Adversarial Attacks on VLMs

VLM: Vision-Language Model

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 14% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 106

May 27, 2026cs.CV

JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language Models

Forensic vision-language models (VLMs) have recently been developed to detect image tampering and provide natural-language explanations. However, their robustness against adversarial manipulation remains underexplored. Existing adversarial attacks typically aim to flip the model's binary judgment, while the accompanying explanation may still reveal forensic cues and contradict the attacked judgment. In this paper, we study judgment-explanation consistent adversarial attacks against forensic VLMs and propose JECA^2, a controlled white-box red-team diagnostic that jointly redirects visual attribution and aligns textual explanations with the target judgment. On the visual side, JECA^2 uses Grad-CAM-guided perturbations to divert attribution from tampered regions toward benign regions. On the textual side, it optimizes prompt embeddings toward authenticity-affirming semantics under a token-proximity constraint. Experiments on forensic VLM benchmarks show that JECA^2 achieves higher attack success and automated judgment-explanation consistency than implemented baselines under white-box threat settings, while transfer to closed-source VLMs remains measurable but limited. Our results highlight a consistency failure mode in explanation-based forensic VLMs and motivate future robustness evaluation beyond binary detection accuracy.

Jiachen Qian

City University of Hong Kong

VLM Robustness Adversarial Attacks on VLMs Digital Image Forensics

May 27, 2026cs.CL

KSAFE-MM: A Multimodal Safety Benchmark via Localized Contextualization for Korean Cultural Risks

Multimodal Large Language Models (MLLMs) exacerbate safety risks by introducing vulnerabilities across multiple modalities, such as language and vision. Current MLLM safety evaluation tools, however, suffer from major limitations: 1) English-centric dataset construction, and 2) a focus on generic risks that are not tied to local cultural contexts. This paper introduces KSAFE-MM, a benchmark for Korean multimodal safety evaluation that covers both general safety risks and culture-specific vulnerabilities. KSAFE-MM consists of two parts, KSAFE-MM-G and KSAFE-MM-C. KSAFE-MM-G evaluates globally shared risks in Korean contexts through linguistic contextualization, which transforms generic safety queries into contextually grounded multimodal samples. KSAFE-MM-C targets culture-dependent MLLM safety vulnerabilities using localized visual queries derived from real-world contexts. It pairs these visual queries with jailbreak-style textual queries to cover multimodal safety risks involving cultural visual cues and malicious textual intent. Together, these components provide a general-to-local construction pipeline for evaluating both globally shared safety risks and culture-specific vulnerabilities. We evaluate 12 state-of-the-art MLLMs on KSAFE-MM and reveal that models exhibit greater vulnerability to culturally grounded attacks than to generic ones. Notably, jailbreaking strategies substantially amplify attack success rates, with ProgramExecution yielding up to 74.2% ASR compared to 13.4% for standard queries. Furthermore, we identify a systematic trade-off between safety and over-refusal, where models achieving low ASR tend to exhibit excessive refusal behavior on benign queries. These findings highlight the urgent need for culturally grounded safety evaluation beyond English-centric benchmarks.

Yongwoo Kim, Sojung An, Yunjin Park +8

Korea University · KT Corporation

Adversarial Attacks on VLMs Language Model Safety Evaluation Multimodal Large Language Models Multimodal Model Evaluation

May 27, 2026cs.CV

Structure-Guided Visual Perturbation Neutralization for LVLMs

Image inputs enable Large Vision Language Models (LVLMs) to perceive fine-grained visual information, but also introduce a pixel-level attack surface through which adversarial perturbations can elicit unsafe model behaviors. However, most existing defenses are designed for traditional computer vision settings and thus often overlook the cross-modal alignment required by LVLMs, leading to degraded performance. Meanwhile, the limited defenses tailored to LVLMs often require substantial image modifications and introduce considerable computational overhead, thereby compromising inference quality and efficiency. To address these limitations, we propose Structure-Induced Guided Neutralization (SIGN), a lightweight, plug-and-play defense framework that improves LVLM compatibility via Prior Structural Extraction and achieves efficient perturbation suppression via Dynamic Guided Neutralization. Extensive experiments show that SIGN achieves over 87% defense success rate with only 0.5% pixel modification and 0.16 seconds per image, while nearly preserving original visual representations and benign task performance. Our work offers a lightweight alternative to defenses that require costly model training and highlights the potential of exploiting a vision encoder for efficient adversarial protection. Our code is open source on https://anonymous.4open.science/r/SIGN-BCB1.

Yuanhe Zhang, Xueting Wang, YanBin Ren +6

1Beijing University of Posts and Telecommunications · University of Science and Technology of China · 3JIUTIAN Research +2

VLM Robustness Adversarial Attacks on VLMs Large Vision-Language Models Adversarial Examples

May 26, 2026cs.CV

Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization

Large Vision-Language Models (LVLMs) have transformed multi-modal understanding, excelling in tasks like image captioning and visual question answering by integrating visual and textual inputs. However, their robustness against adversarial attacks, particularly those exploiting both modalities, remains underexplored, posing risks to critical applications like autonomous driving and content moderation. Existing attacks focus on single modalities or require impractical white-box access, limiting their real-world relevance. In this paper, we introduce Multi-Modal Adversarial Synergy, a groundbreaking framework that crafts universal, black-box multi-modal attacks against LVLMs. MMAS simultaneously generates a texture scale-constrained universal adversarial perturbation for images and a learnable prompt perturbation for text, optimized jointly using only model queries. The image perturbation leverages wavelet-based texture constraints to ensure imperceptibility and robustness across diverse visual inputs. The text perturbation, constrained by an L-norm in the embedding space, maintains semantic coherence while steering outputs toward a target. A novel cross-modal regularization term aligns the perturbations' gradient directions, enhancing their synergistic impact and transferability across tasks and models. Extensive experiments show the strong universal adversarial capabilities of our proposed attack with prevalent LVLMs.

