spoofing artifacts without requiring multimodal fusion. Evaluations on the UniAttackData benchmark demonstrate that DINO-VPT achieves higher accuracy than state-of-the-art VLM-based methods. Our results indicate that a properly structured vision-only architecture can achieve state-of-the-art performance in unified FAS without the need for multimodal supervision.

Almost all adversarial attacks add an imperceptible perturbation to fool a model. We instead study the opposite: a large, clearly visible perturbation that causes the model to keep its original, correct prediction, even though a human would no longer recognize the image. Prior work showed such examples can be generated at scale but left three questions untested: whether humans really perform worse than the model, whether standard out-of-distribution (OOD) detection and calibration tools catch it, and whether existing defenses mitigate it. We answer all three on MNIST, CIFAR-10, and ImageNet. (i) An independent recognizer proxy drops to ~49% on CIFAR-10 while the model stays at 100% -- a gap a small human pilot (N=5) corroborates directly and that is not explained by signal loss (a matched-magnitude Gaussian control degrades recognizability faster); a CLIP zero-shot proxy confirms the gap at ImageNet scale too. (ii) Confidence- and energy-based OOD detectors and calibration are structurally blind (0% detection, ECE ~= 0), while a feature-space Mahalanobis detector flags 100% -- but is evaded by an adaptive attacker at no cost to success. (iii) No classical defense, including adversarial training (45% robust accuracy), reduces attack success (correlation with large-epsilon_l resistance r ~= 0). A mechanistic analysis further shows the attack destroys low-level texture far faster than edge/shape structure.

It is crucial to safeguard computer networks from evolving network security threats and unknown cyberattacks. An essential tool for protecting computer networks against unknown cyber threats is Network Intrusion Detection System (NIDS). However, NIDS faces a major security concern due to its susceptibility to adversarial attacks. Adversarial attacks aim to deceive NIDS by crafting and injecting adversarial examples into the system. These adversarial inputs can deceive the NIDS into misclassifying benign network traffic as malicious. We developed a resilient hybrid defense mechanism aimed to mitigate the impact of two potent adversarial attacks: Fast Gradient Sign Method (FGSM) and Carlini & Wagner (C&W) attack. Our hybrid defense approach leverages the combined strength of two heuristic defense methods: Adversarial Training (AT) and Gaussian Data Augmentation (GDA). GDA provides multi-directional defense, while AT enhances NIDS robustness against specific adversarial vectors. Under pre-attack scenarios, NIDS demonstrated good accuracy and f1-score. However, in the post-attack scenario, its accuracy significantly dropped under FGSM and C&W attacks (0.2649 and 0.4961, respectively). Our proposed hybrid defense method effectively mitigated these adversarial threats, with post-defense accuracy of 96.57% and 89.20% for FGSM and C&W attacks. We evaluated the defense strategy across a range of epsilon and confidence noise factor values (ranging from 0.0001 to 0.0009). This research provides a good direction for future researchers in the emerging area of adversarial machine learning from a security perspective.

AI-based visual perception systems are increasingly deployed in infrastructure surveillance, including roadside monitoring units, highway cameras, and smart-city pedestrian management systems. The security vulnerability of these systems to physical adversarial attacks poses a direct threat to the reliable operation of transportation infrastructure. We propose AdvSerial, a dynamic 2D--3D joint optimization framework for generating continuous high-angle physical adversarial patches against pedestrian detectors in infrastructure-based scenarios. We UV-map a boundary-aware quilted texture onto 3D garments, combine 2D digital attacks with 3D sparse- and continuous-frame rendering, and explicitly suppress person-specific semantic features while enforcing temporal continuity. A Feature Smooth Quilting strategy reduces visible patch boundaries and bounds cross-seam feature discontinuities. A serial-frame loss encourages long uninterrupted sequences of detection failures. In physical world experiments, AdvSerial achieves a 74.8% attack success rate on YOLO-v5 and degrades mean detection confidence from 84.30% to 39.38%. Experiments spanning eight detectors with different architectures demonstrate strong transferability. Notably, it achieves an $89.71$ attack success rate on YOLO-v2 and resists both patch-detection defenses (NapGuard) and 3D-temporal perception (Sparse4D-v3). The results reveal persistent, temporally consistent failure modes under high-angle surveillance, and motivate the design of motion-aware and 3D-aware defenses for security-critical infrastructure deployments.

