Adversarial Attacks on VLMs

VLM: Vision-Language Model

Follow this topic Ask about this topic

This field studies how image perturbations, embedded text, physical patches, poisoned training data, and multi-turn prompts can make models misread scenes, follow malicious instructions, leak information, or fail in agent tasks. Approaches include gradient-based and transferable attacks, typographic and visual prompt injection, jailbreak red-teaming, and backdoors, evaluated across tasks such as visual question answering, captioning, document understanding, video, and robotics. Defenses range from adversarial training and robust encoders to test-time transformations, token or attention interventions, prompt screening, and response monitoring. A central challenge is improving safety and robustness without sacrificing clean accuracy, utility, or latency, while accounting for uneven transfer across models, modalities, languages, and deployment settings.

Latest papers

183 papers23 papers in the last four weeks, up 77% on the four weeks before. 0.1% of all new papers.

Apr 19, 2026

Cross-Modal Attention Analysis and Optimization in Vision-Language Models: A Study on Visual Reliability

Vision-Language Models (VLMs) achieve strong cross-modal performance, yet recent evidence suggests they over-rely on textual descriptions while under-utilizing visual evidence -- a phenomenon termed ``text shortcut learning.'' We propose an adversarial evaluation framework that quantifies this cross-modal dependency by measuring accuracy degradation (Drop) when semantically conflicting text is paired with unchanged images. Four adversarial strategies -- shape_swap, color_swap, position_swap, and random_text -- are applied to a controlled geometric-shapes dataset (

n{=}1{,}000

). We compare three configurations: Baseline CLIP (ViT-B/32), LoRA fine-tuning, and LoRA Optimized (integrating Hard Negative Mining, Label Smoothing, layer-wise learning rates, Cosine Restarts, curriculum learning, and data augmentation). The optimized model reduces average Drop from 27.5% to 9.8% (64.4% relative improvement,

p{<}0.001

) while maintaining 97% normal accuracy. Attention visualization and embedding-space analysis confirm that the optimized model attends more to visual features and achieves tighter cross-modal alignment.

Lijie Zhou

School of Computer Science University of Nottingham Ningbo China Ningbo, China

Cross-Modal Learning VLM Robustness Adversarial Attacks on VLMs Vision-Language Models VLM Adaptation Attention Mechanisms+3

Apr 15, 2026

Penny Wise, Pixel Foolish: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations

The rapid proliferation of Multimodal Large Language Models (MLLMs) has enabled mobile agents to execute high-stakes financial transactions, but their adversarial robustness remains underexplored. We identify Visual Dominance Hallucination (VDH), where imperceptible visual cues can override textual price evidence in screenshot-based, price-constrained settings and lead agents to irrational decisions. We propose PriceBlind, a stealthy white-box adversarial attack framework for controlled screenshot-based evaluation. PriceBlind exploits the modality gap in CLIP-based encoders via a Semantic-Decoupling Loss that aligns the image embedding with low-cost, value-associated anchors while preserving pixel-level fidelity. On E-ShopBench, PriceBlind achieves around 80% ASR in white-box evaluation; under a simplified single-turn coordinate-selection protocol, Ensemble-DI-FGSM transfers with roughly 35-41% ASR across GPT-4o, Gemini-1.5-Pro, and Claude-3.5-Sonnet. We also show that robust encoders and Verify-then-Act defenses reduce ASR substantially, though with some clean-accuracy trade-off.