Xiang Fang, Wanlong Fang, Changshuo Wang

School of Software Engineering, Huazhong University of Science and Technology · Nanyang Technological University, Singapore · University College London

VLM Robustness Adversarial Attacks on VLMs Adversarial Perturbations Black-Box Adversarial Attacks Adversarial Text Attacks

May 25, 2026cs.AI

StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs

Multimodal Large Language Models (MLLMs) excel at structural reasoning yet suffer from a sharp logical brittleness in structural consistency. We term this phenomenon Structural Cognitive Overload (SCO), a byproduct of the contention between deep reasoning and safety alignment. However, prior work has predominantly targeted typographic and pixel-level perturbations, leaving the study of SCO largely unexplored. To this end, we propose StructBreak, an automated end-to-end framework designed to quantify SCO. By leveraging StructBreak, we uncover a novel higher-order cognitive overload attack paradigm; notably, this attack operates under a practical black-box setting, requiring no internal model access. Consequently, we utilize this framework to establish a comprehensive benchmark spanning ten diverse threat scenarios. Empirical evaluations on six leading MLLMs reveal that SCO readily triggers toxic generation, yielding a 92% average ASR (up to 97% on Gemini 2.5). To elucidate the mechanism of SCO, we further conduct model-level interpretations spanning attention dynamics, latent space topology, and geometric analysis. Our findings reveal that StructBreak acts as a novel structural channel to circumvent safety filters. Furthermore, the limited efficacy of inherent safety mechanisms underscores that current alignment paradigms are insufficient for the era of complex multimodal reasoning.

Yang Luo, Xinran Liu, Tiantian Ji +3

Key Laboratory of Trustworthy Distributed Computing and Service (MoE), Beijing University of Posts and Telecommunications · Institute of Computing Technology, Chinese Academy of Sciences

Adversarial Attacks on VLMs Language Model Safety Evaluation Multimodal Large Language Models LLM Safety

May 24, 2026cs.LG

Localization then Neutralization: Gradient-guided Token Suppression against Visual Prompt Injection Attack

Adversarial images pose a severe security threat to multimodal large language models through prompt injection. Existing defenses largely lack a principled understanding of the underlying mechanisms and struggle to balance efficiency and defense utility. In this work, we show that successful adversarial attacks do not rely on the entire image uniformly but instead depend on a small subset of critical image tokens. Based on this insight, we propose Gradient Token Masking (GTM), which localizes these tokens via gradient analysis and neutralizes them through masking. We find that attribution based on the first generated token's output probability fails when attacks preserve the predicted token. To overcome this, GTM utilizes the Hidden-State Gradient Norm score for generation-influence attribution under adversarial inputs. We prove that its ranking is consistent with that of the full adversarial loss gradient, providing a theoretical guarantee for accurate localization. Our method requires only a single forward-backward pass to identify and zero out a small number of high-scoring tokens, effectively disrupting the adversarial attack path. Extensive experiments on prompt injection and multimodal jailbreak attacks demonstrate that our approach reduces attack success rates (ASR) to near zero while preserving model utility with negligible computational overhead.

Dongpeng Zhang, Ke Ma, Yangbangyan Jiang +4

School of Advanced Interdisciplinary Sciences, UCAS · School of Electronic, Electrical and Communication Engineering, UCAS · School of Computer Science and Technology, UCAS +4

Gradient-Based Attribution VLM Robustness Adversarial Attacks on VLMs Prompt Injection Attacks

May 24, 2026cs.CR

Furina: Fragmented Uncertainty-Driven Refusal Instability Attack

Safety alignment in large language models (LLMs) and multimodal large language models (MLLMs) is commonly assumed to operate as a near-binary threshold mechanism. We challenge this assumption by revealing that safety behavior is governed by an instability region where small perturbations induce stochastic refusal decisions rather than deterministic outcomes. We develop a multi-metric diagnostic framework combining external and internal signals to characterize this instability. Through systematic experiments, we identify a characteristic diagnostic signature: inputs in unstable regimes exhibit elevated output uncertainty yet decreased internal safety activation, a decoupling phenomenon that explains why detection-based defenses fail against sophisticated attacks. Building on this framework, we introduce Furina, a jailbreak attack that deliberately induces this signature through fragmented, scene-anchored prompts without model-specific optimization. Furina outperforms strong single-turn and multi-turn baselines on HarmBench and achieves competitive results on MM-SafetyBench, demonstrating that uncertainty amplification provides a principled and transferable mechanism for understanding safety vulnerabilities. Code is available at: https://github.com/0xCavaliers/Furina_Jailbreak.

Tongxi Wu, Jian Zhang, Yang Gao

School of Intelligence Science and Technology, Nanjing University, Suzhou, China · State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China

Adversarial Attacks on VLMs LLM Safety LLM Jailbreak Attacks LLM Safety Evaluation

May 23, 2026cs.CV

Med-R2: An Adversarial Benchmark for Evidence-Grounded Reasoning in Medical VLMs

Vision-language models have demonstrated impressive capabilities in general medical visual question answering, yet due to limited interpretability, it remains unclear whether their predictions reflect evidence-grounded clinical reasoning or reliance on spurious priors. We introduce Med-R2 Bench, a hierarchical benchmark aligned with the clinical workflow to evaluate adversarial robustness with visual grounding. We design stepwise QA tasks to assess whether reasoning chains are strictly grounded in visual evidence across the four clinical stages, and employ adversarial perturbations to test robustness against misleading cues. Med-R2 comprises 42,432 images, 31 task categories, and 110,406 QA pairs. Evaluation across 14 VLMs reveals a sequential performance degradation along the four-stage clinical workflow. Adversarial experiments show that models rely heavily on correct prompts to guess answers. Even when provided with explicit visual cues, the models struggle to accurately align textual descriptions. Finally, we demonstrate stepwise fine-tuning using our hierarchical data significantly improves reasoning robustness, highlighting its potential to drive future improvements in evidence-based medical AI.

