Adversarial Examples

Vision Transformers (ViTs) remain vulnerable to localized adversarial attacks, e.g., adversarial patches, while recent test-time defenses mitigate them by suppressing image tokens with abnormally high attention scores. These defenses exploit a strong coupling between attention and adversarial effectiveness: adversarial tokens often need to attract substantial attention to influence the prediction. We introduce adversarial decoys, independently optimized image patches that redirect the attention, and therefore related defenses, toward selected target tokens. Rather than jointly optimizing misclassifications and defense evasion, our approach decouples the two objectives: the original adversarial region induces the incorrect prediction, while a separate decoy manipulates the attention ranking used by the defense. A layer-wise objective increases target-token attention and promotes these tokens above competing non-target ones. Since the decoy is optimized independently of the underlying attack, the method is attack-agnostic and can be easily integrated with any existing adversarial patch attack. Experiments on ImageNet across multiple ViT architectures and attacks show that decoys can redirect high attention scores away from the true adversarial region while preserving much of the attack effectiveness. These results reveal a fundamental limitation of using attention magnitude as an indicator of adversarial relevance.

LiDAR semantic segmentation is a key perception task in autonomous driving, where false predictions can affect downstream planning and safety-critical decision-making. Although adversarial attacks, and specifically adversarial examples, have been widely studied for image classification and 3D point cloud segmentation, unrestricted adversarial examples remain largely unexplored in the space of 2D range images, which are projections of 3D point clouds. The proposed method is, to the best of our knowledge, the first diffusion-based unrestricted adversarial attack against 2D range-image segmentation, using adversarial guidance from a segmentation loss. By applying guidance directly during sampling, the method produces unrestricted adversarial examples that remain close to the learned LiDAR data manifold while inducing structured segmentation errors. Experiments on the SemanticKITTI dataset using RangeNet++ and CENet segmentation networks demonstrate that the attack provides adjustable degradation across guidance strengths and transfers across segmentation architectures. Compared with norm-bounded FGSM and SegPGD baselines, the proposed attack offers a distinct effectiveness-realism trade-off, achieving controllable white-box and transfer degradation while maintaining competitive distributional and visual realism.

Infrared vision-language models are increasingly used for perception under low-light and adverse visual conditions, yet their robustness to localized structured perturbations remains underexplored. Existing infrared adversarial studies mainly focus on object detectors, leaving the security of infrared vision-language models less systematically examined. We present InfraQR, a QR-inspired structured patch attack for infrared vision-language models. Unlike localized attacks that attach perturbations to the target object, InfraQR places a compact structured patch along image boundaries and optimizes learnable grid cells through surrogate CLIP-style encoders. The resulting patch has a near-binary structured appearance, but is not required to be a valid or machine-readable QR code. We evaluate InfraQR on infrared classification, caption transfer, and question-answer-aware visual question answering (VQA) tasks. On a 300-image infrared benchmark, InfraQR sharply reduces the accuracy of multiple CLIP-style classifiers, including reducing OpenAI CLIP accuracy from 98.67% to 0.70%. The generated adversarial images also transfer to black-box captioning and VQA models, causing semantic degradation in captions and more error-prone answers under GPT-5.4-based evaluation. These results show that infrared vision-language models remain vulnerable to structured edge-placed perturbations, motivating further study of cross-task robustness beyond direct object occlusion.

Vision-language models (VLMs) are increasingly deployed on infrared (IR) remote sensing imagery in security-critical settings, yet their adversarial robustness remains unexamined. We present AirflowAttack, to our knowledge the first adversarial attack for IR remote-sensing VLMs and the first to weaponize thermal-airflow turbulence as the perturbation prior. A lightweight generator synthesizes a single input-agnostic perturbation regularized toward physically plausible airflow patterns. Optimized on one surrogate CLIP model, it attains a mean zero-shot scene-classification attack success rate (ASR, the fraction of samples whose top-1 class changes) of 48.5% across five diverse CLIP backbones, far exceeding four IR-specific physical baselines (27.7--37.0%). Applied to six state-of-the-art VLMs, it cuts scene-classification accuracy by up to 38.2% relative, yet paradoxically makes some models more confident in their IR analysis, confabulating the perturbation as genuine thermal evidence such as temperature gradients and convection. Ablations show the airflow prior raises physical plausibility at no measurable cost to attack success. Together with a benchmark spanning eleven models and four tasks, these findings expose critical vulnerabilities in the rapidly expanding IR VLM ecosystem.

Poisoning attacks against public datasets lead to major concerns, such as (i) misclassification of perceived objects when the poisoned data is used for training and (ii) embedding of backdoors that may eventually be triggered later on, when specific conditions in the system apply over the learned models. Its impact over data augmentation models is unclear. While data augmentation reduces the likelihood of poisoning attack success, some valid questions remain. Is data augmentation affecting the impact of poisoning attacks? can it increase the number of poisoned samples or injected backdoors? We explore in this paper some of these questions. We assess the effects of augmenting poisoned 3D point cloud datasets and validate that poisoning is able to evade the sanitizing nature of augmentation techniques when using the concrete case of Generative Adversarial Network (GAN) techniques to exemplify the case of data augmentation processing. We also validate that poisoning propagates over the augmented datasets and perturbs the decision made by general-purpose classifiers, in the end. All the experimental material (including tools, datasets, and classifiers) is publicly available, to facilitate reproducibility and to foster further research in the topic.

Deepfake image detection is currently served by three fundamentally different paradigms: commercial APIs, zero-shot vision-language models (LLMs), and open-source detectors. Despite their widespread use, these paradigms are rarely evaluated under a common protocol, making direct comparison difficult. We introduce VendorBench-100, a cross-paradigm benchmark that evaluates 36 representative models using a single adversarial 100-image corpus, a unified output schema, and a common evaluation framework. To ensure reliable assessment under the corpus's intentional class imbalance, models are ranked primarily by the Matthews correlation coefficient (MCC), with ROC-AUC reported as a threshold-independent measure of ranking ability. Rather than maximizing dataset size, VendorBench-100 emphasizes challenging real-world scenarios through a curated taxonomy of eight edge-case families, including face swaps, text-to-video stills, AI photo edits, avatar compositing, opaque-provenance images, and compressed research frames. Our evaluation shows that commercial APIs achieve the strongest median performance, followed by vision LLMs and open-source detectors. However, individual open-source models remain competitive with the best vision LLMs. More importantly, we identify a consistent divergence between ranking ability (ROC-AUC) and operating-point quality (MCC), demonstrating that strong score discrimination does not necessarily produce reliable default-threshold decisions. This metric disagreement, rather than any single leaderboard ranking, is the central finding of the benchmark. We release the complete evaluation framework and benchmark results to support reproducible future research. The source code and data are available at: https://github.com/sharayu-20/vendorbench-100

Model-specific adversarial attacks have been extensively studied. We study a different failure mode: naturally occurring statistical signals in vision data that can behave like backdoor-like triggers without being maliciously inserted. We call these signals statistical adversaries. We analyse Imagenet to find patterns that are strongly linked to certain labels. We then use statistical controls to remove random correlations from our candidate signals. Finally, we demonstrate that these signals directly and predictably alter model predictions. These statistical adversaries are more targeted than generic corruptions and transfer across different model architectures. This suggests that some vulnerabilities are driven by dataset structure and distribution rather than a single model's idiosyncrasies. We conclude that ordinary datasets can contain exploitable adversarial surfaces even in the absence of poisoning, and suggest that dataset audits should treat spurious structure not only as a source of bias or interpretability failure, but also as a latent attack surface for vision models.

