Transfer-Based Adversarial Attacks

Overview

Transfer-based adversarial attacks study how to craft adversarial inputs using a surrogate model that also fool unseen target models, often when those targets are black boxes. Common approaches use gradient-based optimization, surrogate ensembles, input transformations, or alignment of semantic and intermediate features to reduce overfitting to one model. The methods span image classifiers, object detectors, speech systems, and vision-language models, with work also exploring physical patches and constraints on perceptual quality. A central challenge is that gains depend on how well the surrogate matches the target, so transfer success can vary across architectures and settings, making careful source–target evaluation essential.

Latest papers

90 papers8 papers in the last four weeks, down 27% on the four weeks before. 0.1% of all new papers.

Apr 17, 2026

PoInit-of-View: Poisoning Initialization of Views Transfers Across Multiple 3D Reconstruction Systems

Poisoning input views of 3D reconstruction systems has been recently studied. However, we identify that existing studies simply backpropagate adversarial gradients through the 3D reconstruction pipeline as a whole, without uncovering the new vulnerability rooted in specific modules of the 3D reconstruction pipeline. In this paper, we argue that the structure-from-motion (SfM) initialization, as the geometric core of many widely used reconstruction systems, can be targeted to achieve transferable poisoning effects across diverse 3D reconstruction systems. To this end, we propose PoInit-of-View, which optimizes adversarial perturbations to intentionally introduce cross-view gradient inconsistencies at projections of corresponding 3D points. These inconsistencies disrupt keypoint detection and feature matching, thereby corrupting pose estimation and triangulation within SfM, eventually resulting in low-quality rendered views. We also provide a theoretical analysis that connects cross-view inconsistency to correspondence collapse. Experimental results demonstrate the effectiveness of our PoInit-of-View on diverse 3D reconstruction systems and datasets, surpassing the single-view baseline by 25.1% in PSNR and 16.5% in SSIM in black-box transfer settings, such as 3DGS to NeRF.
Apr 16, 2026

Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification

Adversarial attacks pose a severe threat to the reliability of deep learning models in remote sensing (RS) image classification. Most existing methods rely on direct pixel-wise perturbations, failing to exploit the inherent atmospheric characteristics of RS imagery or survive real-world image degradations. In this paper, we propose FogFool, a physically plausible adversarial framework that generates fog-based perturbations by iteratively optimizing atmospheric patterns based on Perlin noise. By modeling fog formations with natural, irregular structures, FogFool generates adversarial examples that are not only visually consistent with authentic RS scenes but also deceptive. By leveraging the spatial coherence and mid-to-low-frequency nature of atmospheric phenomena, FogFool embeds adversarial information into structural features shared across diverse architectures. Extensive experiments on two benchmark RS datasets demonstrate that FogFool achieves superior performance: not only does it exceed in white-box settings, but also exhibits exceptional black-box transferability (reaching 83.74% TASR) and robustness against common preprocessing-based defenses such as JPEG compression and filtering. Detailed analyses, including confusion matrices and Class Activation Map (CAM) visualizations, reveal that our atmospheric-driven perturbations induce a universal shift in model attention. These results indicate that FogFool represents a practical, stealthy, and highly persistent threat to RS classification systems, providing a robust benchmark for evaluating model reliability in complex environments.
Apr 10, 2026

Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization

Vision-Language Models (VLMs) are powerful but remain vulnerable to multimodal jailbreak attacks. Existing attacks mainly rely on either explicit visual prompt attacks or gradient-based adversarial optimization. While the former is easier to detect, the latter produces subtle perturbations that are less perceptible, but is usually optimized and evaluated under homogeneous open-source surrogate-target settings, leaving its effectiveness on commercial closed-source VLMs under heterogeneous settings unclear. To examine this issue, we study different surrogate-target settings and observe a consistent gap between homogeneous and heterogeneous settings, a phenomenon we term surrogate dependency. Motivated by this finding, we propose Mosaic, a Multi-view ensemble optimization framework for multimodal jailbreak against closed-source VLMs, which alleviates surrogate dependency under heterogeneous surrogate-target settings by reducing over-reliance on any single surrogate model and visual view. Specifically, Mosaic incorporates three core components: a Text-Side Transformation module, which perturbs refusal-sensitive lexical patterns; a Multi-View Image Optimization module, which updates perturbations under diverse cropped views to avoid overfitting to a single visual view; and a Surrogate Ensemble Guidance module, which aggregates optimization signals from multiple surrogate VLMs to reduce surrogate-specific bias. Extensive experiments on safety benchmarks demonstrate that Mosaic achieves state-of-the-art Attack Success Rate and Average Toxicity against commercial closed-source VLMs.
Mar 30, 2026

XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs

Vision-language models (VLMs) share visual-textual representations across zero-shot classification, image captioning, and visual question answering (VQA), creating a pathway through which subtle perturbations may cause failures across tasks. We introduce X-shaped Sparse Pixel Attack (XSPA), a structured attack that restricts perturbations to two intersecting diagonal lines. Within this fixed support, XSPA jointly optimizes a classification objective, cross-task semantic guidance, perturbation magnitude, and linewise smoothness. Under the default setting, it changes about 1.04% of image pixels. On COCO, XSPA reduces zero-shot accuracy by 52.33 points on OpenAI CLIP ViT-L/14 and 67.00 points on OpenCLIP ViT-B/16; GPT-4-based caption consistency and VQA correctness decrease by up to 58.60 and 44.25 points, respectively. Matched-budget experiments show that an adaptive saliency Top-k support achieves higher attack success than the fixed X-shaped support, while XSPA provides better SSIM and LPIPS but worse PSNR and MAE. Same-image analysis finds no three-task targeted success, indicating that strong surrogate classification effects do not reliably translate into targeted output-space failures. These results position XSPA as a controlled stress test for studying how sparse fixed geometry affects VLM robustness, rather than as a universally superior attack.
Mar 30, 2026

From Pixels to Reality: Physical-Digital Patch Attacks on Real-World Camera

This demonstration presents Digital-Physical Adversarial Attacks (DiPA), a new class of practical adversarial attacks against pervasive camera-based authentication systems, where an attacker displays an adversarial patch directly on a smartphone screen instead of relying on printed artifacts. This digital-only physical presentation enables rapid deployment, removes the need for total-variation regularization, and improves patch transferability in black-box conditions. DiPA leverages an ensemble of state-of-the-art face-recognition models (ArcFace, MagFace, CosFace) to enhance transfer across unseen commercial systems. Our interactive demo shows a real-time dodging attack against a deployed face-recognition camera, preventing authorized users from being recognized while participants dynamically adjust patch patterns and observe immediate effects on the sensing pipeline. We further demonstrate DiPA's superiority over existing physical attacks in terms of success rate, feature-space distortion, and reductions in detection confidence, highlighting critical vulnerabilities at the intersection of mobile devices, pervasive vision, and sensor-driven authentication infrastructures.
Mar 26, 2026

Fast Preemptive Robustification: High-Frequency Response Anti-Aligns Shared Vulnerability

Adversarial attacks can readily compromise deep neural networks (DNNs). In particular, transferable attacks (TAs) exploit the shared vulnerabilities among DNNs, enabling perturbations crafted on surrogates to transfer to unseen models. Training-time and post-attack defenses have been extensively studied for combating TAs. Orthogonal to these approaches, preemptive robustification (PR) has emerged as a pre-attack defense that enhances the robustness of benign samples by superimposing protective variations before attacks. Despite its promise, PR remains underexplored and faces several important limitations. First, dependence on well-trained surrogate classifiers limits applicability, as surrogates are task-specific and may even be unavailable in some practical settings. Second, the required iterative optimization or dedicated PR generator training incurs substantial costs. Third, the generated variations are opaque to humans. To address these, we seek an efficient PR that is surrogate-free, optimization-free, training-free, and human-interpretable. Intriguingly, we discover a numerical correlation between the shared vulnerabilities of DNNs and Laplacian responses, with their cosine similarity being significantly negative. This indicates that negated high-frequency response constitutes an important component of shared vulnerabilities. Consequently, strengthening Laplacian responses counteracts this component, improving resistance to TAs. Building upon this insight, we propose Fast Preemptive Robustification (FPR), which performs Laplacian sharpening via a single channel-wise convolution with a 3\times3 kernel. FPR is simple yet effective, as demonstrated by extensive experiments. Specifically, FPR reduces the attack success rate (ASR) of untargeted TAs by 12.7% and that of targeted TAs from 10.7% to 4.1%. Code will be released publicly.
Mar 25, 2026

Generative Adversarial Perturbations with Cross-paradigm Transferability on Localized Crowd Counting