Wen Ma, Fucheng Niu, Zhiting Fan +3

Zhejiang University, Zhejiang, China · Guangdong Institute of Intelligence Science and Technology

Adversarial Attacks on VLMs Healthcare Medical VLMs VLM Reasoning Visually Grounded Reasoning Medical Image Grounding+1

May 22, 2026cs.CL

Same Model, Different Weakness: How Language and Modality Reshape the Jailbreak Attack Surface in Frontier MLLMs

The attack surface of a multimodal large language model (MLLM) is language-dependent in ways that reveal the mechanistic structure of alignment failures. We present the first systematic cross-lingual, multimodal red-teaming study comparing jailbreak vulnerability in US English (en-US) and Mexican Spanish (es-MX) across four frontier MLLMs: Claude Sonnet 4.5, GPT-5, Pixtral Large, and Qwen Omni. Using a fixed adversarial benchmark of 363 diverse prompt scenarios administered in text-only and multimodal conditions, we collected 52,272 harm ratings and binary attack success judgements from matched panels of nine native-speaker annotators per language group. Our central finding is that language does not scale vulnerability uniformly. Bayesian mixed-effects analyses reveal that linguistic framing attacks such as role-play become substantially less effective under Spanish prompting, while visually explicit multimodal attacks become more effective, which directly implicates the prompt-language interface rather than global annotator leniency. This dissociation indicates that linguistic and visual alignment failures operate through distinct mechanisms, and that switching language is sufficient to expose that separation. The practical consequence is that safety rankings are not preserved across languages. Qwen Omni overtakes Pixtral Large as the most vulnerable model among es-MX participants, a rank reversal no scalar correction of English-condition scores could recover, and absolute attack success rates have declined across model generations without closing the gaps between them. These findings demonstrate that safety evaluation frameworks treating language and modality as independent dimensions fundamentally misspecify the attack surface of globally deployed MLLMs, and must be redesigned accordingly.

Casey Ford, Madison Van Doren, Sicheng Jin +1

Appen

Multilingual Language Model Evaluation Adversarial Attacks on VLMs Language Model Safety Evaluation Multimodal Jailbreak Attacks Multimodal Model Evaluation

May 21, 2026cs.CV

Exposing Vulnerabilities in Visible-Infrared VLMs: A Unified Geometric Adversarial Framework with Cross-Task Transferability

Vision-language models (VLMs) have achieved strong performance across diverse multimodal tasks, but their adversarial robustness in visible-infrared (VIS-IR) scenarios remains underexplored. This gap is critical because VIS-IR sensing is widely used in real-world perception systems to support reliable understanding under challenging imaging conditions. To address this cross-modal threat setting, we propose CFGPatch, a curved-edge fractal geometric adversarial patch framework for attacking VIS-IR VLMs. CFGPatch builds on triangular fractal geometry and replaces rigid straight-edged primitives with Bezier-curved elements, preserving multi-scale fractal self-similarity while introducing smoother contours, richer directional variation, and more flexible shape deformation. In addition, we design a modality-specific Fraser-spiral rendering mechanism to inject fine-grained texture distortions and misleading perceptual cues into visible and infrared images. By coupling global curved-fractal geometry with local spiral-based appearance interference, CFGPatch disrupts both shape perception and texture interpretation. We further adopt expectation over transformation (EOT) to improve robustness against common image-level transformations. Extensive experiments show that CFGPatch effectively fools VIS-IR VLMs and consistently outperforms standard patch baselines in attack effectiveness and robustness. Moreover, adversarial samples optimized for zero-shot classification transfer well to image captioning and visual question answering, demonstrating strong cross-task transferability and generalizability across downstream tasks.

Xiang Chen, Yuxian Dong, Chao Li +6

VLM Robustness Adversarial Patch Attacks Adversarial Attacks on VLMs Large Vision-Language Models Transfer-Based Adversarial Attacks Physical Adversarial Attacks

May 20, 2026cs.CR

Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs

Multimodal large language models (MLLMs) remain vulnerable to transfer-based targeted attacks, where perturbations optimized on open-source surrogate encoders can generalize to closed-source MLLMs. A key challenge for improving adversarial transferability is to effectively capture the intrinsic visual focus shared across different models, such that perturbations align with transferable semantic cues rather than surrogate-specific behaviors. However, existing methods suffer from spatial-domain feature redundancy and surrogate-specific gradient signals, thereby hindering cross-model transferability. In this paper, we propose FRA-Attack, which addresses both challenges from a unified frequency-domain regularization perspective. For feature alignment, a high-pass DCT objective on patch features suppresses redundant global structures and concentrates the loss on the high-frequency band that carries the MLLMs' intrinsic visual focus. For gradient optimization, we introduce Frequency-domain Gradient Regularization (FGR), a \textit{model-agnostic} low-pass regularizer that modulates the surrogate gradient using only the geometric frequency coordinate, \textit{i.e.}, no surrogate-derived statistic is involved, so that FGR is model-agnostic by construction, removing surrogate-specific high-frequency artifacts while preserving transferable low-frequency directions. Together, the two components form a unified frequency-domain treatment of transferability. Extensive experiments on

15

flagship MLLMs across

7

vendors show that FRA-Attack achieves superior cross-model transferability, particularly with state-of-the-art performance on GPT-5.4, Claude-Opus-4.6 and Gemini-3-flash.