World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generation with future world prediction. This coupling is often viewed as a source of robustness, interpretability, and safety, as a robot's action can in principle be checked against its imagined future. In this paper, we show that this assumption is fragile. We introduce BadWAM, a unified framework for modeling and evaluating World-Action Drift Attacks: a new class of WAM-specific adversarial attacks that use small visual perturbations to break the alignment between what a WAM imagines and what it executes. BadWAM characterizes this attack surface along two natural criteria: attack strength and stealthiness. When the adversary prioritizes disruption, BadWAM instantiates an action-only adversarial attack, which directly drives the model toward task-failing actions. When the adversary additionally prioritizes stealth, BadWAM instantiates an imagination-preserving adversarial attack, which seeks to induce harmful action shifts while keeping the model's predicted future close to its clean imagination. Together, these two attacks capture a spectrum of WAM-specific failures: from overt action hijacking to stealthier cases where the model appears to imagine a plausible future but executes a desynchronized action. We evaluate BadWAM across different variants of WAMs. Results show that our attacks substantially reduce task success rates under closed-loop execution. For example, our action-only attack reduces the model performance from 96.5% to 43.1% success. The results of our imagination-preserving attack further exposes a WAM-specific vulnerability: moderate future-preserving regularization can maintain strong attack performance while reducing future imagination drift.

Machine learning models are increasingly adapted in various domains. However, adversarial examples pose a significant threat to the reliable deployment of these models. In recent years, some powerful adversarial example attacks have been proposed for the fast and query-efficient generation of adversarial examples, even in black-box scenarios, highlighting the need for scalable, low-cost, and powerful defenses. In this work, we present two contributions to the domain of black-box adversarial example attacks and defenses. First, we propose Random Logit Scaling (RLS), a randomization-based defense against black-box score-based adversarial example attacks. RLS is a plug-and-play, post-processing defense that can be implemented on top of any existing ML model with minimal effort. The idea behind RLS is to confuse an attacker by outputting falsified scores resulting from randomly scaled logits while maintaining the model accuracy. We show that RLS significantly reduces the success rate of state-of-the-art black-box score-based attacks while preserving the accuracy and minimizing confidence score distortion compared to state-of-the-art randomization-based defenses. Second, we introduce a novel adaptive attack against AAA, a SOTA non-randomized black-box defense against black-box score-based attacks that also modifies output logits to confuse attackers, demonstrating its vulnerability against adaptive attacks.

Vision-language pre-trained models (VLPs) are widely used in real-world applications. However, they remain vulnerable to adversarial attacks. Although adversarial detection methods have demonstrated success in single-modality settings (either vision or language), their effectiveness and reliability in multimodal models such as VLPs remain largely unexplored. In this work, we study the geometry of VLP embedding spaces and observe structured anisotropy that differs from unimodal vision models. Our theoretical analysis shows that under this anisotropic structure, adversarial attacks increase the expected geometric separation between clean and adversarial examples (AEs). Specifically, we demonstrate that AEs consistently exhibit greater expected distances to randomly sampled points than their clean counterparts, indicating that AEs tend to push representations out of manifold regions. Building on these insights, we propose GeoDetect, which leverages these off-manifold deviations via geometric scores to identify AEs. Through comprehensive evaluations, we show that our approach reliably detects AEs across diverse VLP architectures and threat settings, covering unimodal and multimodal attacks as well as adaptive attacks, thereby providing a robust and practical approach to improving the safety and reliability of these models.

Multimodal Large Language Models (MLLMs) are increasingly deployed for nuanced content safety and moderation tasks, yet they remain vulnerable to adversarial attacks and out-of-distribution edge cases. Traditional active learning and manual annotation fail to scale against the complexity and volume of novel multimodal threats. In this paper, we propose an automated, agentic red-teaming framework that systematically synthesizes difficult examples using an iterative strategy that proposes novel hypotheses as well as mutating on past attempts. Leveraging a multi-agent architecture that consists of a high-reasoning Architect agent, an advanced image generator, and a multi-level verification committee of LLM raters, our system autonomously uncovers boundary-pushing violations and ambiguous policy edge cases without any human intervention. By employing these carefully synthesized adversarial examples as in-context demonstrations via test-time Retrieval, we substantially improve the target model's robustness, reducing the False Negative Rate (FNR) from 41.2% to 24.5% in a public image safety benchmark without relying on any human labeling.

Deep learning models for online handwriting recognition have been shown effective and are increasingly deployed in practical applications. However, their vulnerability to adversarial attacks is still a challenge. Existing adversarial methods are predominantly designed for image-based inputs and typically rely on additive spatial perturbations. When applied to online handwriting, which is inherently represented as a time series of pen trajectories, such perturbations often introduce high-frequency jitter and visibly unnatural stroke artifacts. In this work, we propose a novel adversarial attack framework for online handwriting recognition based on salience-guided temporal editing. Instead of adding noise, the proposed method generates adversarial examples by inserting and deleting points at time steps selected according to temporal salience, preserving the shape and smoothness of the original handwriting. Temporal salience is estimated using gradient-based activation mapping, which guides edits toward time steps that strongly support the original class prediction. We evaluate the proposed approach on the Unipen and CASIA-OLHWDB datasets under both white-box and one-shot black-box attack settings. Experimental results demonstrate that while conventional image-based attacks achieve strong white-box performance, they exhibit poor transferability across models. In contrast, the proposed temporal editing attack achieves stronger one-shot black-box transferability while preserving the visual structure of the handwriting. These results indicate that temporal editing is a relevant threat model for online handwriting recognition, particularly in one-shot black-box transfer settings.