State-of-the-art crowd counting and localization are primarily modeled using two paradigms: density maps and point regression. Given the field's security ramifications, there is active interest in model robustness against adversarial attacks. Recent studies have demonstrated transferability across density-map-based approaches via adversarial patches, but cross-paradigm attacks (i.e., across both density map-based models and point regression-based models) remain unexplored. We introduce a novel adversarial framework that compromises both density map and point regression architectural paradigms through a comprehensive multi-task loss optimization. For point-regression models, we employ scene-density-specific high-confidence logit suppression; for density-map approaches, we use peak-targeted density map suppression. Both are combined with model-agnostic perceptual constraints to ensure that perturbations are effective and imperceptible to the human eye. Extensive experiments demonstrate the effectiveness of our attack, achieving on average a 7X increase in Mean Absolute Error compared to clean images while maintaining competitive visual quality, and successfully transferring across seven state-of-the-art crowd models with transfer ratios ranging from 0.55 to 1.69. Our approach strikes a balance between attack effectiveness and imperceptibility compared to state-of-the-art transferable attack strategies. The source code is available at https://github.com/simurgh7/CrowdGen
Mar 23, 2026

Adversarial Camouflage

While the rapid development of facial recognition algorithms has enabled numerous beneficial applications, their widespread deployment has raised significant concerns about the risks of mass surveillance and threats to individual privacy. In this paper, we introduce Adversarial Camouflage as a novel solution for protecting users' privacy. This approach is designed to be efficient and simple to reproduce for users in the physical world. The algorithm starts by defining a low-dimensional pattern space parameterized by color, shape, and angle. Optimized patterns, once found, are projected onto semantically valid facial regions for evaluation. Our method maximizes recognition error across multiple architectures, ensuring high cross-model transferability even against black-box systems. It significantly degrades the performance of all tested state-of-the-art face recognition models during simulations and demonstrates promising results in real-world human experiments, while revealing differences in model robustness and evidence of attack transferability across architectures.
Mar 21, 2026

OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation

Robust semantic segmentation is crucial for safe autonomous driving, yet deployed models remain vulnerable to black-box adversarial attacks when target weights are unknown. Most existing approaches either craft image-wide perturbations or optimize patches for a single architecture, which limits their practicality and transferability. We introduce OmniPatch, a training framework for learning a universal adversarial patch that generalizes across images and both ViT and CNN architectures without requiring access to target model parameters.
Mar 6, 2026

Latent Transfer Attack: Adversarial Examples via Generative Latent Spaces

Adversarial attacks are a central tool for probing the robustness of modern vision models, yet most methods optimize perturbations directly in pixel space under ℓ∞\ell_\infty or ℓ2\ell_2 constraints. While effective in white-box settings, pixel-space optimization often produces high-frequency, texture-like noise that is brittle to common preprocessing (e.g., resizing and cropping) and transfers poorly across architectures. We propose LTA\textbf{LTA} (L\textbf{L}atent T\textbf{T}ransfer A\textbf{A}ttack), a transfer-based attack that instead optimizes perturbations in the latent space of a pretrained Stable Diffusion VAE. Given a clean image, we encode it into a latent code and optimize the latent representation to maximize a surrogate classifier loss, while softly enforcing a pixel-space ℓ∞\ell_\infty budget after decoding. To improve robustness to resolution mismatch and standard input pipelines, we incorporate Expectation Over Transformations (EOT) via randomized resizing, interpolation, and cropping, and apply periodic latent Gaussian smoothing to suppress emerging artifacts and stabilize optimization. Across a suite of CNN and vision-transformer targets, LTA achieves strong transfer attack success while producing spatially coherent, predominantly low-frequency perturbations that differ qualitatively from pixel-space baselines and occupy a distinct point in the transfer-quality trade-off. Our results highlight pretrained generative latent spaces as an effective and structured domain for adversarial optimization, bridging robustness evaluation with modern generative priors.
Mar 5, 2026

Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models

The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also exposes serious transferable adversarial vulnerabilities. In general, existing adversarial attacks against MLLMs typically rely on surrogate models trained within a single learning paradigm and perform independent optimisation in their respective feature spaces. This straightforward setting naturally restricts the richness of feature representations, delivering limits on the search space and thus impeding the diversity of adversarial perturbations. To address this, we propose a novel Multi-Paradigm Collaborative Attack (MPCAttack) framework to boost the transferability of adversarial examples against MLLMs. In principle, MPCAttack aggregates semantic representations, from both visual images and language texts, to facilitate joint adversarial optimisation on the aggregated features through a Multi-Paradigm Collaborative Optimisation (MPCO) strategy. By performing contrastive matching on multi-paradigm features, MPCO adaptively balances the importance of different paradigm representations and guides the global perturbation optimisation, effectively alleviating the representation bias. Extensive experimental results on multiple benchmarks demonstrate the superiority of MPCAttack, indicating that our solution consistently outperforms state-of-the-art methods in both targeted and untargeted attacks on open-source and closed-source MLLMs. The code is released at https://github.com/LiYuanBoJNU/MPCAttack.
Mar 5, 2026