Leitao Yuan, Qinghua Mao, Daizong Liu +5

Shanghai Artificial Intelligence Laboratory · Zhejiang University · Shanghai Jiao Tong University +3

Adversarial Attacks on VLMs Multimodal Large Language Models Transfer-Based Adversarial Attacks Adversarial Transferability

May 19, 2026cs.CV

Towards Fine-Grained Robustness: Attention-Guided Test-Time Prompt Tuning for Vision-Language Models

Vision-Language Models (VLMs), such as CLIP, have achieved significant zero-shot performance on downstream tasks with various fine-tuning adaptation methods. However, recent studies have proven that adversarial attacks can significantly degrade the inference ability of VLMs, posing substantial risks to their practical applications. Prevalent test-time adaptation methods typically rely on multi-view augmentation to implement various fine-tuning strategies, which struggle to identify semantic information and are prone to destroying discriminative regions in fine-grained scenarios. To address these limitations, we propose Attention-Guided Test-Time Prompt Tuning (A-TPT), a semantics-preserving method designed for test-time adaptation. We first refine the gradient attention rollout mechanism to identify semantically meaningful regions surviving under adversarial attacks. Furthermore, we leverage them to guide the spatially varying augmentation intensities and multi-view ensemble for prompt tuning and inference. Extensive experiments demonstrate that A-TPT outperforms existing test-time adaptation methods on both adversarial and clean data. Codes are available at https://github.com/SEU-VIPGroup/A-TPT .

Jia-Wei Hai, Yijun Wang, Xiu-Shen Wei

School of Computer Science and Engineering, and Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Southeast University, China. · School of Intelligence Science and Engineering, Southeast University, China.

VLM Robustness Adversarial Attacks on VLMs Test-Time Adaptation Test-Time Adaptation of VLMs Test-Time Prompt Tuning

May 18, 2026cs.CR

Surviving the Unseen: Predictive Defense for Novel Multi-Turn Multimodal Attacks

The expansion of Multimodal Large Language Models (MLLMs) and their integration into autonomous agentic workflows has introduced a non-stationary attack surface. Empirical observations indicate that adversaries employ progressive, cross-modal perturbations that evade turn-specific guardrails by distributing malicious intent across longitudinal conversational trajectories. Static defense mechanisms, constrained by the Markov property, evaluate inputs in isolation and fail to detect cumulative structural poisoning. To handle this limitation, this paper formulates safety verification as a dynamic survival prediction and trajectory dynamics problem. The Triple-tier Anomaly Defense (TRIAD) framework is proposed as a predictive model that maps multimodal and multi-turn conversational flow as a continuous trajectory. The framework integrates structural anomaly detection to monitor covariance shifts, a Ledoit-Wolf regularized Mahalanobis distance to monitor covariance shifts in high-dimensional spaces, and topological trajectory acceleration to differentiate benign creative exploration from continuous malicious drift. These kinematic and geometric features are integrated into a time-varying Cox Proportional Hazards model via a Bayesian Hidden Markov Model (HMM) feedback loop. Theoretical analysis demonstrates that the TRIAD framework provides a mathematically bounded expected time-to-failure under adversarial perturbations, ensuring that malicious acceleration diverges positively. This framework provides a computationally efficient, interpretable, and predictive safeguard for real-time agentic AI systems, establishing a rigorous foundation for continuous safety alignment without relying on empirical retraining.

Doohee You

Trust and Safety, Google

Adversarial Attacks on VLMs Multimodal Robustness AI Agent Safety AI Agent Monitoring

May 18, 2026cs.CR

Not What You Asked For: Typographic Attacks in Household Robot Manipulation

Open-vocabulary embodied AI agents increasingly rely on vision-language models such as CLIP for object perception and task grounding. However, the shared embedding space that enables this flexibility introduces a structural vulnerability to typographic attacks, where printed text in a physical scene semantically overrides visual judgment. While prior work has quantified this threat in static 2D benchmarks and 3D navigation tasks, its impact on the full Sense-Plan-Act pipeline of household robot manipulation remains unexplored. This work evaluates typographic attacks in a Habitat-based simulation using the HomeRobot benchmark. We introduce a decoupled perception architecture that exposes a frozen CLIP encoder to adversarial stickers while maintaining geometric grounding via DETIC. In a controlled evaluation pool of 59 attributable episodes, the attack achieves an overall Attack Success Rate (ASR) of 67.8%, rising to 70.0% among fully successful episodes, under uncontrolled viewing angles and occlusion with no perceptual optimization. Critically, we find that perceptual errors propagate through the persistent 3D semantic map to produce kinetic failures, defined here as physically executed grasping and transport of the wrong object driven by an adversarially poisoned semantic state. In these cases, the robot physically grasps and delivers the wrong object to a target receptacle. These results establish typographic misclassification as a real, measurable, and physically consequential threat to the safety of modular manipulation pipelines that prior typographic attack research has left unexamined.

Ali Iranmanesh, Peng Liu

Cyber Security Lab The Pennsylvania State University State College, USA

Adversarial Attacks on VLMs Robotic Manipulation

May 17, 2026cs.CV

TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models

Large-scale pre-trained Vision-Language models (VLMs), such as CLIP, exhibit strong zero-shot generalization, yet remain highly vulnerable to imperceptible adversarial perturbations, raising serious safety concerns for open-world deployment. To enhance robustness without requiring downstream task-specific retraining, we propose TAME, a novel test-time defense. Building upon our prior Test-Time Adversarial Prompt Tuning (TAPT), TAME introduces an architectural reformulation by replacing TAPT's single adaptive prompt with an input-conditioned Mixture-of-Experts (MoE) framework, enabling more expressive and adaptive defense. Specifically, TAME maintains a bank of learnable expert prompts and employs an input-dependent routing mechanism to aggregate a customized prompt mixture for each unlabeled test sample at inference time. This test-time defense mechanism is driven by three unsupervised objectives: (1) multi-view prediction entropy minimization, (2) layer-wise alignment of visual token statistics to precomputed clean and adversarial reference distributions, and (3) MoE regularization for balanced expert utilization and prompt diversity. We evaluated TAME on 11 benchmark datasets, including ImageNet and 10 additional zero-shot datasets. The results show that TAME improves the zero-shot adversarial robustness of the original CLIP by at least 49.1% under AutoAttack while largely preserving generalization on clean samples. TAME also consistently outperforms existing adversarial prompt tuning methods across multiple prompt designs, yielding an average robustness gain of at least 30.2%.