Jiachen Qian, Zhaolu Kang

City University of Hong Kong · Peking University

VLM Robustness Adversarial Attacks on VLMs Adversarial Attacks on Unified Multimodal Models Multimodal Hallucination Modality Gap in VLMs

Apr 14, 2026

Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attacks

Vision-Language Models (VLMs) have shown remarkable performance, yet their security remains insufficiently understood. Existing adversarial studies focus almost exclusively on the digital setting, leaving physical-world threats largely unexplored. As VLMs are increasingly deployed in real environments, this gap becomes critical, since adversarial perturbations must be physically realizable. Despite this practical relevance, physical attacks against VLMs have not been systematically studied. Such attacks may induce recognition failures and further disrupt multimodal reasoning, leading to severe semantic misinterpretation in downstream tasks. Therefore, investigating physical attacks on VLMs is essential for assessing their real-world security risks. To address this gap, we propose Multimodal Semantic Lighting Attacks (MSLA), the first physically deployable adversarial attack framework against VLMs. MSLA uses controllable adversarial lighting to disrupt multimodal semantic understanding in real scenes, attacking semantic alignment rather than only task-specific outputs. Consequently, it degrades zero-shot classification performance of mainstream CLIP variants while inducing severe semantic hallucinations in advanced VLMs such as LLaVA and BLIP across image captioning and visual question answering (VQA). Extensive experiments in both digital and physical domains demonstrate that MSLA is effective, transferable, and practically realizable. Our findings provide the first evidence that VLMs are highly vulnerable to physically deployable semantic attacks, exposing a previously overlooked robustness gap and underscoring the urgent need for physical-world robustness evaluation of VLMs.

Yingying Zhao, Chengyin Hu, Qike Zhang +7

Adversarial Attacks on VLMs VLM Robustness

Apr 14, 2026

Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs

Vision-Language Models (VLMs) expand the attack surface of safety-aligned systems by coupling visual perception with text generation. Existing multimodal jailbreak attacks primarily rely on crafted visual content, adversarial perturbations, or image-specific attack strategies, leaving the potential of reusable visual anchors in benign natural images largely unexplored. To address the problem, we introduce MemJack, a memory-augmented multi-agent framework for automated VLM red-teaming with natural images. MemJack combines visual-anchor discovery, visual-semantic camouflage, response evaluation, reflection-guided repair, and dynamic replanning within a closed-loop attack pipeline. Beyond attack generation, MemJack automatically transforms public images into attack anchors, enables the construction of MemJack-Bench, a dataset of over 113,000 interactive multimodal jailbreak trajectories for safety evaluation and defensive alignment. Extensive empirical evaluations across full, unmodified COCO val2017 images demonstrate that MemJack achieves a 71.48% attack success rate (ASR) against Qwen3-VL-Plus, scaling to 90% under extended budgets. Compared with representative multimodal jailbreak baselines under the same natural-image evaluation setting, MemJack achieves the highest ASR while requiring fewer mean rounds to success, demonstrating superior jailbreak effectiveness on VLMs. These results demonstrate that benign natural images can act as transferable jailbreak anchors and reveal substantial vulnerabilities in current safety-aligned VLMs.

Jianhao Chen, Shiqin Wang, Haoyang Chen +4

School of Computer Science, Wuhan University, Wuhan, China · Zhongguancun Academy, Beijing, China · Tianjin University, Tianjin, China +1

Adversarial Attacks on VLMs VLM Evaluation Multimodal Model Evaluation

Apr 14, 2026

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models

Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted results are accessible. Research on this problem is in its infancy, and only a handful of methods are available. Nevertheless, existing methods either rely on a complex iterative cross-search strategy, which inevitably consumes numerous queries, or only consider reducing the similarity of positive image-text pairs but ignore that of negative ones, which will also be implicitly diminished, thus inevitably affecting the attack performance. To alleviate the above issues, we propose a simple yet effective framework to generate high-quality adversarial examples on vision-language pre-trained models, named HQA-VLAttack, which consists of text and image attack stages. For text perturbation generation, it leverages the counter-fitting word vector to generate the substitute word set, thus guaranteeing the semantic consistency between the substitute word and the original word. For image perturbation generation, it first initializes the image adversarial example via the layer-importance guided strategy, and then utilizes contrastive learning to optimize the image adversarial perturbation, which ensures that the similarity of positive image-text pairs is decreased while that of negative image-text pairs is increased. In this way, the optimized adversarial images and texts are more likely to retrieve negative examples, thereby enhancing the attack success rate. Experimental results on three benchmark datasets demonstrate that HQA-VLAttack significantly outperforms strong baselines in terms of attack success rate.