Towards Highly Transferable Vision-Language Attack via Semantic-Augmented Dynamic Contrastive Interaction

With the rapid advancement and widespread application of vision-language pre-training (VLP) models, their vulnerability to adversarial attacks has become a critical concern. In general, the adversarial examples can typically be designed to exhibit transferable power, attacking not only different models but also across diverse tasks. However, existing attacks on language-vision models mainly rely on static cross-modal interactions and focus solely on disrupting positive image-text pairs, resulting in limited cross-modal disruption and poor transferability. To address this issue, we propose a Semantic-Augmented Dynamic Contrastive Attack (SADCA) that enhances adversarial transferability through progressive and semantically guided perturbation. SADCA progressively disrupts cross-modal alignment through dynamic interactions between adversarial images and texts. This is accomplished by SADCA establishing a contrastive learning mechanism involving adversarial, positive and negative samples, to reinforce the semantic inconsistency of the obtained perturbations. Moreover, we empirically find that input transformations commonly used in traditional transfer-based attacks also benefit VLPs, which motivates a semantic augmentation module that increases the diversity and generalization of adversarial examples. Extensive experiments on multiple datasets and models demonstrate that SADCA significantly improves adversarial transferability and consistently surpasses state-of-the-art methods. The code is released at https://github.com/LiYuanBoJNU/SADCA.
Feb 26, 2026

Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluation

Adversarial transferability refers to the capacity of adversarial examples generated on the surrogate model to deceive alternate, unexposed victim models. This property eliminates the need for direct access to the victim model during an attack, thereby raising considerable security concerns in practical applications and attracting substantial research attention recently. In this work, we discern a lack of a standardized framework and criteria for evaluating transfer-based attacks, leading to potentially biased assessments of existing approaches. To rectify this gap, we have conducted an exhaustive review of hundreds of related works, organizing various transfer-based attacks into six distinct categories. Subsequently, we propose a comprehensive framework designed to serve as a benchmark for evaluating these attacks. In addition, we delineate common strategies that enhance adversarial transferability and highlight prevalent issues that could lead to unfair comparisons. Finally, we provide a brief review of transfer-based attacks beyond image classification.
Feb 22, 2026

The Power of Decaying Steps: Enhancing Attack Stability and Transferability for Sign-based Optimizers

Crafting adversarial examples can be formulated as an optimization problem. While sign-based optimizers such as I-FGSM and MI-FGSM have become the de facto standard for the induced optimization problems, there still exist several unsolved problems in theoretical grounding and practical reliability especially in non-convergence and instability, which inevitably influences their transferability. Contrary to the expectation, we observe that the attack success rate may degrade sharply when more number of iterations are conducted. In this paper, we address these issues from an optimization perspective. By reformulating the sign-based optimizer as a specific coordinate-wise gradient descent, we argue that one cause for non-convergence and instability is their non-decaying step-size scheduling. Based upon this viewpoint, we propose a series of new attack algorithms that enforce Monotonically Decreasing Coordinate-wise Step-sizes (MDCS) within sign-based optimizers. Typically, we further provide theoretical guarantees proving that MDCS-MI attains an optimal convergence rate of O(1/T)O(1/\sqrt{T}), where TT is the number of iterations. Extensive experiments on image classification and cross-modal retrieval tasks demonstrate that our approach not only significantly improves transferability but also enhances attack stability compared to state-of-the-art sign-based methods.
Feb 19, 2026

Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting

Black-box adversarial attacks on Large Vision-Language Models (LVLMs) are challenging due to missing gradients and complex multimodal boundaries. Prior state-of-the-art transfer-based approaches such as M-Attack match local crops between source and target images, but this induces high-variance, nearly orthogonal gradients across iterations. We attribute this instability to (i) ViT translation sensitivity, which yields spike-like gradients, and (ii) a structural asymmetry between source and target crops. We reformulate local matching as an asymmetric expectation over source transformations and target semantics, and introduce M-Attack-V2 based on this formulation. Multi-Crop Alignment (MCA) averages gradients from multiple local views per iteration, while Auxiliary Target Alignment (ATA) replaces aggressive target augmentation with a small set of semantically correlated auxiliary images. Patch Momentum replays historical crop gradients, and a patch-diverse surrogate ensemble (PE+) strengthens transferable directions. M-Attack-V2 raises attack success rates over M-Attack from 40% to 61% on GPT-6.1 Sol, from 40% to 60% on GPT-6 Astra, and from 85% to 97% on Claude Sonnet 5.5. Code and data are publicly available at: https://github.com/VILA-Lab/M-Attack-V2.
Feb 9, 2026

StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors

AI-text detectors are increasingly used in high-stakes settings, but their robustness to meaning-preserving adversarial rewriting remains unclear. We introduce StealthRL, a reinforcement learning framework for stress-testing detectors with adaptive paraphrase attacks. StealthRL trains a paraphrase policy against a detector ensemble while enforcing semantic fidelity, then evaluates transfer to held-out detector families on the full filtered MAGE test pool. Across RoBERTa, Fast-DetectGPT, Binoculars, and MAGE, the resulting attack sharply degrades detection performance, driving mean TPR@1%FPR down to 0.024 while retaining nontrivial semantic overlap and readable prose. The attack also transfers to detectors not used during training, indicating a broader robustness failure rather than overfitting to a single target model. We complement the main results with detector-score analysis, repeated-generation stability checks, and automatic and judge-based quality evaluation. Our findings suggest that current AI-text detectors remain brittle under adaptive paraphrasing pressure and motivate robustness evaluation at deployment-relevant operating points. Our code and the trained model checkpoint are publicly available.
Jan 30, 2026

The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer

Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignment. However, whether such alignment inadvertently facilitates the transfer of safety vulnerabilities across modalities remains underexplored. This question is critical as text-based jailbreak attacks are considerably more mature than audio-based ones; if they transfer systematically, current audio safety evaluations may underestimate risks originating from the text modality. In this paper, we introduce the Alignment Curse, a formally characterized and empirically validated principle showing that stronger modality alignment enables more effective transfer of attacks from text to audio, revealing a fundamental tension between capability and safety. Motivated by this principle, we conduct a comprehensive black-box evaluation of three attack categories on recent omni-models (e.g., Qwen2.5-Omni, Qwen3-Omni): text attacks, text-transferred audio attacks, and audio attacks. We find that text-transferred audio attacks perform comparably to, and often better than, audio-based attacks, exhibiting a clear advantage under audio-only access. This suggests that text-based vulnerabilities play a pivotal role in shaping audio safety risks. Finally, we empirically analyze the relationship between modality alignment and transfer effectiveness across attack methods and models, observing consistent support for the Alignment Curse: tighter modality alignment leads to more effective cross-modality attack transfer.
Dec 26, 2025

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models

Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM reliability. While prior entropy-based attacks maximize uncertainty at all decoding steps, implicitly assuming that every token equally contributes to model instability, we reveal that a small fraction (around 20%) of high-entropy tokens, in the evaluated representative open-source VLMs with diverse architectures, concentrates a disproportionate share of adversarial influence during autoregressive generation. We demonstrate that concentrating adversarial perturbations on these high-entropy positions achieves comparable semantic degradation to global methods while optimizing fewer decoding positions. Additionally, across multiple representative VLMs, such attacks induce not only semantic drift but also a substantial unsafe subset (20-31%) under the current pipeline. Remarkably, since such vulnerable high-entropy tokens recur across architecturally diverse VLMs, attacks focused on them exhibit non-trivial transferability. Motivated by these findings, we design a simple Entropy-Guided Attack (EGA) that operationalizes sparse high-entropy targeting and extends it with a reusable token bank, yielding competitive attack success rates (93-95%) with a considerable harmful rate (30.2-38.6%) on the three representative open-source VLMs.
Nov 21, 2025

Enhancing Adversarial Transferability through Block Stretch and Shrink

Input transformation-based attacks improve adversarial transferability by aggregating gradients over transformed inputs. Existing analyses mainly explain their efficacy from image diversity, semantic preservation, attention variance or hypothesis space augmentation, yet overlook the critical role of model frontend responses. In this paper, we revisit transformation-based attacks from an implicit ensemble perspective: each transformation can be viewed as a pre-processing operator before the surrogate model, inducing a distinct frontend response for gradient aggregation. Based on this view, we propose FRO, a Frontend Response-Oriented input transformation method that enriches such responses through two complementary operators. The Local Scaling Operator perturbs local content sampling via block-wise stretch-and-shrink operations, while the Projection Operator modifies global spatial organization through coherent perspective deformation. Together, they produce structured transformed views to optimize transferable adversarial perturbations. Experiments on an ImageNet subset show that FRO consistently improves black-box transferability across diverse CNN and Vision Transformer models. We further analyze the effect of implicit ensemble size and evaluate different transformation-based methods under a unified ensemble scale, demonstrating the superiority of designing input transformations from the perspective of front-end response ensembles.
Oct 1, 2025

Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors

Existing data poisoning attacks on retrieval-augmented generation (RAG) systems scale poorly because they require costly optimization of poisoned documents for each target phrase. We introduce Eyes-on-Me, a modular attack that decomposes an adversarial document into reusable Attention Attractors and Focus Regions. Attractors are optimized to direct attention to the Focus Region. Attackers can then insert semantic baits for the retriever or malicious instructions for the generator, adapting to new targets at near zero cost. This is achieved by steering a small subset of attention heads that we empirically identify as strongly correlated with attack success. Across 18 end-to-end RAG settings (3 datasets ×\times 2 retrievers ×\times 3 generators), Eyes-on-Me raises average attack success rates from 21.9 to 57.8 (+35.9 points, 2.6×\times over prior work). A single optimized attractor transfers to unseen black box retrievers and generators without retraining. Our findings establish a scalable paradigm for RAG data poisoning and show that modular, reusable components pose a practical threat to modern AI systems. They also contribute to interpretability research by revealing a strong link between attention concentration and model outputs.
Aug 7, 2025

PhysPatch: A Physically Realizable and Transferable Adversarial Patch Attack for Multimodal Large Language Models-based Autonomous Driving Systems

Multimodal Large Language Models (MLLMs) are becoming integral to autonomous driving (AD) systems due to their strong vision-language reasoning capabilities. However, MLLMs are vulnerable to adversarial attacks, particularly adversarial patch attacks, which can pose serious threats in real-world scenarios. Existing patch-based attack methods are primarily designed for object detection models and perform poorly when transferred to MLLM-based systems due to the latter's complex architectures and reasoning abilities. To address these limitations, we propose PhysPatch, a physically realizable and transferable adversarial patch framework tailored for MLLM-based AD systems. PhysPatch jointly optimizes patch location, shape, and content to enhance attack effectiveness and real-world applicability. It introduces a semantic-based mask initialization strategy for realistic placement, an SVD-based local alignment loss with patch-guided crop-resize to improve transferability, and a potential field-based mask refinement method. Extensive experiments across open-source, commercial, and reasoning-capable MLLMs demonstrate that PhysPatch significantly outperforms prior methods in steering MLLM-based AD systems toward target-aligned perception and planning outputs. Moreover, PhysPatch consistently places adversarial patches in physically feasible regions of AD scenes, ensuring strong real-world applicability and deployability.
Jun 4, 2025

RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors

AI-generated images (AIGIs) have reached a level of quality at which humans are unable to reliably distinguish them from real images. To counter the inherent risks of fraud and disinformation, their detection is a pressing challenge and an active research topic. While many of the presented methods claim high detection accuracy, they are often evaluated without considering their adversarial robustness. In real-world scenarios, malicious actors can modify AIGIs, e.g., through imperceptible perturbations, to evade detection systems. In this work, we provide a dataset to assess the robustness of AI-generated image detectors. We present RAID (Robust evaluation of AI-generated image Detectors), a benchmark dataset of 216k diverse and transferable adversarial images. The proposed dataset is created starting from images generated by four different text-to-image models (to promote diversity) and optimizing attacks against an ensemble of seven state-of-the-art detectors (to promote transferability). Extensive experiments show that our methodology generates adversarial images that transfer to unseen detectors, degrading the performance of every detector outside the attack ensemble that we evaluate, and provides a practical, worst-case robustness screen: failure on RAID is a strong indicator that a detector is not adversarially robust. We release our dataset at https://huggingface.co/datasets/aimagelab/RAID and evaluation code at https://github.com/pralab/RAID.
Apr 11, 2025

On the Adversarial Robustness of Spiking Neural Networks Trained by Local Learning

Recent research has shown the vulnerability of Spiking Neural Networks (SNNs) under adversarial examples that are nearly indistinguishable from clean data in the context of frame-based and event-based information. The majority of these studies are constrained in generating adversarial examples using Backpropagation Through Time (BPTT), a gradient-based method which lacks biological plausibility. In contrast, local learning methods, which relax many of BPTT's constraints, remain under-explored in the context of adversarial attacks. With the increasing real-world deployment of local learning methods in SNNs, it is critical to investigate whether these approaches introduce adversarial vulnerabilities that could compromise reliability. To address this problem, we examine adversarial robustness in SNNs through the framework of four types of training algorithms. We provide an in-depth analysis showing that direct gradient-based attacks are ineffective for locally trained models. To overcome these limitations, we introduce a hybrid adversarial attack paradigm that leverages the transferability of adversarial instances. The proposed hybrid approach demonstrates superior performance, outperforming existing adversarial attack methods. Furthermore, the generalizability of the method is assessed under multi-step adversarial attacks, adversarial attacks in black-box scenarios, and within the non-spiking domain.
Mar 8, 2025