Vision and vision-language models rely on high-level visual representations that are increasingly used across recognition, retrieval, and multimodal reasoning pipelines. However, recent advances in generative modeling have shown that such features can often be inverted, enabling realistic reconstructions of the underlying image and raising significant privacy risks. We revisit this problem through the lens of reconstruction and propose TrustCLIP, a reconstruction-driven framework that treats a feature-conditioned generator as an explicit privacy adversary. TrustCLIP learns a projection between encoder features and downstream modules that is explicitly optimized to degrade the reconstructions produced by generative attackers while retaining the necessary signals for downstream tasks. Unlike prior defenses that rely on discriminative privacy metrics, TrustCLIP directly optimizes against a generative reconstruction attacker, targeting a threat not captured by standard evaluation protocols. We demonstrate its effectiveness in both conventional classification and multimodal large language model pipelines. Across these settings, TrustCLIP consistently reduces the fidelity of generative inversions while maintaining downstream task performance. Project page: https://atnikos.github.io/trustclip/

Adversarial attacks guide and provide additional training and test data for both adversarial training and adversarial robustness validation, and expose the 'piecewise linearity' of deep learning based models. Since adversarial attacks and adversarial robustness are mathematically defined problems that can be optimised directly with end-to-end differentiable search, adversarial robustness is more widely applicable than other robustness metrics such as corruption and perturbation robustness, and new kinds of adversarial attacks are beneficial for robustness testing. Attacks are targeted or non-targeted depending on whether the image is modified to misclassify to a particular class or to any incorrect class; we focus on the non-targeted setting. Finding the optimal input data points and hyper-parameters for generating non-targeted adversarial attacks remains a challenge for current methods like the Fast Gradient Method, Basic Iterative Method and Virtual Adversarial Method. We propose a new method, the "Binary Iterative Method" (BinIM), which uses a divide-and-conquer paradigm to optimise parameters and hyper-parameters for the generation of non-targeted attacks. We compare our method to other gradient-based adversarial attacks evaluated over pre-trained networks (InceptionV3, InceptionV2, ResNet V2 152) on classification tasks. On 1000 randomly-sampled images from the standard ImageNet dataset, the Binary Iterative Method outperforms all other gradient-based methods, qualitatively making the classifier misclassify with confidence up to 0.995 while reducing the probability of the true label to 2.21e-09 (approximately 0).

AI-generated images have proliferated rapidly, motivating extensive research. Most existing AI-generated image detectors are developed and evaluated under image-free generation paradigms, such as noise-based or text-guided generation. However, image-conditioned generation has become increasingly important in practical applications, as it enables more fine-grained control over generated content. Detecting AI-generated images across these two paradigms creates a critical cross-paradigm detection problem that has long been overlooked. To study this problem, we construct ConImageGen, a benchmark for cross-paradigm AI-generated image detection. Evaluations on ConImageGen show that existing detectors fail to generalize reliably across image-free and image-conditioned generation. To address this failure, this paper identifies a cross-paradigm forensic cue and provides a new perspective for generalized AI-generated image detection. Specifically, by suppressing semantic interference, we visualize, for the first time, semantics-irrelevant texture patterns across generation paradigms. These patterns exhibit structured local-global texture relations, indicating a generalizable form of forensic evidence. Motivated by this finding, we shift the focus from directly exploiting explicit artifacts to modeling texture relations and propose DTS-Det, a detection framework that captures and leverages such relations for generalized AI-generated image detection. Extensive experiments validate the effectiveness of our method. DTS-Det achieves state-of-the-art performance across diverse evaluation settings, reaching 99.6% ACC on ConImageGen with a 10.5% gain over the best baseline. It also achieves 93.2%/94.1% ACC in cross-dataset evaluation on PicoBanana/RAID and maintains detection rates of 95.2%/88.1% under reconstruction attacks and black-box adversarial attacks, respectively.

Adversarial attacks on motion planning are crucial for evaluating and quantifying the intrinsic robustness of robotic manipulation. However, existing approaches are typically limited by restrictive exact-pose objectives and their reliance on planner-in-the-loop queries. To address these limitations, we propose a planner-agnostic attack framework for tolerance-aware manipulation. Our approach shifts the evaluation paradigm to task-level feasibility over goal regions, efficiently inserting adversarial obstacles without requiring oracle access to the victim system. Offline, we characterize the robot's intrinsic workspace capabilities via a kinematic occupancy heatmap, which encodes the density of feasible trajectories and robustness priors without invoking a specific planner. Online, we formulate the attack as a budgeted maximum-coverage optimization, strategically deploying obstacles subject to explicit geometric constraints to occlude the solution space. Extensive experiments across simulation and real-world scenarios demonstrate that our method reliably induces planning failures, significantly outperforming planner-in-the-loop baselines in both computational efficiency and attack efficacy.

Large Vision-Language Models (LVLMs) exhibit remarkable vision-language capabilities and are increasingly deployed in real-world applications such as personal assistants, document analysis systems, and embodied agents. However, their dual-modal attack surfaces make them vulnerable to jailbreak attacks. Existing LVLM jailbreaks rely on simple designs, e.g., short text and out-of-distribution images. Nevertheless, recent advancements in both large language model backbones and multimodal mechanisms undermine these attacks, particularly their transferability among model architectures. To overcome this limitation, we propose a novel information overloading method that is equipped with both extensive text and multi-dimensional image attacks. These components are arranged in recursion-based image-typography layouts to exponentially increase multimodal information complexity. This overloading approach amplifies the cross-modal processing required, which undermines the safety alignment in LVLMs. Extensive experiments on both open-sourced and commercial LVLMs establish our method as a new state-of-the-art LVLM jailbreak attack. On open-source models, our method achieves an average ASR of 88.6%; on commercial LVLMs, it reaches an average ASR of 84.0%, exceeding the best baseline by 48.7%. Moreover, our prompts optimized on open-source surrogate models transfer effectively across model families. Beyond empirical results, we probe the safety-critical information flows within victim LVLMs. Our observations reveal that complex image-typography compositions induce intensified cross-modal processing and reduce the model's certainty in generating refusal responses. Together, these findings highlight information overloading as a practical and emerging safety risk for real-world LVLM deployments, underscoring the need for stronger defenses against complex multimodal jailbreak inputs.

As Large Language Models (LLMs) and agentic systems become integrated into real-world applications, ensuring their safety and security is critical. Guardrail systems that detect and block malicious instructions sent to and from an LLM are an essential component of AI security. However, researchers conducting black-box adversarial emulation against production AI systems often struggle to determine whether a guardrail block or an LLM rejection has occurred. This distinction is important because the techniques used to bypass guardrails can differ substantially from those used to bypass LLM safety alignment, and has a material impact on attack technique selection and optimization. We propose the first black-box guardrail reconnaissance methodology, which detects the presence of a guardrail within a target AI system through behavioral monitoring of HTTP, lexical, and timing signals, assuming only black-box access and zero prior knowledge of the guardrail or AI system. Experiments demonstrate that our approach detects guardrail presence with 100% accuracy, with statistically significant behavioral separation between benign and malicious interactions (q < 0.001). Our approach further identifies the content categories a guardrail is designed to block, and distinguishes guardrail blocks from LLM rejection on unseen prompts with an average F1 score of 98%.

Face-swapping deepfakes pose an escalating threat to personal privacy by enabling unauthorized identity manipulation. While adversarial approaches have demonstrated success against black-box face recognition (FR) models, their applicability to face-swapping scenarios remains underexplored. In particular, reliance on fixed or random targets yields ambiguous latent guidance, and the lack of explicit spatial constraints causes perturbations to spill into identity-irrelevant regions. These issues are further exacerbated by identity-style disentanglement, which suppresses adversarial signals during deepfake generation. In this paper, we present Phantom, a unified face-swap deepfake protection framework that jointly constrains perturbations in latent and spatial domains. Phantom adaptively synthesizes identity-shifted yet attribute-preserving targets to guide identity-aware latent optimization, and applies masked perturbations confined to semantically relevant facial regions. Extensive experiments on state-of-the-art face-swapping deepfakes demonstrate that Phantom improves protection success rates in dodging scenarios by 27.8%, 25.6%, and 16.6% on UniFace, INSwapper, and SimSwap, respectively, while also enhancing visual quality. Furthermore, Phantom generalizes to impersonation scenario, yielding up to 10.2% higher protection while improving perceptual fidelity. These results underscore the effectiveness of jointly leveraging latent and spatial constraints for robust and coherent facial privacy protection.

Speech conveys rich emotional information. As Speech Emotion Recognition (SER) is usually deployed in privacy-sensitive and reliability-critical environments, adversarial attacks on SER have attracted increasing attention. Existing sparse attacks control the number of perturbed elements, yet, they often lack explainability guidance and explicit measures of explanation consistency. A unified treatment of sparsity and magnitude constraints is also uncommon. In addition, transferability across attack families and target models remains limited. Hence, we propose a SalIency-Guided sparse Mask Attack (SIGMA). On self-supervised speech features, we use post-hoc explainable artificial intelligence (XAI) techniques to produce saliency maps and identify the scope of the mask, and then restrict magnitude-bounded updates to this mask. The mask is computed once and can be reused across models and different sparsity attacks to amortise cost. We evaluate on the IEMOCAP and TESS datasets. Under matched budgets and across multiple sparse-attack settings, SIGMA maintains competitive attack success rates, navigating a conscious trade-off between attack efficacy and explanation consistency. SIGMA therefore provides an efficient and interpretable framework for analysing the vulnerability and explanation behaviour of SER models under structured perturbations.