Han Liu, Jiaqi Li, Zhi Xu +5

Dalian University of Technology, Dalian, China · The Pennsylvania State University, Pennsylvania, USA · Shenzhen University, Shenzhen, China

Adversarial Attacks on VLMs Black-Box Adversarial Attacks Adversarial Text Attacks

Apr 14, 2026

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models

We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as VLMs serve as the perceptual backbone of autonomous agents, from browser automation and computer-use systems to camera-equipped embodied agents. In practice, the attack surface is heterogeneous: adversarial text appears at varying font sizes and under diverse visual conditions, while the growing ecosystem of VLMs exhibits substantial variation in vulnerability, complicating defensive approaches. Evaluating 1,000 prompts from SALAD-Bench across four VLMs, namely, GPT-4o, Claude Sonnet 4.5, Mistral-Large-3, and Qwen3-VL-4B-Instruct under varying font sizes (6--28px) and visual transformations (rotation, blur, noise, contrast changes), we find: (1) font size significantly affects attack success rate (ASR), with very small fonts (6px) yielding near-zero ASR while mid-range fonts achieve peak effectiveness; (2) text attacks are more effective than image attacks for GPT-4o (36% vs 8%) and Claude (47% vs 22%), while Qwen3-VL and Mistral show comparable ASR across modalities; (3) text-image embedding distance from two multimodal embedding models (JinaCLIP and Qwen3-VL-Embedding) shows strong negative correlation with ASR across all four models (r = -0.71 to -0.93, p < 0.01); (4) heavy degradations increase embedding distance by 10--12% and reduce ASR by 34--96%, while rotation asymmetrically affects models (Mistral drops 50%, GPT-4o unchanged). These findings highlight that model-specific robustness patterns preclude one-size-fits-all defenses and offer empirical guidance for practitioners selecting VLM backbones for agentic systems operating in adversarial environments.

Ravikumar Balakrishnan, Sanket Mendapara, Ankit Garg

Cisco Systems

Adversarial Attacks on VLMs VLM Robustness Adversarial Text Attacks Vision-Language Alignment

Apr 11, 2026

Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer from slow convergence due to gradient conflict between adversarial objectives and the model's safety-retrieval mechanism. We propose Attention-Guided Visual Jailbreaking, which circumvents rather than overpowers safety alignment by directly manipulating attention patterns. Our method introduces two simple auxiliary objectives: (1) suppressing attention to alignment-relevant prefix tokens and (2) anchoring generation on adversarial image features. This simple yet effective push-pull formulation reduces gradient conflict by 45% and achieves 94.4% attack success rate on Qwen-VL (vs. 68.8% baseline) with 40% fewer iterations. At tighter perturbation budgets (

ε=8/255

), we maintain 59.0% ASR compared to 45.7% for standard methods. Mechanistic analysis reveals a failure mode we term safety blindness: successful attacks suppress system-prompt attention by 80%, causing models to generate harmful content not by overriding safety rules, but by failing to retrieve them.

Jingru Li, Wei Ren, Tianqing Zhu

China University of Geosciences, Wuhan · City University of Macau

Jailbreak Attacks Adversarial Attacks on VLMs VLM Safety Large Vision-Language Models Attention-Based Adversarial Attacks VLM Safety Alignment+1

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.

Yuqin Lan, Gen Li, Yuanze Hu +6

Beihang University Beijing, China · Huazhong University of Science and Technology Wuhan, China