Boosting the Local Invariance for Better Adversarial Transferability

Transfer-based attacks pose a significant threat to real-world applications by directly targeting victim models with adversarial examples generated on surrogate models. While numerous approaches have been proposed to enhance adversarial transferability, existing works often overlook the intrinsic relationship between adversarial perturbations and input images. In this work, we find that the adversarial perturbations often exhibit poor translation invariance for a given clean image and model, which is attributed to local invariance. Through empirical analysis, we demonstrate a positive correlation between the local invariance of adversarial perturbations w.r.t. the input image and their transferability across models. Based on this finding, we propose a general adversarial transferability boosting technique called the Local Invariance Boosting approach (LI-Boost). Extensive experiments on the standard ImageNet dataset demonstrate that LI-Boost significantly enhances five categories of transfer-based attacks, i.e., gradient-based, input transformation-based, model-related, advanced objective function, and ensemble attacks. The improvements hold not only on conventional CNNs, ViTs, and defense mechanisms, but also on real-world commercial vision API systems and vision-language models. Our approach provides a promising direction for future research on improving adversarial transferability across models. Our code is available at https://github.com/Trustworthy-AI-Group/TransferAttack.
Feb 24, 2025

Information-Geometric Inverse Distillation for Enhancing Adversarial Transferability

Transfer-based adversarial attacks rely on surrogate models to craft perturbations, yet often overfit the surrogate's decision boundary. To address this problem, we propose Inverse Knowledge Distillation (IKD), a simple and attack-agnostic mechanism that maximizes the prediction-distribution discrepancy between benign and adversarial samples on the surrogate model. IKD uses a CE/KL-equivalent soft-label objective to push adversarial predictions away from a fixed benign prediction anchor and enrich the attack with Fisher-sensitive surrogate directions. We prove that, under a matched fixed-anchor implementation, soft-label cross-entropy and KL divergence differ only by a constant entropy term and therefore induce identical gradients, Hessians, and adversarial optimization trajectories. Our information-geometric analysis further derives a quantitative lower bound on dominant Fisher-subspace overlap between surrogate and target models from local same-task stability and a Fisher eigengap, and establishes a sufficient target-margin crossing condition under oriented gradient coherence and target smoothness. This analysis connects IKD's surrogate Fisher sensitivity to cross-model transfer. In contrast, mean squared error uses a different Euclidean pullback in output probability space. IKD integrates seamlessly with standard gradient-based attacks without modifying their optimization pipelines. Extensive ImageNet experiments demonstrate consistent black-box gains across CNN, ViT, and defended models, while ablations confirm CE and KL equivalence and the pronounced disadvantage of MSE. These results establish IKD as an effective and lightweight component for improving adversarial transferability. Code is available at https://github.com/ImmortalTing/IKD.
Feb 6, 2025

How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies

Imitation learning, also known as learning from demonstrations, is a popular approach to train AI models; however, the vulnerability of these models to adversarial attacks remains underexplored. We present the first systematic study of adversarial attacks, across a range of both classic and recently proposed imitation learning algorithms, including Vanilla Behavior Cloning (Vanilla BC), LSTM-GMM, Implicit Behavior Cloning (IBC), Diffusion Policy (DP), and Vector-Quantized Behavior Transformer (VQ-BET). We study the vulnerability of these methods to white-box, grey-box and black-box adversarial perturbations. Our experiments reveal that most existing methods are highly vulnerable to these attacks, including black-box transfer attacks that transfer across algorithms. White-box attacks cause at least a 65% reduction in average task success across all evaluated tasks and algorithms, while the black-box transfer attacks reduce task success by up to 88% on Lift, 99% on Can, and 100% on Square. To the best of our knowledge, we are the first to study and compare the vulnerabilities of different popular imitation learning algorithms to both white-box and black-box attacks. Our findings highlight the vulnerabilities of modern imitation learning algorithms, paving the way for future work in addressing such limitations. Videos and code are available at https://sites.google.com/view/uap-attacks-on-bc.
Dec 11, 2024

Exploiting Vision Encoder Vulnerabilities for Universal Adversarial Perturbations on Large Vision-Language Models