Xin Wang, Yixu Wang, Jiaming Zhang +6

Adversarial Attacks on VLMs Test-Time Adaptation VLM Adaptation Test-Time Prompt Tuning

May 17, 2026cs.CV

Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models

Existing adversarial attacks on vision-language models (VLMs) can steer model outputs toward attacker-specified target responses, but their effectiveness often degrades when the same perturbed input is paired with different textual queries. This paper studies cross-query response manipulation, where a single adversarial example is expected to remain effective across diverse user queries. We first analyze the limitations of existing attacks and find that successful transfer is closely associated with preserving an image-dominant attention pattern during response generation. Motivated by the observation, we propose \textbf{Attention Hijacking}, a novel adversarial attack that explicitly steers internal attention distributions toward a persistent image-dominant pattern. By amplifying the influence of visual tokens on target response tokens while suppressing the competing influence of textual tokens, our method reduces the dependence of the manipulated output on the specific wording of the query. Extensive experiments on widely used VLMs show that Attention Hijacking substantially improves cross-query transferability across diverse target responses and unseen queries. The method also extends effectively to multiple attack scenarios, offering new insights into the role of attention stability in transferable response manipulation for VLMs.

Zhiqiang Wang, Dongrui Liu, Yan Li +4

Hong Kong University of Science and Technology · Shanghai Jiao Tong University · Beihang University

Adversarial Attacks on VLMs Adversarial Attacks Transfer-Based Adversarial Attacks

May 15, 2026cs.CV

Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations

Explanation mechanisms are increasingly used to support transparency and trust in vision-language models (VLMs), particularly in settings where model decisions require human oversight. However, the robustness of these explanations remains insufficiently understood. In this work, we investigate whether explanation heatmaps in VLMs, particularly CLIP-based models, faithfully reflect model reasoning under adversarial conditions. We show that explanation maps can be systematically manipulated while preserving the model's original prediction, revealing a disconnect between predictive behavior and explanation faithfulness. To study this vulnerability, we introduce X-Shift, a novel grey-box attack that perturbs patch-level visual representations to redirect explanation heatmaps toward semantically irrelevant regions without altering the predicted output. Unlike conventional adversarial attacks that aim to induce misclassification, X-Shift specifically targets the integrity of the explanation process itself. The attack operates without modifying model parameters and generalizes across multiple CLIP architectures and explanation methods. We evaluate the proposed approach on ImageNet-1k, MS-COCO, and Flickr30K, demonstrating consistent degradation in explanation alignment under imperceptible perturbations while maintaining prediction stability. Furthermore, standard prediction-oriented adversarial attacks fail to reproduce the same explanation-shifting behavior even under substantially larger perturbation budgets. Our findings highlight a fundamental limitation of current explanation mechanisms in VLMs and raise concerns about their use as reliable indicators of model trustworthiness in high-impact applications.

Narges Babadi, Hadis Karimipour

Department of Electrical and Software Engineering, University of Calgary, Calgary, Canada.

VLM Robustness Adversarial Attacks on VLMs Adversarial Attacks VLM Interpretability

May 15, 2026cs.CR

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation

Large vision-language models (LVLMs) have emerged as a powerful paradigm for multimodal intelligence, but their growing deployment also expands the attack surface of prompt injection. Despite this growing concern, existing attacks still suffer from a critical limitation: the injected prompt for one modality only steers the model's interpretation of that singular input. Alternatively, these attacks remain multimodal but fail to achieve cross-modal prompt perturbation. To bridge this gap, we introduce a novel cross-modal prompt injection attack CrossMPI, which can steer the model's interpretation of both textual and visual inputs via image-only prompt injection. Our design is underpinned by the following key breakthroughs. First, we turn the focus of the injected prompt perturbation optimization from the visual embedding space (typically with only

10^5

parameters) to the model hidden state space (for multimodal information integration and with

10^7

parameters). Then, two strategies are adopted to mitigate the optimization challenges posed by the larger parameter space. To constrain the optimized model parameter space, we introduce a layer selection strategy that identifies the layers most critical to multimodal integration. Interestingly, deviating from the past experience, our analysis reveals that the optimal layers for LVLM prompt perturbation reside in the middle of the model rather than the last. To constrain the image perturbation space, we propose a new distance-decremental perturbation budget assignment strategy that allocates budgets decrementally as the pixel distance to semantic-critical regions increases. Extensive experiments across multiple LVLMs and datasets show that our method significantly outperforms baseline approaches.

Hao Yang, Zhuo Ma, Yang Liu +3

Xidian University Xi’an, Shaanxi, China

VLM Robustness Adversarial Attacks on VLMs Large Vision-Language Models

May 15, 2026cs.CR

DarkLLM: Learning Language-Driven Adversarial Attacks with Large Language Models

While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial attacks. However, traditional adversarial attacks are typically limited to single, predefined objectives, tightly coupling each attack to a specific model or task, which restricts their scalability and flexibility in real-world scenarios. In this work, we present DarkLLM, a novel attack framework that trains an LLM to translate natural-language attack instructions into latent attack vectors, which are then decoded into visual adversarial perturbations. By leveraging natural-language instruction tuning, DarkLLM not only unifies targeted, untargeted, segmentation, and multi-model attacks within a single framework, but also achieves flexible and controllable adversarial generation, enabling each instruction to produce a perturbation that induces desired behaviors across heterogeneous models. Through extensive experiments across 4 tasks, 13 datasets, and 15 models, we demonstrate that DarkLLM with only 1B parameters can follow attacker instructions and generate highly effective attacks against CLIP, SAM, and frontier LLMs, revealing a systemic vulnerability in modern foundation models.