The training-free integration of expert models via model merging has exposed significant security risks, enabling free-riders to combine specialized models without authorization. Recent works propose parameter-level defenses that employ linear parameter transformations to neutralize this threat. In this paper, we systematically analyze such defenses and reveal that their protected task vectors are inherently small in magnitude. Consequently, the protected weights remain overwhelmingly dominated by the pretrained model. Based on this observation, we designate the pretrained model as a static reference anchor and propose the Anchor-Guided Attack (AGA) to circumvent existing safeguards. Specifically, AGA aligns the protected model with this anchor to recover the transformation matrix analytically. Extensive evaluations validate that AGA consistently bypasses both individual and composite defenses under realistic defense-agnostic scenarios. Furthermore, we provide Anchor-Repulsive Fine-tuning (ARF), a defense method to mitigate the anchor dominance leveraged by AGA. Empirical results confirm that ARF effectively defeats the proposed attack. Our code is available at https://github.com/krumpguo/secure-merge-attack.

Adversarial attacks pose a challenge to the reliability of deep learning models, motivating effective detection methods. Existing techniques often rely on attack-specific assumptions, access to adversarial samples, or knowledge of the underlying classifier (white-box). We propose $A^4D$ Attack- and Architecture-Agnostic Adversarial Detector, a completely black-box, zero-shot adversarial attack detection framework that utilizes prompt-based similarity scores derived from CLIP. To the best of our knowledge this is the first attempt to utilize CLIP for such a task. The method is based on two key observations: (i) CLIP is sensitive even to small imperceptible non-semantic perturbations; (ii) The shift in CLIP embedding space is not arbitrary and can be used as a robust attack indicator. Experiments across multiple attacks, datasets and classifiers validate that $A^4D$ achieves SOTA detection results in the attack-agnostic and classifier-agnostic setting.

The structural vulnerabilities of point cloud-based 3D object detectors remain poorly understood. Prior work has studied adversarial robustness primarily on isolated 3D object models, while recent LiDAR spoofing attacks target richer and more realistic driving scenes but focus mainly on physical realizability rather than understanding detector behavior or attack efficiency. In this work, we investigate how LiDAR-based detectors rely on spatial evidence in complex scenes and whether these reliance patterns can be exploited to induce failures more efficiently. To this end, we propose an explainability-guided adversarial analysis methodology. We introduce the Saliency-LiDAR (SALL) method, which aggregates Integrated Gradient attributions across scenes to produce universal saliency maps for LiDAR-based 3D object detectors. Guided by these maps, we design the Explainability-aware Frustum Attack (EFA), which selectively perturbs only the most influential frustums rather than uniformly attacking entire object regions. Experiments on KITTI and nuScenes, across detectors such as PointPillars and SECOND, show that EFA reduces detection recall by more than 15 percentage points while requiring 25-50% fewer perturbed frustums than the state-of-the-art non-saliency-aware baseline. These findings reveal that modern 3D detectors concentrate discriminative evidence in a small subset of spatial regions, exposing a structural robustness vulnerability in current LiDAR perception systems. Our code is released at https://github.com/SecMindLab/Saliency_LiDAR.

The application of graph data in numerous disciplines raises the need for gathering and analyzing huge volumes of data, some of which is private and sensitive. The non-Euclidean nature of the graph data makes the analysis computationally challenging, leading to the use of Graph Neural Networks (GNNs) in the age of AI. GNNs may inadvertently leak sensitive data they are trained on, which raises serious data security issues, including the model inversion attack. In this study, we analyze GNNs' vulnerabilities by introducing two novel graph inversion (i.e., reconstruction) attacks: graph-label conditioned (GLC) attack and embedding-label conditioned (ELC) attack, utilizing targetmodel predictions and their intermediate representations, respectively. We perform a comprehensive analysis of our introduced privacy attacks and compare them with existing baselines across three benchmark graph datasets (i.e., NCI1, PROTEINS, and AIDS) and four graph distributional/structural metrics (i.e., FGD, EGD, MMD, and GKS). Our work demonstrates that an adversary can use the generator-discriminator technique to reconstruct high-quality graphs in real-world black-box attack scenarios against GNNs. Additionally, we present a variant of our attacks (Ours--) with 50% reduced queries, achieving good or comparable reconstruction attack performance. In addition, we show that GNNs are highly vulnerable to privacy attacks, varying Laplacian noise-scales.

Statistical adversarial detection (SAD) treats detection as a two-sample test. Given a reference set of clean examples (CEs) and a batch of queries, potentially containing an unknown mixture of CEs and adversarial examples (AEs), SAD decides whether the query distribution drifts away from the CE distribution while controlling the false-alarm rate. Existing SAD-based methods mainly use maximum mean discrepancy (MMD) to measure the distributional discrepancy. However, MMD's distributional properties limit its ability to capture characteristic uncertainty patterns of AEs that are crucial for detection: AEs typically exhibit abnormal feature spread (i.e., global uncertainty) and instability under perturbations (i.e., local uncertainty). To close the gap, we propose Uncertainty-aware Statistical Adversarial Detection (USAD), which explicitly captures these uncertainty patterns with two new statistics: (1) Variance Discrepancy (VD), which measures the difference in feature spread between AEs and CEs to capture global uncertainty differences. (2) Perturbation-based Covariance Discrepancy (PCD), which compares feature covariance under Gaussian perturbations to capture local uncertainty differences. By aggregating VD and PCD, USAD achieves superior detection performances over baseline methods against various adversarial attacks, highlighting the importance of considering characteristic behaviors of AEs for effective SAD. Our code is available at: https://anonymous.4open.science/r/USAD.

Deep neural networks (DNNs) are widely applied in Network-based Intrusion Detection System (NIDS) due to their high accuracy. However, DNNs are highly susceptible to adversarial attacks, which generate malicious traffic to evade NIDS detection. Existing approaches often adapt adversarial attacks from computer vision (CV) tasks to the NIDS domain, overlooking the fundamental differences between CV and NIDS. This results in two major issues: 1) The generated network traffic may become invalid, 2) The generated traffic may lose its original attack semantics. To address these issues, this paper proposes an adversarial attack specifically designed for NIDS. Instead of directly generating flow-level features, our approach incrementally generates packet-level features to construct adversarial traffic. During the generation process, the semantic integrity of the traffic is monitored at each stage, effectively avoiding the issues of invalid traffic and semantic loss observed in existing methods. We evaluate our attack algorithm against current NIDS models using the CIC-UNSW-NB15, CIC-DDoS2019, and CIC-IDS-2017 datasets. The proposed method achieves an average evasion success rate of 92.78%, while ensuring that the generated adversarial traffic remains semantically consistent with the original malicious traffic.

Deep learning models have achieved impressive performance across various fields but remain vulnerable to adversarial inputs, particularly in NLP, where such attacks can have significant real-world consequences. Adversarial attacks often involve small, semantically similar token replacements to fool NLP models, and recent methods have become more precise by targeting specific vulnerable words, often by exploiting some level of access to the model's internal structure. This paper proposes GAversary, a hybrid Genetic Algorithm (GA) to generate adversarial attacks on natural language models. The GA is able to treat the target model as a black box, requiring only the logit value output by the model to guide the search. GAversary differs from GAs previously proposed for this problem by using GloVe embeddings to propose word replacements (the mutation operator) to improve the semantic similarity of the adversarial examples. GAversary is applied to several benchmark data sets and well-known target models. GAversary is able to substantially reduce the target model's accuracy on test data compared to the BAE and A2T attacks compared against (in the best case, reducing a 76.8% accuracy to 5.8%, compared to BAE's 27.6%). The trade-off is that GAversary perturbs just under twice as many words as the other two methods, with a slightly lower semantic similarity to the original text and around a 5% increase in run-time.