Adversarial Attacks on VLMs Transfer-Based Adversarial Attacks

Apr 10, 2026

Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection

Multi-modal large language models (MLLMs) have emerged as powerful tools for analyzing Internet-scale image data, offering significant benefits but also raising critical safety and societal concerns. In particular, open-weight MLLMs may be misused to extract sensitive information from personal images at scale, such as identities, locations, or other private details. In this work, we propose ImageProtector, a user-side method that proactively protects images before sharing by embedding a carefully crafted, nearly imperceptible perturbation that acts as a visual prompt injection attack on MLLMs. As a result, when an adversary analyzes a protected image with an MLLM, the MLLM is consistently induced to generate a refusal response such as "I'm sorry, I can't help with that request." We empirically demonstrate the effectiveness of ImageProtector across six MLLMs and four datasets. Additionally, we evaluate three potential countermeasures, Gaussian noise, DiffPure, and adversarial training, and show that while they partially mitigate the impact of ImageProtector, they simultaneously degrade model accuracy and/or efficiency. Our study focuses on the practically important setting of open-weight MLLMs and large-scale automated image analysis, and highlights both the promise and the limitations of perturbation-based privacy protection.

Zedian Shao, Hongbin Liu, Yuepeng Hu +1

Georgia Institute of Technology · Duke University

Privacy Protection in VLMs Adversarial Attacks on VLMs VLM Robustness Prompt Injection Attacks

Apr 9, 2026

Preference Redirection via Attention Concentration: An Attack on Computer Use Agents

Advancements in multimodal foundation models have enabled the development of Computer Use Agents (CUAs) capable of autonomously interacting with GUI environments. As CUAs are not restricted to certain tools, they allow to automate more complex agentic tasks but at the same time open up new security vulnerabilities. While prior work has concentrated on the language modality, the vulnerability of the vision modality has received less attention. In this paper, we introduce PRAC, a novel attack that, unlike prior work targeting the VLM output directly, manipulates the model's internal preferences by redirecting its attention toward a stealthy adversarial patch. We show that PRAC is able to manipulate the selection process of a CUA on an online shopping platform towards a chosen target product. While we require white-box access to the model for the creation of the attack, we show that our attack generalizes to fine-tuned versions of the same model, presenting a critical threat as multiple companies build specific CUAs based on open weights models.

Dominik Seip, Matthias Hein

Tübingen AI Center, University of Tübingen

Adversarial Attacks Adversarial Attacks on VLMs Multimodal Agents Adversarial Patch Attacks

Apr 8, 2026

Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation

Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a critical threat: Adversarial Smuggling Attacks. Unlike adversarial perturbations (for misclassification) and adversarial jailbreaks (for harmful output generation), adversarial smuggling exploits the Human-AI capability gap. It encodes harmful content into human-readable visual formats that remain AI-unreadable, thereby evading automated detection and enabling the dissemination of harmful content. We classify smuggling attacks into two pathways: (1) Perceptual Blindness, disrupting text recognition; and (2) Reasoning Blockade, inhibiting semantic understanding despite successful text recognition. To evaluate this threat, we constructed SmuggleBench, the first comprehensive benchmark comprising 1,700 adversarial smuggling attack instances. Evaluations on SmuggleBench reveal that both proprietary (e.g., GPT-5) and open-source (e.g., Qwen3-VL) state-of-the-art models are vulnerable to this threat, producing Attack Success Rates (ASR) exceeding 90%. By analyzing the vulnerability through the lenses of perception and reasoning, we identify three root causes: the limited capabilities of vision encoders, the robustness gap in OCR, and the scarcity of domain-specific adversarial examples. We conduct a preliminary exploration of mitigation strategies, investigating the potential of test-time scaling (via CoT) and adversarial training (via SFT) to mitigate this threat. Our code is publicly available at https://github.com/zhihengli-casia/smugglebench.

Zhiheng Li, Zongyang Ma, Yuntong Pan +8

State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA · School of Artificial Intelligence, University of Chinese Academy of Sciences · Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information +4

Multimodal Content Moderation Adversarial Attacks on VLMs Content Moderation

Apr 7, 2026

VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts

Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration. Existing defenses suffer from efficiency and robustness. To address these challenges, we first propose the Multimodal Aggregated Feature Extraction (MAFE) framework that enables CLIP to handle long text and fuse multimodal information into unified representations. Through empirical analysis of MAFE-extracted features, we discover distinct distributional patterns between benign and malicious prompts. Building upon this finding, we develop VLMShield, a lightweight safety detector that efficiently identifies multimodal malicious attacks as a plug-and-play solution. Extensive experiments demonstrate superior performance across multiple dimensions, including robustness, efficiency, and utility. Through our work, we hope to pave the way for more secure multimodal AI deployment. Code is available at this https URL.