Large Vision-Language Models (LVLMs) have achieved remarkable performance on multimodal tasks but remain highly vulnerable to small adversarial perturbations in input images. Existing attacks typically target the vision encoder's final output embeddings, implicitly treating the encoder as a uniform attack surface, while a systematic analysis of which internal components are most vulnerable has remained largely unexplored. We show such analysis is essential, as adversarial vulnerability in LVLM vision encoders is structurally concentrated rather than uniformly distributed. Building on this, we propose Vision Encoder Vulnerable-Component-Targeted Universal Adversarial Perturbation (VEV-UAP), a task-agnostic and cost-efficient attack framework. Through a component- and layer-wise analysis of attention mechanisms, we identify the value components in middle layers as critical vulnerabilities that strongly influence downstream language model behavior. VEV-UAP selectively targets these components to generate a single universal perturbation shared across images, without involving textual inputs or the language model during optimization. Experiments across multiple LVLMs and tasks show VEV-UAP achieves state-of-the-art attack success rates with reduced computational overhead. Moreover, a single VEV-UAP transfers across LVLMs sharing the same vision encoder, even when paired with different language models, making it a practical framework for scalable robustness evaluation.
Sep 26, 2024

Transferable Multiform Attack for Cross-Modal Person Re-Identification

Cross-modal person re-identification (ReID) adversarial attacks face a transferability challenge: existing methods may exhibit source-pair overfitting, where learned perturbations become overly dependent on the feature statistics of the source modality pair, thereby limiting their transferability under heterogeneous domain shifts. We argue that a key challenge is reducing source-pair-specific bias while maintaining attack effectiveness. To address this, we propose Multiform Attack (MA). The framework first learns a universal perturbation via Mahalanobis-guided gradient optimization. Since this perturbation may still retain source-pair-specific bias, the second stage performs sparse refinement through attention-shift-filtered multi-objective evolutionary search, leveraging heterogeneous source distributions in transfer settings. By separating universal perturbation learning from sparse evolutionary refinement, MA aims to reduce reliance on source-pair-specific patterns and improve transferability to unseen domains. Extensive experiments demonstrate strong attack effectiveness on cross-modal ReID benchmarks and improved transferability in the evaluated held-out-domain settings, with additional evaluations across model architectures.
Dec 4, 2023

InstructTA: Instruction-Tuned Targeted Attack for Large Vision-Language Models

Large vision-language models (LVLMs) have demonstrated their incredible capability in visual question answering. However, this rich visual interaction also makes LVLMs vulnerable to adversarial examples. In this paper, we formulate a novel and practical targeted attack scenario that the adversary knows only the vision encoder of the victim LVLM, without the knowledge of its prompts and its underlying large language model. This practical setting poses challenges to the cross-prompt and cross-model transferability of targeted adversarial attack, which aims to confuse the LVLM to output a response that is semantically similar to the attacker's chosen target text. To this end, we propose an instruction-tuned targeted attack (dubbed InstructTA) to deliver the targeted adversarial attack on LVLMs with high transferability. Initially, we utilize a public text-to-image generative model to reverse the target response into a target image, and employ GPT-4 to infer a reasonable instruction p′\boldsymbol{p}^\prime from the target response. We then form a local surrogate model (sharing the same vision encoder with the victim LVLM) to extract instruction-aware features of an adversarial image example and the target image, and minimize the distance between these two features to optimize the adversarial example. To further improve the transferability with instruction tuning, we augment the instruction p′\boldsymbol{p}^\prime with instructions paraphrased from GPT-4. Extensive experiments on 6 victim LVLMs demonstrate the superiority of our proposed method in targeted attack performance and transferability. In particular, InstructTA achieves an attack success rate of 51.9% on BLIP-2, outperforming the strongest baseline by 10.5%, and consistently yields the highest attack success rates across all evaluated models. The code is available at https://github.com/xunguangwang/InstructTA.
Nov 20, 2023

Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems

Transferable attacks allow adversarial manipulations or learned attack mechanisms constructed in one setting to compromise other AI systems, potentially reducing attack costs and amplifying security and privacy risks. Yet fragmented terminology and evaluation practices hinder understanding of what transfers, why it transfers, and where transfer fails. This survey synthesizes representative research and develops a unified taxonomy spanning six complementary axes: cross-instance, cross-domain, cross-modality, cross-model, cross-task, and cross-deployment. By separating source-target configuration changes from attacker access and adaptation budgets, the taxonomy provides a common framework for comparing transfer across evasion, poisoning, backdoors, privacy inference, model stealing, and prompt-based attacks. We connect transfer mechanisms, including gradient alignment, shared representations, training persistence, and deployment invariances, to enhancement methods based on augmentation, disentanglement, and optimization. Our synthesis identifies inconsistent transfer, incompatible metrics, and gaps between simulated and physical evaluations, and establishes a research agenda for compositional transfer, configuration differences, temporal persistence, and reproducible benchmarking. Together, this work supports systematic investigation of shared vulnerabilities and guides transfer-aware security assessment and defense.