In this paper, we challenge the prevailing view that information dependency (including rote memorization) drives training data exposure to image reconstruction attacks. We show that extensive exposure can persist without rote memorization and is instead caused by a tunable connection to adversarial robustness. We begin by presenting three surprising results: (1) recent defenses that inhibit reconstruction by Model Inversion Attacks (MIAs), which evaluate leakage under an idealized attacker, do not reduce standard measures of information dependency (HSIC); (2) models that maximally memorize their training datasets remain robust to MIA reconstruction; and (3) models trained without seeing 97% of the training pixels, where recent information-theoretic bounds give arbitrarily strong privacy guarantees under standard assumptions, can still be devastatingly reconstructed by MIA. To explain these findings, we provide causal evidence that privacy under MIA arises from what the adversarial examples literature calls ``non-robust'' features (generalizable but imperceptible and unstable features). We further show that recent MIA defenses obtain their privacy improvements by unintentionally shifting models toward such features. To establish this causal relationship, we introduce Anti Adversarial Training (AT-AT), a training regime that intentionally learns non-robust features to obtain both superior reconstruction defense and higher accuracy than state-of-the-art defenses. Our results revise the prevailing understanding of training data exposure and reveal a new privacy-robustness tradeoff.

Despite progress in Embodied AI, Vision-and-Language Navigation systems remain vulnerable to adversarial visual disturbances. Most existing methods rely on white-box access to target model gradients, which is often unrealistic for real-world deployed systems and computationally exhaustive due to recursive backpropagation for optimization, limiting their applicability. While previous black-box methods predominantly target single-step, instantaneous decision tasks, they struggle to handle the task complexities and temporal dependencies. This highlights the need for a gradient-free attack method that can effectively disrupt the multistep sequential perception-action loop using only observable inputs and outputs. Therefore, we propose AdvNav, a behavior-guided black-box adversarial attack framework that disturbs an agent's first-person views during navigation. To construct an informative surrogate objective for effective optimization guidance in gradient-free search under the black-box setting, we design a dual-granularity behavior-based feedback, aggregating a trajectory-level performance score representing overall navigation degradation, an action-level reward score considering the potential decision risk, and a deviation indicator, all of which are extracted from the agent's self-output behaviors. This feedback guides a hybrid optimization strategy that heuristically tunes perturbation strength via adaptive updates and evolves noise spatial structure genetically, to iteratively discover the most disruptive noise configuration. Evaluated against Transformer-based HAMT and LLM-based MapGPT with two types of backbones on R2R dataset, AdvNav achieves 49.70/65.96/87.30% Attack Success Rate. The result demonstrates the effectiveness and generality of AdvNav, reveals critical perception vulnerabilities and offers insights for the design of future resilient VLN models.

Vision Language Models (VLMs) offer powerful multimodal ability but also expose users to text-based privacy attacks where adversaries crawl online photos and query VLMs to extract sensitive attributes. Existing reversible adversarial example (RAE) methods protect images in purely visual tasks but fail in multimodal settings, and current adversarial examples on VLMs rely on high frequency noise that severely degrades visual quality. We propose CloakDiff, the first framework for reversible, high fidelity privacy protection against text-based query attacks in VLMs. CloakDiff produces imperceptible adversarial examples by combining diffusion based adversarial editing with an invertible network that embeds the original image for lossless recovery. It perturbs both pixel space embeddings and manipulates latent cross attention maps to ensure strong cross-model and cross-prompt transferability while preserving global visual structure. To further enhance fidelity, we design EDM Heuristic Sampling, a principled diffusion schedule for adversarial guidance. Experiments on multiple datasets and VLMs demonstrate that CloakDiff delivers multimodal privacy preservation with high visual quality and reversibility.

We show how an adversarial model trainer can plant backdoors in a large class of deep, feedforward neural networks. These backdoors are statistically undetectable in the white-box setting, meaning that the backdoored and honestly trained models are close in total variation distance, even given the full descriptions of the models (e.g., all of the weights). The backdoor provides access to invariance-based adversarial examples for every input, mapping distant inputs to unusually close outputs. However, without the backdoor, it is provably impossible (under standard cryptographic assumptions) to generate any such adversarial examples in polynomial time. Our theoretical and preliminary empirical findings demonstrate a fundamental power asymmetry between model trainers and model users.

The growing applications of facial recognition systems are accompanied by increasingly diverse security threats. Existing datasets lack detailed textual descriptions of forgery cues, leading most prior methods to treat face attack detection primarily as a visual recognition task. In this paper, building upon the large-scale MS-UFAD dataset which contains over 8 million attack images, we enrich each image with a fine-grained textual description of forgery cues. Furthermore, we propose a Dual Alignment Forgery Network(DAF-Net) to better leverage these textual information. Extensive experiments demonstrate that our approach extracts more generalizable and semantically meaningful forgery representations from attack images, outperforming both vision-only methods and approaches based on coarse-grained descriptions.