Peigui Qi, Kunsheng Tang, Yanpu Yu +7

University of Science and Technology of China · Ant Group · University of Washington

VLM Safety VLM Robustness Adversarial Attacks on VLMs

Apr 7, 2026

Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models

Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and formalize the inscriptive jailbreak, where an adversary coerces a T2I system into generating images containing harmful textual payloads (e.g., fraudulent documents) embedded within visually benign scenes. Unlike traditional depictive jailbreaks that elicit visually objectionable imagery, inscriptive attacks weaponize the text-rendering capability itself. Because existing jailbreak techniques are designed for coarse visual manipulation, they struggle to bypass multi-stage safety filters while maintaining character-level fidelity. To expose this vulnerability, we propose Etch, a black-box attack framework that decomposes the adversarial prompt into three functionally orthogonal layers: semantic camouflage, visual-spatial anchoring, and typographic encoding. This decomposition reduces joint optimization over the full prompt space to tractable sub-problems, which are iteratively refined through a zero-order loop. In this process, a vision-language model critiques each generated image, localizes failures to specific layers, and prescribes targeted revisions. Extensive evaluations across 7 models on the 2 benchmarks demonstrate that Etch achieves an average attack success rate of 65.57% (peaking at 91.00%), significantly outperforming existing baselines. Our results reveal a critical blind spot in current T2I safety alignments and underscore the urgent need for typography-aware defense multimodal mechanisms.

Zonghao Ying, Haowen Dai, Lianyu Hu +5

Beihang University Beijing, China · University of Nottingham Ningbo China Ningbo, China · Nanyang Technological University Singapore +2

Black-Box Adversarial Attacks Safe T2I Generation Prompt Optimization for T2I Generation Adversarial Attacks on VLMs

Apr 7, 2026

Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization

Vision-Language Models (VLMs) have become essential for tasks such as image synthesis, captioning, and retrieval by aligning textual and visual information in a shared embedding space. Yet, this flexibility also makes them vulnerable to malicious prompts designed to produce unsafe content, raising critical safety concerns. Existing defenses either rely on blacklist filters, which are easily circumvented, or on heavy classifier-based systems, both of which are costly and fragile under embedding-level attacks. We address these challenges with two complementary components: Hyperbolic Prompt Espial (HyPE) and Hyperbolic Prompt Sanitization (HyPS). HyPE is a lightweight anomaly detector that leverages the structured geometry of hyperbolic space to model benign prompts and detect harmful ones as outliers. HyPS builds on this detection by applying explainable attribution methods to identify and selectively modify harmful words, neutralizing unsafe intent while preserving the original semantics of user prompts. Through extensive experiments across multiple datasets and adversarial scenarios, we prove that our framework consistently outperforms prior defenses in both detection accuracy and robustness. Together, HyPE and HyPS offer an efficient, interpretable, and resilient approach to safeguarding VLMs against malicious prompt misuse.

Igor Maljkovic, Maria Rosaria Briglia, Iacopo Masi +2

University of Genoa, Italy · Sapienza University of Rome, Italy · University of Cagliari, Italy

VLM Robustness Adversarial Attacks on VLMs Anomaly Detection

Apr 7, 2026

Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models

This paper presents Text-Guided Backdoor (TGB), an adjustable backdoor attack against multimodal pretrained models that uses natural-word triggers, namely words that can naturally occur in ordinary textual inputs. Most existing backdoor attacks require specific trigger conditions that are typically not satisfied by ordinary inference inputs, thereby limiting their activation in real-world deployments. TGB overcomes this limitation by exploiting naturally occurring words as triggers, enabling stealthy activation without requiring explicit trigger insertion at inference time. This property avoids conspicuous trigger patterns and improves the practicality of TGB. Furthermore, we introduce visual adversarial perturbations on poisoned samples to modulate the model's learning of natural-word triggers, thereby enabling flexible adjustment of TGB attack strength without modifying the poisoned data. Extensive experiments are conducted on downstream tasks built upon multimodal pretrained models, including Composed Image Retrieval (CIR) and Visual Question Answering (VQA). Results demonstrate the effectiveness of TGB across diverse poisoning settings and its ability to flexibly adjust attack success rates, which reveal critical security vulnerabilities in multimodal pretrained models.