Noise-based backdoor attacks on diffusion models typically rely on input-time trigger injection, untargeted activation, and out-of-distribution target generation. Such assumptions reduce both the stealthiness and the practical relevance of these attacks. In this work, we present TEMPO-Diffusion, a targeted backdoor framework that localizes the malicious distribution shift to a temporal, in-distribution exposure. TEMPO-Diffusion supports: (i) targeted attacks on and to specific classes, (ii) multiple sub-image backdoors that reconstruct specific features within multiple, different output images and at multiple locations, and (iii) in-painting with time-conditioned triggers. To study relevant, practical security concerns in leveraging backdoored diffusion models for synthetic training data, we also introduce CALISA: a balanced, region-aware traffic-sign dataset emphasizing Canadian and U.S. road signs. Across CIFAR10, GTSRB, and CALISA, our experiments show that TEMPO-Diffusion can reliably poison class-specific synthetic data generation and induce high attack success rates in downstream classifiers trained on that data.

Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry. However, the assumptions underlying these works are rarely examined empirically, and systematic evidence remains limited. In this work, we present a systematic study of the role of input dimensionality in both the emergence and the targeted control of adversarial examples. We first analyse the scope and limitations of existing theoretical frameworks based on concentration of measure, showing that real image classes exhibit strong empirical localization, beyond what such theories typically assume. We then conduct an extensive empirical evaluation across hierarchical image datasets spanning a wide range of input dimensionalities and diverse neural architectures. Our results consistently show that adversarial examples become easier to construct as dimensionality increases. We also investigate how input dimensionality affects the additional difficulty of crafting targeted adversarial examples. In particular, we provide theoretical arguments showing that high-dimensional geometry implies that enforcing a specific target label entails only a limited additional distortion compared to untargeted attacks. We corroborate this insight through extensive experiments, demonstrating that the gap between targeted and untargeted perturbations remains small and further narrows as input dimensionality increases. While, taken together, our findings establish high input dimensionality as a fundamental factor underlying the emergence and targeted control of adversarial examples, whether this phenomenon primarily arises from the interplay between high-dimensional geometry and data distributions or from the architectural properties of deep neural networks remains an open question.

Although deep Face Swapping (FS) models may benefit the entertainment industry, they pose severe threats to privacy and security. Existing protections, including deepfake detection and adversarial perturbation, are either passive responses or ineffective to unseen subject-agnostic FS models. In this paper, we propose a transferable attack against subject-agnostic FS models named Additive Identity attack based on a Relighting function (AIR). AIR leverages reillumination and additive perturbations to mislead the identity extraction modules in subject-agnostic FS models. By using these two types of perturbations simultaneously, the attack space is extended such that stronger but more visually natural adversarial examples can be identified. To further enhance the visual quality while preserving the effectiveness of the attack, an adaptive translation-invariant operation and an illumination control scheme are designed for AIR. Unlike other methods, AIR does not require a surrogate FS model to achieve high transferability. In addition, a mathematical proof is given for the extension of the attack space. Extensive experiments using 1000 image pairs across various state-of-the-art subject-agnostic FS models, including GAN and diffusion-based FS models, show that AIR surpasses all existing attacks in terms of both attack success rate and image quality.

We introduce a large-scale, open-source dataset of pre-generated adversarial attacks for vision-language models (VLMs). The dataset is designed to be diverse, representative, and practical, extending existing benchmarks by covering 10 high-level categories and 55 subcategories of harmful intents. Our primary goal is to make adversarial data accessible to the research community, given the computational cost and complexity of generating large numbers of attacks. The dataset comprises 47 524 adversarial samples, generated using state-of-the-art attack strategies from recent literature. Our work complements existing efforts by consolidating and extending prior benchmarks from multiple established sources, resulting in 7 826 intents, and introduce an additional category to broaden coverage. This provides realistic evaluation resources for studying model robustness and alignment. Our dataset intends to enable researchers and practitioners to systematically evaluate the robustness and safety of VLMs, fine-tune attack-generation models, and develop or stress-test defensive guardrails under diverse adversarial conditions. By releasing this resource, we aim to lower the barrier to adversarial research and foster more reproducible, comprehensive, and comparable evaluations of VLM safety.

Advances in generative AI have made image falsification highly realistic, demanding trustworthy authentication systems. Existing forensic detectors can target certain forgery types but lack interpretability, while vision-language models (VLMs) provide explanations but cannot exploit forensic traces for reliable detection. We propose Forensic Knowledge Graphs (FKGs), a unified framework that integrates forensic evidence extraction, structured reasoning, and human-interpretable explanation. Our FKG structure encodes forensic traces along with their causal dependencies and links to scene content. To generate accurate FKGs, we introduce a novel forensic authentication network and an Iterative Context Refinement strategy that guides VLMs to produce faithful, grounded explanations. We also present FKG-50K, a dataset of 50,000 realistic forgeries with ground-truth FKGs. Experiments demonstrate that FKG outperforms both forensic detectors and VLMs in detection, forgery identification and localization, and forensic justification.

A primary challenge in AI safety is the existence of adversarial examples -- slightly distorted inputs that cause a neural network (NN) to misclassify. To mitigate this problem, recent research focuses on the computation of robustness certifications, which, for a given input, determine the largest distortion the input may receive without breaking the network's prediction. Robustness certifications can be interpreted as an axis-aligned hyper-rectangle (multi-dimensional intervals). Most existing approaches focus on maximizing the certification's volume, but recent intractability results prohibit the computation of volume-optimal certifications in reasonable time. We introduce the apothem measure and show how to compute apothem-optimal certifications in a linear number of calls to a NN verifier (oracle) w.r.t. the input domain's diameter. Moreover, we prove that we cannot have a volume-optimal, oracle-based algorithm, even if we discard the oracle costs. Also, we introduce dual certifications -- an interval including all instances of a class -- thus providing apothem-minimum upper bounds to a robustness certification. Further, we present the ParallelepipedoNN system, which we evaluate on the standard MNIST and Fashion MNIST benchmarks. A preliminary comparison with existing work on the same datasets reveals at least two-fold improvement w.r.t. the minimum edge length.

As machine learning models grow more influential and opaque, algorithmic fairness and explainability are critical for ensuring accountability. However, we demonstrate that these auditing mechanisms are themselves vulnerable to subtle manipulation, camouflaging the influence of protected features. While prior work on data-agnostic attacks has exposed this vulnerability, they leave behind detectable artifacts that compromise their stealth. We introduce Targeted Identity Re-Association (TIRA) attacks, a novel family of attacks that iteratively and probabilistically manipulate a model's outputs without requiring access to the model's internals or feature representations. We formalize two algorithms: Probabilistic Micro-Shuffling (PMiS), which applies localized adjacent swaps, and Probabilistic Rank-Shift Micro-Perturbation (PRSMP), which introduces small, randomized rank shifts. We empirically demonstrate that TIRA attacks are highly effective at pushing fairness metrics towards ideal values. Crucially, TIRA attacks successfully confound SHAP-based explanations, leaving effectively zero residual attribution for protected features, a major improvement over prior work.

The proliferation of IoT devices has fueled distributed edge systems to collect vast amounts of sensitive data, creating fertile ground for on-device machine learning applications. While federated learning (FL) mitigates privacy concerns by exchanging model parameters instead of raw data, we identify a critical blind spot in current research. We examine the most commonly used personalized federated learning (PFL) methods, which allow clients to maintain private, personalized models to address data heterogeneity across clients. Through systematic analysis, we reveal that PFL methods exhibit heightened vulnerability to transfer-based adversarial attacks compared to centralized learning paradigms. Wherein, malicious clients can exploit local model knowledge to craft adversarial examples that can compromise peer clients' personalized models. We establish this vulnerability through both theoretical analysis and empirical evaluation across multiple benchmark datasets, demonstrating significant accuracy drops across various PFL methods. To address this challenge, we propose a defense framework combining stochastic input noise, input-scaled trace regularization, and parameter sensitivity maximization to improve FL's robustness. Our findings establish the first systematic study of adversarial threats in PFL systems, providing both diagnostic tools and practical countermeasures.