Ye Sun, Xin Wang, Jiaming Zhang +7

Fudan University · Nanyang Technological University · Tongji University

Adversarial Attacks on VLMs Adversarial Perturbations Multimodal Foundation Models

May 12, 2026cs.AI

SafeSteer: A Decoding-level Defense Mechanism for Multimodal Large Language Models

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning or inefficient post-hoc interventions, limiting their ability to address novel attacks and involving performance trade-offs. To address the above issues, we explore the inherent safety capabilities within MLLMs and quantify their intrinsic ability to discern harmfulness at decoding stage. We observe that 1) MLLMs can distinguish the harmful and harmless inputs during decoding process, 2) Image-based attacks are more stealthy. Based on these insights, we introduce SafeSteer, a decoding-level defense mechanism for MLLMs. Specifically, it includes a Decoding-Probe, a lightweight probe for detecting and correcting harmful output during decoding, which iteratively steers the decoding process toward safety. Furthermore, a modal semantic alignment vector is integrated to transfer the strong textual safety alignment to the vision modality. Experiments on multiple MLLMs demonstrate that SafeSterr can improve MLLMs' safety by up to 33.40% without fine-tuning. Notably, it can maintain the effectiveness of MLLMs, ensuring a balance between their helpfulness and harmlessness.

Xinyi Zeng, Xue Yang, Jingyuan Zhang +5

Tsinghua University, Beijing, China · Shanghai Jiao Tong University · Kuaishou Technology, Beijing, China +4

Adversarial Attacks on VLMs Multimodal Robustness Multimodal Large Language Models LLM Safety Alignment LLM Safety Inference-Time Intervention

May 11, 2026cs.CV

Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization

Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibility of transferable multimodal jailbreaks. We revisit this conclusion under a strictly untargeted threat model without enforcing a fixed prefix or response pattern. Our preliminary experiment reveals that refusal behavior concentrates at high-entropy tokens during autoregressive decoding, and non-refusal tokens already carry substantial probability mass among the top-ranked candidates before attack. Motivated by this finding, we propose Untargeted Jailbreak via Entropy Maximization(UJEM)-KL, a lightweight attack that maximizes entropy at these decision tokens to flip refusal outcomes, while stabilizing the remaining low-entropy positions to preserve output quality. Across three VLMs and two safety benchmarks, UJEM-KL achieves competitive white-box attack success rates and consistently improves transferability, while remaining effective under representative defenses. Our experimental results indicate that the limited transferability primarily stems from overly constrained optimization objectives.

Mengqi He, Xinyu Tian, Xin Shen +6

Australian National University, ACT, Australia · The University Of Queensland, Brisbane, Queensland, Australia · GE research, Niskayuna, New York, USA +2

Adversarial Attacks on VLMs Adversarial Attacks Multimodal Jailbreak Attacks Transfer-Based Adversarial Attacks Adversarial Transferability

May 11, 2026cs.CR

Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) is a widely adopted paradigm for enhancing LLMs in medical applications by incorporating expert multimodal knowledge during generation. However, the underlying retrieval databases may naturally contain, or be intentionally injected with, adversarial knowledge, which can perturb model outputs and undermine system reliability. To investigate this risk, prior studies have explored knowledge poisoning attacks in medical RAG systems. Nevertheless, most of them rely on the strong assumption that adversaries possess prior knowledge of user queries, which is unrealistic in deployments and substantially limits their practical applicability. In this paper, we propose M\textsuperscript{3}Att, a knowledge-poisoning framework designed for medical multimodal RAG systems, assuming only limited distribution knowledge of the underlying database. Our core idea is to inject covert misinformation into textual data while using paired visual data as a query-agnostic trigger to promote retrieval. We first propose a unified framework that introduces imperceptible perturbations to visual inputs to manipulate retrieval probabilities. Besides, due to the prior medical knowledge in LLMs, naively poisoned medical content with explicit factual errors can be corrected during generation. Thus, we leverage the inherent ambiguity of medical diagnosis and design a covert misinformation injection strategy that degrades diagnostic accuracy while evading model self-correction. Experiments on five LLMs and datasets demonstrate that M\textsuperscript{3}Att consistently produces clinically plausible yet incorrect generations. Codes: https://github.com/ypr17/M3Att.

Peiru Yang, Haoran Zheng, Tong Ju +6

1Tsinghua University · 2Beijing University of Posts and Telecommunications · 3Northwestern Polytechnical University +1

Multimodal RAG Adversarial Attacks on VLMs Retrieval-Augmented Generation RAG Poisoning Attacks RAG Security

May 11, 2026cs.CV

Adversarial Attacks Against MLLMs via Progressive Resolution Processing and Adaptive Feature Alignment

Adversarial perturbations can mislead Multimodal Large Language Models (MLLMs) recognize a benign image as a specific target object, posing serious risks in safety-critical scenarios such as autonomous driving and medical diagnosis. This makes transfer-based targeted attacks crucial for understanding and improving black-box MLLM robustness. Existing transfer-based targeted attack methods typically rely on the final global features of the surrogate encoder and anchor optimization to original-resolution target crops, leading to their limited transferability and robustness. To address these challenges, we propose Progressive Resolution Processing and Adaptive Feature Alignment (PRAF-Attack), a targeted transfer-based attack framework that integrates multi-scale global semantic guidance with robust intermediate-layer local alignment. Unlike prior methods that align only the surrogate encoder's final layer, we design an adaptive feature alignment strategy that leverages intermediate representations to enhance transferability. Specifically, we introduce an adaptive intermediate layer selection mechanism to identify transferable hierarchical features across surrogate ensembles via gradient consistency, along with an adaptive patch-level optimization strategy that preserves highly correlated local regions through efficient patch filtering. To overcome the reliance on fixed original-resolution target crops, we propose a progressive resolution processing strategy that gradually refines optimization from coarse to fine, enabling the attack to better exploit target information at multiple scales and achieve stronger transferability. We evaluate PRAF-Attack on a diverse suite of black-box MLLMs, including six open-source models and six closed-source commercial APIs. Compared with seven state-of-the-art targeted attack baselines, the proposed PRAF-Attack consistently achieves superior transferability.