Yiyang Zhang, Chaojian Yu, Ziming Hong +4

National Anti-Counterfeit Engineering Research Center, Huazhong University of Science and Technology · School of Electronic Information and Communications, Huazhong University of Science and Technology · Sydney AI Centre, The University of Sydney

Adversarial Attacks on VLMs Backdoor Attacks on VLMs

Apr 7, 2026

Benchmarking Vision-Language Models under Contradictory Virtual Content Attacks in Augmented Reality

Augmented reality (AR) has rapidly expanded over the past decade. As AR becomes increasingly integrated into daily life, its security and reliability emerge as critical challenges. Among various threats, contradictory virtual content attacks, where malicious or inconsistent virtual elements are introduced into the user's view, pose a unique risk by misleading users, creating semantic confusion, or delivering harmful information. In this work, we systematically model such attacks and present ContrAR, a novel benchmark for evaluating the robustness of vision-language models (VLMs) against virtual content manipulation and contradiction in AR. ContrAR contains 312 real-world AR videos validated by 10 human participants. We further benchmark 11 VLMs, including both commercial and open-source models. Experimental results reveal that while current VLMs exhibit reasonable understanding of contradictory virtual content, room still remains for improvement in detecting and reasoning about adversarial content manipulations in AR environments. Moreover, balancing detection accuracy and latency remains challenging.

Yanming Xiu, Zhengyuan Jiang, Neil Zhenqiang Gong +1

Duke University

Augmented Reality VLM Robustness VLM Evaluation Adversarial Attacks on VLMs Adversarial Attacks

Apr 3, 2026

Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patch for Infrared Vision-Language Models

Infrared vision-language models (IR-VLMs) are becoming important for semantic perception in low-visibility environments, yet their robustness to physical semantic attacks remains underexplored. Existing adversarial patch methods are mainly designed for red-green-blue (RGB) images or closed-set infrared detectors and do not directly address open-ended IR-VLM tasks, where one deployable artifact can affect classification, captioning, and visual question answering (VQA) simultaneously. We propose Universal Curved-Grid Patch, abbreviated UCGP, a universal physical adversarial patch framework tailored to IR-VLMs. UCGP represents the patch as a deployable low-frequency curved grid and optimizes it with a representation-driven objective over subspace departure, topology disruption, and local appearance regularization. Meta Differential Evolution (MetaDE) searches for patch parameters with two physical robustness augmentations: Expectation over Transformation (EOT) capture sampling for imaging variations and thin-plate spline (TPS) patch-deformation modeling for non-rigid local shape changes. Rather than manipulating labels or prompts, UCGP disrupts the clean-category manifold in visual representation space, which later appears as degraded cross-modal outputs. Experiments show that a single shared patch degrades classification, captioning, and VQA across diverse IR-VLM architectures while retaining measurable cross-model transfer, cross-dataset generalization, cross-category extensibility, and real-scene physical effectiveness under the evaluated conditions. These results reveal a robustness blind spot in current infrared multimodal systems. Code and reproducibility assets are available at https://github.com/dyx6663/UCGP.