Input Diversity (DI), a random resize and pad applied at each attack iteration, is a near-default ingredient of transfer-based attacks, widely assumed to improve transferability. We show this assumption is regime-dependent and, for adversarially trained surrogates, often reversed. Holding the attack fixed and varying only the surrogate, raising the DI probability improves transfer from standard surrogates but degrades it from robust ones: the two response curves separate like a pair of scissors, a pattern we call the Scissors Effect. On ImageNet, blind DI costs a robust source 10.3 percentage points of attack success across four architecturally diverse targets; the effect is several times smaller at 32x32. Direct measurement supports a bias-variance account: DI displaces the gradient by a comparable amount on both groups but reduces its variance only where the gradient is noisy, and robust surrogates have little noise left to average away. A gradient-consistency probe, frozen and hashed before the runs, predicts the sign of the effect on seven unseen surrogates, and we report where it fails alongside where it works. The practical consequence holds independently of the mechanism: leaving DI enabled by default understates the attack a robust surrogate can mount, and so overstates the robustness of the model being evaluated. Code: https://github.com/Avalon-S/ScissorsEffect.

The vulnerability of ML models to adversarial examples has recently emerged as a major concern. While adversarial training is one of the most effective countermeasures to this issue, its high computational cost remains an obstacle to practical deployment. Recent progress in reducing this cost has relied, in the case of linear models, on a formal equivalence between the adversarial risk and a simpler form of regularized risk. This enabled significantly more efficient training procedures, which naturally raises the question of whether such an equivalence can be extended beyond linear models. In this work, we formally show that no such equivalence is possible for two-layer networks. Our proofs proceed via a reduction to key properties that fundamentally separate the adversarial risk from any simple regularized risk which would only exhibit a weak form of data dependence. Beyond this setting, we provide empirical evidence on Wide-ResNets indicating that the same type of impossibility persists in deeper and more expressive architectures.

Deep learning-based audio classification systems, including automatic speaker verification, are vulnerable to adversarial attacks. Realistic real-time threat assessment remains difficult because optimization-based methods, such as projected gradient descent (PGD) and Carlini-Wagner, require costly iterative updates in the high-dimensional waveform domain. Generative attacks allow single-shot synthesis but often introduce perceptible artifacts or depend on computationally intensive architectures, while diffusion and autoregressive approaches incur high inference latency. To address this gap, we propose a generative attack framework operating in the continuous latent space of a neural audio codec. A conditional generator synthesizes class-specific perturbations in a single forward pass and decodes them into adversarial waveforms. Our method achieves targeted attack success rates up to 99% with sub-7 ms inference, outperforming generative baselines while reducing latency by 24x.

Adversarial camouflage in the physical world remains highly challenging, particularly under UAV reconnaissance where targets undergo continuous geometric changes and extreme illumination variations. Existing methods either optimize 2D digital perturbations that fail to generalize to dynamic viewpoints or produce visually unnatural textures that cannot be deployed in real scenarios. Therefore, we propose an end-to-end framework for adversarial camouflage generation that automatically produces wearable adversarial patterns and maintains stable attack performance in real physical environments with changing viewpoints, poses, and lighting conditions. Our method integrates UV-volume rendering with a diffusion-based texture generator, enabling consistent appearance under varying scales, poses, and lighting conditions. To ensure environmental realism, we propose an illumination color consistency estimator that extracts dominant background attributes and guides a natural texture loss to align the generated UV texture with the surrounding environment. A multi-scale dynamic training strategy further enhances robustness against viewpoint shifts and body deformation. Extensive experiments across multiple mainstream detectors demonstrate that our method achieves strong and stable physical attack performance while maintaining high perceptual naturalness, reducing human detection rates without introducing unnatural artifacts.

Recent empirical work shows that semantically equivalent paraphrases can fool financial sentiment classifiers: although a paraphrase remains close to the original under a strong reference embedding, it may shift the target model's representation enough to change the predicted class. Existing robustness theory either assumes a single-model threat model or focuses mainly on empirical attack algorithms. We develop a continuous local model of semantic paraphrase perturbations that captures this two-model structure. We show that the worst-case local displacement of the target representation, subject to a proxy-model budget, is governed by the largest generalised eigenvalue of a matrix pencil $(A,B)$ constructed from the Jacobians of the two embedding maps. The resulting attackability index $λ^*(x)$ is intrinsic to the local paraphrase geometry and the chosen embedders, yields a closed-form prediction-flip condition for affine readouts, and supports conservative population and finite-sample attackability certificates. For uniform control over classes of affine readouts, we derive a distribution-free VC bound for binary attackability indicators and a scale-sensitive margin bound based on an attackability-adjusted margin that subtracts a local geometric penalty from the standard classifier margin. We also connect the continuous theory to discrete paraphrase search, identify an asymmetry between successful and unsuccessful finite searches, and give a covering condition under which the discrete and continuous settings agree. Finally, we propose an empirical verification framework using soft-token relaxations and generated paraphrase sets to assess the local eigenvalue geometry, prediction-flip condition, and finite-search approximation on a deployed financial-text classifier.

Multimodal Large Language Model (MLLM)-based web agents provide practical, high-precision solutions for visual browser automation; however, they inherently expand the attack surface, introducing novel vision-based vulnerabilities. Existing adversarial evaluations targeting these agents frequently rely on permissive threat models and visually conspicuous artifacts. In this paper, we investigate a constrained vulnerability detection setting: a trusted web platform where the evaluator acts solely as an unprivileged third party, such as a merchant or advertiser, controlling only a semantically legitimate, spatially constrained region, such as an ad slot, a sponsored card, or a localized widget. Operating under these realistic constraints, we propose MIRAGE, a novel visual indirect prompt injection framework for targeted next-action hijacking. Our approach leverages diffusion models to generate perceptually benign adversarial images strictly confined to the attacker-controlled boundaries permitted by the trusted service provider. To maximize attack efficacy within such a restrictive setting, we introduce a robust optimization technique combining curvature-aware adversarial diffusion guidance with sparse, dark-pixel residual perturbations. Comprehensive evaluations against prominent MLLM web agent frameworks, specifically SeeAct and OpenClaw, empirically demonstrate the potency, realism, and stealth of our proposed MIRAGE.

Adversarial patches pose a practical threat to modern object detectors. Prior work shows vulnerability, but three gaps limit actionable insight: (i) few \emph{score-based black-box} attacks \emph{jointly} optimize patch \emph{location, texture, and size} under tight query budgets; (ii) success is rarely tied to the patch's \emph{visual footprint}; and (iii) evaluations often conflate EOT robustness with plain-view suppression. We present \method{}, a query-efficient, budget-adaptive black-box attack that couples a lightweight \emph{Contextual Thompson-Sampling} placer with NES-style pixel updates, growing the patch only when progress stalls. Reporting is anchored by a \emph{strict plain-image} suppression test; EOT is audited but never used as a substitute for success, and optional appearance/printability weights expose strength--visibility trade-offs. Across YOLOv5, Faster R-CNN, and YOLOS, \method{} achieves strong suppression on CNN-based detectors and substantial suppression on the transformer-based detector, using compact patches and exposing clear query--footprint trade-offs relative to fixed-size and heuristic baselines. A print--capture pilot further shows transfer across unseen physical objects and viewpoints.

Pixel-wise adversarial patches are computationally heavy and often visually detectable, limiting utility in security-critical systems. We present adversarial Voronoi camouflage that optimizes only seed-point locations under fixed, printable palettes using a soft assignment, producing structured, splinter camouflage-like patterns without additional regularization. Evaluated on person detection with COCO-style AP@[.5:.95], naive placement (Inria -> COCO) performs comparably bad, while garment-level application via segmentation mask (3DPeople) results in a significant AP drop. The attack transfers to out-of-domain backgrounds and across detector families (YOLOv9/10/11/12), indicating robustness in black-box settings. Repainting with different palettes largely nullifies the effect, and single-color tweaks show limited tolerance (<=0.17), highlighting a structure-palette coupling. The parameter-efficient, palette-constrained design improves visual plausibility while degrading real-time detector performance. Physical validation and color calibration are left for future work. Code: https://github.com/JensBayer/Voronoi This paper was originally presented at the International Conference on Military Communication and Information Systems (ICMCIS), organized by the Information Systems Technology (IST) Scientific and Technical Committee, IST-224-RSY - the ICMCIS, held in Bath, United Kingdom, 12-13 May 2026.