Haobo Wang, Xiaorong Ma, Weiqi Luo +2

Sun Yat-sen University, China · Nanyang Technological University, Singapore · Shenzhen MSU-BIT University, China

Adversarial Attacks on VLMs Multimodal Large Language Models Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks Adversarial Transferability

May 8, 2026cs.CV

Sparse Autoencoders as Plug-and-Play Firewalls for Adversarial Attack Detection in VLMs

Vision-language models (VLMs) have advanced rapidly and are increasingly deployed in real-world applications, especially with the rise of agent-based systems. However, their safety has received relatively limited attention. Even the latest proprietary and open-weight VLMs remain highly vulnerable to adversarial attacks, leaving downstream applications exposed to significant risks. In this work, we propose a novel and lightweight adversarial attack detection framework based on sparse autoencoders (SAEs), termed SAEgis. By inserting an SAE module into a pretrained VLM and training it with standard reconstruction objectives, we find that the learned sparse latent features naturally capture attack-relevant signals. These features enable reliable classification of whether an input image has been adversarially perturbed, even for previously unseen samples. Extensive experiments show that SAEgis achieves strong performance across in-domain, cross-domain, and cross-attack settings, with particularly large improvements in cross-domain generalization compared to existing baselines. In addition, combining signals from multiple layers further improves robustness and stability. To the best of our knowledge, this is the first work to explore SAE as a plug-and-play mechanism for adversarial attack detection in VLMs. Our method requires no additional adversarial training, introduces minimal overhead, and provides a practical approach for improving the safety of real-world VLM systems.

Hao Wang, Yiqun Sun, Pengfei Wei +2

2Waseda University · 1Magellan Technology Research Institute (MTRI)

VLM Robustness Adversarial Attacks on VLMs Sparse Autoencoders Adversarial Example Detection

May 8, 2026cs.CV

GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability Optimization

Diffusion Vision-Language Models (dVLMs), built upon the non-causal foundations of Diffusion Large Language Models (dLLMs), have demonstrated remarkable efficacy in multimodal tasks by departing from the traditional autoregressive generation paradigm. While dVLMs appear inherently robust against conventional jailbreak tactics, which we categorize as Fixed Prefix Optimization (FPO) (e.g., anchoring responses with "Sure, here is"), this perceived resilience is deceptive. Our investigation into the safety landscape of dVLMs reveals a unique refusal pattern: Immediate Refusal and Progressive Refusal. We find that while FPO-based attacks often fail by triggering the latter, the progressive refinement process itself uncovers a novel, latent attack surface. To exploit this vulnerability, we propose Global Probability Optimization (GPO), a general jailbreak paradigm designed specifically for the denoising trajectory of masked diffusion models. Unlike prefix-based methods, GPO manipulates the global generative dynamics to bypass guardrails in diffusion language models. Building on this, we introduce GPO-V, the first visual-modality jailbreak framework tailored for dVLMs. Empirical results demonstrate that GPO-V produces stealthy perturbations with exceptional cross-model transferability, revealing a critical security gap in non-sequential generative architectures. Our findings underscore the critical urgency of addressing safety alignment in dVLMs. These results necessitate an immediate and fundamental re-evaluation of current defense paradigms to mitigate the unique risks of diffusion-based generation. Our code is available at: https://anonymous.4open.science/r/GPO-V-0250.

Yu Pan, Andi Zhang, Yi Wang +2

ShanghaiTech University · University of Warwick · SUN YAT-SEN UNIVERSITY

Diffusion Model Alignment Adversarial Attacks on VLMs Vision-Language Models Diffusion Language Models

May 8, 2026cs.CV

Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment

Recent advancements in visual context compression enable MLLMs to process ultra-long contexts efficiently by rendering text into images. However, we identify a critical vulnerability inherent to this paradigm: lowering image resolution inadvertently catalyzes jailbreaking. Our experiments reveal that the safety defenses of SOTA models deteriorate sharply as resolution degrades, surprisingly persisting even when text remains legible. We attribute this to

Cognitive Overload'', hypothesizing that the effort required to decipher degraded inputs diverts attentional resources from safety auditing. This phenomenon is consistent across various visual perturbations, including noise and geometric distortion. To address this, we propose a simple

Structured Cognitive Offloading'' strategy that mitigates these risks by enforcing a serialized pipeline to decouple visual transcription from safety assessment. Our work exposes a significant risk in vision-based compression and provides critical insights for the secure design of future MLLMs.