Visual world models (VWMs) synthesize interactive, action-conditioned rollouts from a single context image. However, it remains an open question how robust these models are to adversarial perturbations. Standard adversarial attacks fail to assess this vulnerability because attackers lack ground-truth future videos and cannot predict subsequent user controls. We introduce BadWorld, a label-free adversarial framework tailored for autoregressive VWMs that systematically overcomes both constraints. First, to bypass the need for future supervision, we propose a self-supervised velocity attack that directly disrupts the early denoising dynamics of the model. Second, to ensure the attack generalizes across unpredictable user actions, we formulate a trajectory-adaptive bi-level optimization that actively mines hard control sequences to forge control-agnostic perturbations. Evaluated on representative VWMs with continuous and discrete controls, BadWorld exposes severe structural fragility. Visually indistinguishable adversarial images reliably trigger catastrophic degradation in future rollouts, leading to incomplete denoising, structural collapse, and control inconsistency. These findings reveal critical risks for deploying VWMs in safety-critical systems while highlighting a practical mechanism for privacy protection.

Standard accuracy benchmarks evaluate whether large language models (LLMs) reach correct answers. However, they do not test whether models maintain that answer when challenged by a plausible counter-argument. We introduce a controlled protocol for evaluating answer stability: after a model answers a multiple-choice question correctly, we challenge the model's answer with a coherent argument for an incorrect option and measure whether the model flips. The setup a) isolates argumentative content from overt social pressure and b) varies argument length, self-attribution, and cross-model source. Across seven frontier models and 57 MMLU subjects, flip rates range from 17.5% to 97.3%, revealing large differences in stability that are not captured by accuracy metrics alone. We find that self-attribution consistently increases flip rates (mean 7.1pp, up to 18.7pp). Furthermore, pooling wrong-answer arguments across models and selecting the most effective one per question yields stronger adversarial challenges than relying on any single source model. From this cross-model pool, we construct MaxFlip, a curated benchmark that amplifies answer flips by up to 23.6pp over self-generated challenges. We release the protocol, challenge records, and MaxFlip to support stability evaluation alongside standard accuracy benchmarks. Materials are available at https://github.com/nafisenik/WhoFlips, https://hf.co/datasets/nafisehNik/WhoFlips.

Adversarial attacks on large language models have limited practical impact despite extensive research. Optimization-based attacks such as Greedy Coordinate Gradient (GCG) (Zou et al., 2023) produce high-perplexity, incoherent suffixes that existing defenses easily detect (Bengio et al., 2024). Moreover, attempting to enforce coherence constraints during optimization often prevents the attack from successfully eliciting the specific targeted response, resulting in low success rates against robust models. Conversely, attacks that maintain coherence often alter the semantic intent of queries; when the model complies with these altered queries, responses fail to address the adversary's original goal. In this work, we introduce Greedy Coordinate Diffusion (GCD), a novel framework that efficiently generates adversarial attacks against safety-aligned models while maintaining low perplexity and high semantic adherence to the adversary's original intent. GCD leverages the generative priors of discrete diffusion language models to guide the search for adversarial suffixes that achieve semantic coherence and adherence. Unlike GCG, GCD does not require direct gradient access, allowing it to operate in a gray-box setting. We show GCD achieves highest ASR while remaining competitive on response-quality scores, and that the constructed adversarial prompts are detected at lower rates than other methods by perplexity-based and guard-model filters.

While multimodal large language models (MLLMs) have shown strong visual reasoning abilities, serving a large model for every query is computationally expensive. MLLM cascades mitigate this cost by first querying a weak but cheaper model and deferring to a strong model when the weak model's output is unconfident. However, since the weak model's confidence directly controls compute allocation, these systems expose a new attack surface: an adversary can manipulate confidence so that their queries are consistently deferred to the strong model. Motivated by this vulnerability, we introduce the Forced Deferral Attack (FDA), an adversarial image attack that lowers the weak model's confidence and causes cascades to route queries to the strong model. FDA learns a universal border trigger by optimizing a temperature-flattened objective. This objective pushes the weak model's token distribution on triggered inputs toward less concentrated targets constructed from its clean responses. Across datasets, model families, and deferral metrics, FDA consistently increases strong-model routing while outperforming image-perturbation and prompt-injection baselines. These results show that MLLM cascades are vulnerable to attacks that manipulate compute allocation, forcing unintended strong-model usage without directly targeting answer correctness.

Targeted advertising systems can pair audiences selected by advertisers with ad units that expose visible user actions. When an interaction remains linked to the campaign that elicited it, the advertiser may receive an observation tied to a user rather than only an aggregate report. We model that channel as a noisy oracle for attribute inference. The model separates targeting predicates, exposure, interaction, and disclosure. These boundaries capture the gap between eligibility and delivery, and the gap between interaction and advertiser visibility. We build a reproducible benchmark using synthetic populations calibrated with public data, each with known sensitive labels. A generated campaign semantics layer provides topic variants and response priors. The simulator generates the ground truth, event traces, disclosed observations, and metrics. The evaluation compares Bayesian, supervised, positive and unlabeled, and adaptive attacks under common campaign and disclosure definitions. The final evaluation uses four topic variants, seven simulator seeds, and two interaction settings. Repeated campaigns with identity exposure produce measurable but bounded inference signal. At $160$ campaigns, Bayesian and supervised attacks reach about $0.64$ AUC in the main setting and about $0.65$ AUC in the higher interaction setting. Disclosure policy is the strongest control. Aggregate reporting removes the evaluated oracle input tied to users. Type filtering and randomized disclosure reduce the released signal. The result is a model, artifact, and defense evaluation method for privacy in interactive targeted advertising. The code is available at https://github.com/P-HOW/Interactive-Ad-Oracle.

Artificial Intelligence (AI) is increasingly used to automate a variety of real-world computer vision (CV) applications, such as autonomous vehicle control, facial recognition, and security cameras. Recent research has shown that acoustic vibration can induce real physical motion in cameras, interfering with their internal stabilization mechanisms. Because the motion falls outside the conditions the stabilization system was designed to handle, the system introduces artifacts into the frame, causing AI-based CV models to misclassify, miss targets, or hallucinate objects. Previous work used ultrasonic frequencies (>20 kHz) to perform short-range attacks, which limits them to short distances due to the attenuation exhibited by high frequencies. In this work, we investigate acoustic attacks using lower frequencies in the audible range (<20 kHz), and we further expand our analysis to include how various image and object features are affected by the attacks. Specifically, we performed physical experiments to demonstrate the viability of our attacks on an off-the-shelf object detection model (YOLO11) by resonating a commercially available camera with various frequencies. Based on our results, we provide insights into several factors that make an AI CV system more vulnerable to these attacks, which could help inform the development of future mitigation strategies.

Physical adversarial attacks on vision systems are typically studied through scene manipulation, such as adversarial patches or projections, where the adversary controls what the camera observes. Camera-side attacks using stickers or auxiliary optics have also been explored, but they treat attacks as image-space perturbations from designed patterns. This misses how physical imperfections interact with scene-dependent lighting and optics. We identify a threat: passive lens-side damage that is persistent yet trigger-conditioned, producing optical artifacts that bias geometric inference under particular visual conditions. We instantiate this threat through Scratch-induced Lens Adversarial Streak Hijacking SLASH, a physical-world attack caused by small scratches on a camera lens or protective cover. Scratches interact with bright light sources and specular reflections to create structured streak artifacts that distort depth cues. Since the perturbation is fixed in the optical path but triggered by the scene, it is both persistent and selective. We formulate the attack in optical space, model the scratch pattern as a trigger-conditioned optical channel, and optimize one fixed configuration across diverse viewing conditions. We evaluate SLASH on monocular depth estimation and monocular 3D object detection in digital and real-world settings. Under the fixed-scratch constraint, directional depth shifts reach up to 32% relative error for monocular depth estimation, with consistent effects on monocular 3D object detection. Physical experiments confirm transfer to real camera recordings, inducing depth shifts above the model's natural prediction baseline. These findings reveal an attack surface where benign-looking hardware imperfections act as latent, scene-triggered adversarial mechanisms, challenging assumptions about physical robustness and motivating defenses for secure vision systems.