Zhixue Song, Boyan Han, Yiwei Wang +1

1AGI Lab, Westlake University, China · University of California, Merced, USA

VLM Robustness Adversarial Attacks on VLMs LLM Safety Alignment

May 5, 2026cs.CR

Laundering AI Authority with Adversarial Examples

Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly trust that these systems perceive the same visual content as they do. We show that adversarial examples break this assumption, enabling \emph{AI authority laundering}: an attacker subtly perturbs an image so that the VLM produces confident and authoritative responses about the \emph{wrong} input. Unlike jailbreaks or prompt injections, our attacks do not compromise model alignment; the attack operates entirely at the perceptual level. We demonstrate that standard attacks against publicly available CLIP models transfer reliably to production VLMs -- including GPT-5.4, Claude Opus~~4.6, Gemini~~3, and Grok~4.2. Across four attack surfaces, we show that authority laundering can amplify misinformation, disparage individuals, evade content moderation, and manipulate product recommendations. Our attacks have high success rates: In hundreds of attacks targeting identity manipulation and NSFW evasion, we measure success rates of

22 - 100\%

across six models. No novel attack algorithm is required: basic techniques known for over a decade suffice, establishing a lower bound on attacker capability that should concern defenders. Our results demonstrate that visual adversarial robustness is now a practical -- and still largely unsolved -- safety problem.

Jie Zhang, Pura Peetathawatchai, Florian Tramèr +1

ETH Zurich · Switzerland

VLM Robustness Adversarial Attacks on VLMs Adversarial Examples

May 4, 2026cs.AI

CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models

Vision-Language Models (VLMs) have achieved remarkable success in tasks such as image captioning and visual question answering (VQA). However, as their applications become increasingly widespread, recent studies have revealed that VLMs are vulnerable to backdoor attacks. Existing backdoor attacks on VLMs primarily rely on data poisoning by adding visual triggers and modifying text labels, where the induced image-text mismatch makes poisoned samples easy to detect. To address this limitation, we propose the Clean-Label Backdoor Attack on VLMs via Diffusion Models (CBV), which leverages diffusion models to generate natural poisoned examples via score matching. Specifically, CBV modifies the score during the reverse generation process of the diffusion model to guide the generation of poisoned samples that contain triggered image features. To further enhance the effectiveness of the attack, we incorporate the textual information of the triggered images as multimodal guidance during generation. Moreover, to enhance stealthiness, we introduce a GradCAM-guided Mask (GM) that restricts modifications to only the most semantically important regions, rather than the entire image. We evaluate our method on MSCOCO and VQA v2 with four representative VLMs, achieving over 80% ASR while preserving normal functionality.

Ji Guo, Xiaolong Qin, Cencen Liu +3

Laboratory of Intelligent Collaborative Computing, University of Electronic Science and Technology of China, China · School of Software Engineering, Chengdu University of Information Technology, China · The Hong Kong University of Science and Technology, China

VLM Robustness Adversarial Attacks on VLMs Backdoor Attacks Backdoor Attacks on VLMs

May 2, 2026cs.CR

VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models

Universal adversarial attacks on aligned multimodal large language models are increasingly reported with attack success rates in the 60-80% range, suggesting the visual modality is highly vulnerable to imperceptible perturbations as a prompt-injection channel. We argue that this number conflates two distinct events: (i) the model's output was perturbed (Influence), and (ii) the attacker's chosen target concept was actually emitted (Precise Injection). We compose two existing techniques -- Universal Adversarial Attack and AnyAttack -- under an

L_{inf}

budget of 16/255, and we add a dual-axis evaluation: a deterministic Ratcliff-Obershelp drift score for Influence (programmatic baseline) plus a 4-tier ordinal categorical none/weak/partial/confirmed for Precise Injection. The judge is DeepSeek-V4-Pro in thinking mode, calibrated against Claude Opus 4.7 with Cohen's

κ

= 0.77 on the injection axis (substantial agreement); the entire 4475-entry SHA-256 input cache ships with the dataset so reviewers can re-derive paper numbers bit-exact without an API key. Across 6615 pairs over four open VLMs, seven attack prompts, and seven test images, the two axes diverge by roughly 90

\times

: 66.4% of pairs are programmatically disturbed (LLM-judged 46.6% at the substantial-or-complete tier), but only 0.756% (50/6615) reach any non-none injection tier and only 0.030% (2/6615) verbatim. The few injections that do land cluster on screenshot- or document-style carriers whose semantics already invite text transcription. BLIP-2 shows \emph{zero detectable drift} at

L_{inf}

= 16/255 across all 2205 pairs even when used as a Stage-1 surrogate. We release the full dataset -- 21 universal images, 147 adversarial photos, 6,615 response pairs, the v3 dual-axis judge results, and the cache at huggingface.co/datasets/jeffliulab/visinject.

Pang Liu, Yingjie Lao

Department of Electrical and Computer Engineering, Tufts University

VLM Evaluation VLM Robustness Adversarial Attacks on VLMs Prompt Injection Prompt Injection Attacks on LLMs

May 1, 2026cs.CV

Jailbreaking Vision-Language Models Through the Visual Modality

The visual modality of vision-language models (VLMs) is an underexplored attack surface for bypassing safety alignment. We introduce four jailbreak attacks exploiting the vision component: (1) encoding harmful instructions as visual symbol sequences with a decoding legend, (2) replacing harmful objects with benign substitutes (e.g., bomb -> banana) then prompting for harmful actions using the substitute term, (3) replacing harmful text in images (e.g., on book covers) with benign words while visual context preserves the original meaning, and (4) visual analogy puzzles whose solution requires inferring a prohibited concept. Evaluating across six frontier VLMs, our visual attacks bypass safety alignment and expose a cross-modality alignment gap: text-based safety training does not automatically generalize to harmful intent conveyed visually. For example, our visual cipher achieves 40.9% attack success on Claude-Haiku-4.5 versus 10.7% for an equivalent textual cipher. To further our insight into the attack mechanism, we present preliminary interpretability and mitigation results. These findings highlight that robust VLM alignment requires treating vision as a first-class target for safety post-training.

Aharon Azulay, Jan Dubiński, Zhuoyun Li +2

Independent · NASK National Research Institute, Warsaw, Poland · Warsaw University of Technology, Warsaw, Poland +3

Adversarial Attacks on VLMs Vision-Language Models Modality Gap in VLMs Vision-Language Alignment