Existing studies reveal that current backdoor defenses exhibit limited robustness and often fail against specific types of attacks. More concerningly, prevailing safety tuning strategies tend to provide only superficial safety protection, as they fall short of completely eliminating the backdoor effects. In this work, we present a novel formulation of backdoor learning and unlearning as a sequential, three-stage process from a continual learning perspective. Within this framework, we formally define complete backdoor unlearning and further derive the necessary conditions for achieving it based on the mechanism of catastrophic forgetting. Guided by these insights, we propose Blind Inversion-Backdoor Adversarial Unlearning (BI-BAU), which formulates the generation of adversarial examples satisfying the unlearning conditions as a blind inversion problem. We solve this by integrating the bi-level optimization process of adversarial training into an Expectation-Maximization (EM) algorithm framework to optimize the maximum a posteriori (MAP) objective. Furthermore, BI-BAU is extended to untargeted adversarial scenarios with unknown target classes, as well as to multi-modal contrastive learning tasks, enhancing its applicability to real-world deployment scenarios where pre-trained models may be compromised. Extensive experiments demonstrate that our method exhibits general applicability across a wide spectrum of backdoor attacks and can effectively and thoroughly eliminate the backdoor effects from a backdoor model.

Adversarial conditions such as paraphrasing and targeted style transfer sharply degrade the accuracy of machine text detectors. A document, however, carries multiple complementary signals (e.g., stylistic features, likelihood and rank-order features, and structural features), and an attack that suppresses one may leave others intact. While a parametric classifier can learn to combine these features given sufficient supervision, classifiers are prone to making confidently incorrect predictions when the distribution shifts (e.g., novel attacks or unseen language models). To address this, we propose a multi-view, non-parametric detection framework that extracts complementary feature views from the same document and aggregates per-view evidence through a Gaussian process ensemble. By aggregating evidence across views, an adversary must simultaneously defeat multiple independent axes of detection, substantially raising the cost of evasion. The Gaussian process formulation additionally provides calibrated probabilities and principled abstention on out-of-distribution inputs, supporting reliable deployment in high-stakes settings. We evaluate on three benchmarks spanning diverse generators and attacks: the DetectRL and RAID benchmarks, and the PAN2025 shared task and demonstrate that our multi-view detector maintains strong performance under the considered attacks, outperforming existing approaches against held out attacks.

Adversarial attacks on skeletal human action recognition have received significant attention. However, existing methods typically introduce noise-like perturbations that degrade motion quality post-attack, and thereby are inherently perceptible with recent advancements in S-HAR systems. We discover that this degradation stems from the gap between empirical and true risks during the optimization process of previous adversarial attacks. To address this issue, we propose an attack where adversarial motions are obtained without compromising their motion quality. To minimize the risk gap and preserve motion quality, we propose a distribution-based adversarial attack method without introducing noise-like perturbations. To faithfully evaluate the motion quality, we propose a new metric that aligns with human perception on real-world naturalness. Experiments have been conducted on the state-of-the-art S-HAR methods across two datasets, demonstrating the superiority of our method in both the attack success rate and the post-attack motion quality through qualitative and quantitative analyses. The success of our quality-preserving attack application and distribution-based method raises serious concerns about the robustness of action recognizers, highlighting the need for further enhancements in this domain.

Network Intrusion Detection Systems (NIDS) heavily utlize Machine Learning (ML) but ML models can be manipulated via adversarial attacks. These attacks add carefully crafted perturbations to network traffic data that leads to misclassifications. While prior work has demonstrated adversarial vulnerabilities in isolated settings, systematic cross-architecture as well as class and category of attack based comparisons under controlled attack conditions remain limited, leaving practitioners without clear guidance on which models to deploy in adversarial environments. This paper asks a simple question: what type of classifier architectures actually hold up when attackers try to manipulate the systems? We put three popular architectures through their paces: a 1D Convolutional Neural Network, a Long Short-Term Memory (LSTM) network, and a Random Forest (RF) ensemble. Using the ACI-IoT-2023 dataset (over 1.2 million samples spanning 12 attack types), we subject each model with FGSM and PGD adversarial attacks, which apply gradient-based perturbations in normalized feature space consistent with established adversarial ML evaluation protocols, at perturbation budgets ranging from $ε=0.01$ to $ε=0.1$. Surprisingly, Random Forest achieved near-perfect baseline accuracy (99.98%), yet collapsed catastrophically under attack, dropping 73 percentage points at the smallest perturbation we tested. CNN, on the other hand, retained 95.5% accuracy at $ε=0.01$ and degraded gracefully as perturbations increased. LSTM fell somewhere in between. These findings flip the conventional wisdom where high baseline accuracy means nothing if a model shatters at the first sign of adversarial pressure. For practitioners deploying intrusion detection in adversarial environments, we recommend CNN-based architectures and provide scenario-specific deployment guidance.

Trustworthy AI requires reliable data-processing pipelines, not only robust downstream predictive models. As an upstream component, data summarization determines which information is retained and passed to subsequent learning or decision modules. Therefore, adversarial perturbations to the summarization process can compromise trustworthy AI in an upstream manner: they may alter the selected summary, reduce its representativeness, and further degrade the utility of subsequent learning tasks. In this paper, we study adversarial attacks on continuous data summarization under similarity-level perturbations through DR-submodular optimization. We show that a class of multi-resolution image summarization objectives can be formulated as multilinear extensions of non-negative submodular set functions and satisfy DR-submodularity with $m$-weak monotonicity. We then formulate multi-target attack generation as a min-max problem, where one admissible perturbation of the similarity structure is optimized to degrade multiple target summarization models. To mitigate such perturbations, we formulate robust defense against mixed attack types as a regularized max-min problem. For both problems, we develop approximation algorithms with theoretical guarantees. Experiments on real-data and controlled clustered benchmarks show that the proposed attack is effective in representative low-to-moderate budget regimes and can induce downstream task-performance loss. The proposed defense improves the robustness--mitigation trade-off in structured settings, while also revealing the parameter sensitivity of robust protection on real data.

The widespread adoption of face recognition (FR) technologies raises serious privacy concerns, as facial data can be exploited without consent. To address this challenge, we propose Adv-TGD, a generative adversarial attack framework that synthesizes photorealistic faces capable of impersonating target identities and deceiving face recognition systems. Built upon Stable Diffusion v2.1, Adv-TGD performs per-sample LoRA fine-tuning conditioned on concise textual prompts to generate natural yet adversarially manipulated identities. Unlike conventional identity attack approaches, our method optimizes lightweight cross-attention adapters for each source-target pair within a fixed-timestep denoising process. Latent blending is constrained by a face-local heatmap mask to ensure spatially precise identity manipulation while preserving non-sensitive regions. We introduce a composite objective that integrates masked epsilon-MSE reconstruction, thresholded identity divergence in FR embedding space, directional feature alignment, and source-similarity suppression to balance adversarial attack and visual realism. Optionally, LLaVA-generated attribute prompts enhance fine-grained semantic details without reintroducing identity cues. Under the black-box evaluation protocol, Adv-TGD attains an average attack success rate (ASR) of 85.90% across IR152, IRSE50, MobileFace, and FaceNet, surpassing the semantic SOTA baseline Adv-CPG by 6.25 points, the diffusion-based makeup method DiffAIM by 3 points, and the noise-based P3-Mask by 16 points. Despite its strong attack efficacy, Adv-TGD preserves high visual fidelity (PSNR = 28.18 dB, SSIM = 0.981). Furthermore, we demonstrate the flexibility of our framework by successfully extending it to in-the-wild datasets (LADN), general object classification (ImageNet), and transformer-based diffusion models (FLUX.1).

While existing AI-generated image detectors report high performance, we identify that this is largely driven by a critical prediction asymmetry: a bias toward the real class that severely limits sensitivity to generated content, especially under standard post-processing operations such as compression and resizing. We hypothesize that this stems from the model's reliance on spurious features, distracting signals that obscure true generative artifacts. To address this, we propose DEAR (Dissect and Prune), which leverages inpainted images to identify and prune these interfering components. Specifically, we find that features strongly aligned to either inpainted or non-inpainted regions are less robust to post-processing. By measuring the alignment between channel activations and inpaint masks, DEAR removes features at both extremes, retaining only those that capture genuine generative artifacts. Experimental results demonstrate that our approach significantly enhances robustness against unseen generators and post-processing, effectively mitigating the prediction asymmetry. Our code is available at https://github.com/dahyedahye/dear.

Large language model (LLM)-powered content moderation systems are a critical defense against harmful online content. However, they operate primarily on tokenized text and often overlook visual cues that humans naturally use when interpreting content. We show that this limitation creates a fundamental vulnerability: content readily recognized as harmful by humans can evade automated moderation. To systematically study this problem, we introduce Human-Perceptible Adversarial Attacks (HPAA), which embed harmful expressions into otherwise benign text using visually salient typographic manipulations. HPAA strategically combines features such as spacing, emphasis, and spatial arrangement to preserve human recognition while reducing machine detectability. Operating in a black-box setting with a small query budget, the attack automatically generates evasive content without model access or gradient information. We evaluate HPAA on multiple datasets and thirteen widely deployed moderation systems, including commercial APIs and state-of-the-art open-source guardrails. With only three detector queries, generated attacks achieve over 86% human recognition while keeping detection rates below 1% across evaluated systems. We further identify the typographic factors driving successful evasion, analyze why current moderation architectures fail to capture these signals, and discuss practical defenses. Our findings reveal a fundamental blind spot in current LLM-based moderation systems and motivate moderation approaches that better align with human perceptual understanding.

Self-supervised data curation provides a pathway to scaling and improving the generalization capabilities of machine learning models. By leveraging self-supervised learning (SSL) for data curation, the demand for massive training datasets required by foundation models can be effectively met. SSL greatly alleviates the costs associated with annotation and manual dataset curation while minimizing the need for human oversight. However, the integrity of SSL-curated datasets must be rigorously checked, as reliance on anonymous and unvetted external sources can substantially increase the risk of data poisoning. In this paper, we propose a Poisoned Data Detector (PDD), an active defense mechanism designed to ensure the integrity of SSL-curated datasets prior to foundation model training. PDDs are designed using a combination of the pretrained ImageBind model and traditional classifiers, including Random Forest (RF), k-Nearest Neighbors (KNN), Naive Bayes (NB), and Support Vector Machines (SVM). We rigorously evaluated PDDs using 176,200 images from three diverse datasets and three different adversarial attacks encompassing both in-distribution and out-of-distribution scenarios. Notably, SVM-PDD achieves superior performance for both in-distribution (Set3-Set5) and out-of-distribution (TrueFace and 140K RealFace) datasets. Our design demonstrates strong scalability and enables the rapid integration of new adversarial attack detectors through an ensemble approach.

Vertical federated learning (VFL) is a distributed learning paradigm that leverages vertically partitioned features across isolated parties without sharing raw samples; however, it remains vulnerable to active sample reconstruction attacks. Existing defenses fail to achieve a satisfactory trade-off between model utility and privacy protection, due to either suppressing task-relevant information alongside privacy-sensitive features or relying on end-to-end supervised training to converge the defense module, which exposes the model to early-epoch vulnerability. To address this challenge, we adopt a structural causal model (SCM) insight and construct CausShield. From a task-learning standpoint, causal features within a raw sample are those that are directly relevant and contributory to the learning objective, whereas non-causal features are task-irrelevant but often encode sample-specific private information, thereby facilitating reconstruction. Importantly, we lay a theoretical foundation to prove this insight. CausShield thus decomposes the shared representations between the client and the coordinating server in VFL into task-relevant and task-irrelevant components to ensure full-cycle privacy protection. Nonetheless, the decomposition is inherently challenging due to the dual objectives of preserving model utility while mitigating privacy leakage. We address this via a carefully formulated optimization problem, which is solved through unsupervised representation learning. We further theoretically prove that CausShield preserves the convergence behavior of standard VFL. Extensive experiments compare CausShield against seven SOTAs, including InvL (USENIX Security'25), and evaluate robustness against advanced reconstruction attacks such as URVFL (NDSS'25). Results demonstrate that CausShield consistently outperforms in privacy protection, model utility, and computational efficiency.

Cross-domain shifts challenge Presentation Attack Detection (PAD) on ID Cards, given the restricted data available due to privacy concerns. This work proposes a compact multimodal model, based on new generative and discriminative blocks, which combines visual and textual data for PAD on genuine and synthetic ID images. While multimodal models exhibit strong generalisation after supervised fine-tuning, they fail in zero-shot settings. Our findings underscore that model capacity and real-world data are essential for reliable PAD, while existing synthetic datasets may not reflect real-world challenges. We argue for a re-evaluation of synthetic data as a benchmark and emphasise the need for more realistic, diverse datasets to advance PAD research.

Vision-language-action (VLA) models are gaining attention in robotics, yet their robustness to adversarial attacks remains largely unexplored. Existing work shows that adversarial patches can mislead VLA-based robots but assumes full access to the entire execution trajectory, an unrealistic requirement in practice. We address this limitation by formulating a partially observable threat model, where the adversary can exploit only a short prefix of the trajectory to generate a fixed patch applied to all subsequent frames. Under this setting, we propose a two-phase framework. First, we localize the patch using the model's attention maps to identify visually critical regions that correspond to the full instruction. Then, we optimize the patch to disrupt the semantic grounding of target objects and increase the curvature of action trajectories, thereby compounding failures in both perception and control. Extensive experiments in simulation and real-world robotic environments show that our method sustains adversarial effects under partial observability, inducing long-horizon disruptions and significantly reducing task success rates.

Recent advancements in generative AI have led to image editing models capable of producing realistic forgeries that evade traditional image forgery localization methods, as these approaches depend on physical noise absent in synthetic data. To address this challenge, we theoretically demonstrate that the diffusion process inherently suppresses local high-frequency variance, creating a statistical energy gap that is distinguishable from the natural entropy of optical imaging. Guided by this insight, we propose FLAME, a unified framework that utilizes a LAD map to capture these intrinsic anomalies, coupled with a parameter-efficient adapter for SAM to achieve precise, pixel-level forgery localization. Furthermore, to bridge the lag between forensic benchmarks and evolving generative models, we introduce EditStream, an automated pipeline for continuous, instruction-based training data synthesis. Extensive experiments demonstrate that FLAME establishes a new state-of-the-art, significantly outperforming previous methods on AI-generated forgery datasets while effectively generalizing to unseen generative architectures. Our code is available at https://github.com/phoenixnir/FLAME.

Retrieval-Augmented Generation (RAG) systems are widely deployed and increasingly influential, but their reliance on external corpora exposes new security risks from poisoned retrieval content. Existing RAG attacks are largely focusing on individual queries or narrow topic-local query sets, which limits their practical reach and offers limited camouflage in real-world settings. In this paper, we introduce discourse-level opinion manipulation, a new threat model in which coordinated influence across a semantic query network induces opinion shifts over a holistic, multi-topic query space. We formalize this threat in a black-box setting and propose DiscourseFlip, an agentic, graph-guided attack that dynamically allocates a limited poisoning budget to maximize discourse-level opinion deviation. Extensive experiments demonstrate that DiscourseFlip consistently induces targeted opinion shifts across the contextualized query network and significantly outperforms existing baselines in terms of coverage and effectiveness. User studies further confirm that DiscourseFlip is effective while remaining well camouflaged from user detection. Moreover, systematic analyses show that existing mitigation strategies are ineffective against discourse-level manipulation, underscoring the urgent need for more robust and adaptive defenses to address discourse-level vulnerabilities.

While decision-based black-box adversarial attacks present a severe security threat, current methodologies suffer from fundamental limitations. Pixel-wise attacks frequently introduce unnatural, high-frequency visual artifacts, while latent-space frameworks are confined by the limited search space of low-dimensional manifolds and inherent reconstruction flaws. To resolve these limitations, we propose Latent Geometric Chords (LGC) for Query-Efficient Decision-Based Adversarial Attacks alongside a variant, LGC-H. At its core, LGC navigates decision boundaries by executing a curvature-aware geometric search within a compressed semantic manifold. To guarantee high visual fidelity and circumvent dimensionality bottlenecks, we introduce a Residual-based Adversarial Generation (RAG) mechanism. RAG isolates semantic perturbations as geometric chords and superimposes them directly onto the original source image. RAG substantially resolves baseline reconstruction flaws and effectively doubles the permissible search space dimensions. Experimental results demonstrate that LGC achieves robust cross-dataset transferability and substantially outperforms state-of-the-art baselines. Notably, our method, LGC, minimizes perturbation magnitudes while achieving state-of-the-art visual fidelity--with a Structural Similarity Index Measure (SSIM) exceeding 0.99 and a Learned Perceptual Image Patch Similarity (LPIPS) below 0.01 at 5000 queries--and sustaining high attack success rates under stringent perceptual constraints, successfully compromising adversarially trained robust models. The source code is available at: https://github.com/eihmuekhine/Latent-Geometric-Chords.