Chengyin Hu, Yuxian Dong, Yikun Guo +8

China University of Petroleum-Beijing at Karamay, No. 355 Anding Road, Karamay 834000, Xinjiang, China. · the Defense Innovation Institute, Chinese Academy of Military Science, Beijing, China. · Shenzhen University, Shenzhen, China. +1

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

Apr 2, 2026

Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters

Text-to-image generative models are widely deployed in creative tools and online platforms. To mitigate misuse, these systems rely on safety filters and moderation pipelines that aim to block harmful or policy violating content. In this work we show that modern text-to-image models remain vulnerable to low-effort jailbreak attacks that require only natural language prompts. We present a systematic study of prompt-based strategies that bypass safety filters without model access, optimization, or adversarial training. We introduce a taxonomy of visual jailbreak techniques including artistic reframing, material substitution, pseudo-educational framing, lifestyle aesthetic camouflage, and ambiguous action substitution. These strategies exploit weaknesses in prompt moderation and visual safety filtering by masking unsafe intent within benign semantic contexts. We evaluate these attacks across several state-of-the-art text-to-image systems and demonstrate that simple linguistic modifications can reliably evade existing safeguards and produce restricted imagery. Our findings highlight a critical gap between surface-level prompt filtering and the semantic understanding required to detect adversarial intent in generative media systems. Across all tested models and attack categories we observe an attack success rate (ASR) of up to 74.47%.

Ahmed B Mustafa, Zihan Ye, Yang Lu +2

School of Computer Science, University of Nottingham, Wollaton Road, NG8 1BB · Department of Intelligent Science, Xi’an Jiaotong-Liverpool University, China, 215123 · School of Informatics, Xiamen University, Xiamen, 361005, China

Adversarial Attacks on VLMs Safe T2I Generation Adversarial Prompt Generation Black-Box Adversarial Attacks T2I Diffusion Models

Apr 1, 2026

PDA: Text-Augmented Defense Framework for Robust Vision-Language Models against Adversarial Image Attacks

Vision-language models (VLMs) are vulnerable to adversarial image perturbations. Existing works based on adversarial training against task-specific adversarial examples are computationally expensive and often fail to generalize to unseen attack types. To address these limitations, we introduce Paraphrase-Decomposition-Aggregation (PDA), a training-free defense framework that leverages text augmentation to enhance VLM robustness under diverse adversarial image attacks. PDA performs prompt paraphrasing, question decomposition, and consistency aggregation entirely at test time, thus requiring no modification on the underlying models. To balance robustness and efficiency, we instantiate PDA as invariants that reduce the inference cost while retaining most of its robustness gains. Experiments on multiple VLM architectures and benchmarks for visual question answering, classification, and captioning show that PDA achieves consistent robustness gains against various adversarial perturbations while maintaining competitive clean accuracy, establishing a generic, strong and practical defense framework for VLMs during inference.

Jingning Xu, Haochen Luo, Chen Liu

Department of Computer Science City University of Hong Kong

VLM Robustness Vision-Language Models Adversarial Attacks on VLMs

Mar 31, 2026

CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment

Multimodal large-language models (MLLMs) often experience degraded safety alignment when harmful queries exploit cross-modal interactions. Models aligned on text alone show a higher rate of successful attacks when extended to two or more modalities. We propose a simple conditional decoding strategy, CASA (Classification Augmented with Safety Attention) that uses internal representations of MLLMs to predict a binary safety token before response generation. The classification is guided by a safety attention mechanism that computes attention between a dedicated query prompt and the input to scale the classification logits, sharpening the model's ability to detect malicious queries. Our design ensures robust safety alignment without relying on any external classifier or auxiliary head, and without modality-specific safety fine-tuning. Unlike prior safety-decoding methods that attach an external classifier or moderation head, or rescale every generated token with a reward model, CASA makes a single, internal, attention-gated safety decision over the shared multimodal representation, which is precisely what lets safety learned from text-only training transfer to image and audio inputs. Compared against 4 baseline models across 7 attack types spanning text, image, and audio modalities, evaluated on benchmarks such as MM-SafetyBench, JailbreakV-28k, and adversarial audio tests, CASA lowers the average attack success rate by >90% relative when paired with a standard safety prompt (applied to all baselines for fair comparison), and by 54--61% using its internal safety mechanism alone. Our empirical evaluations also show that CASA~maintains strong utility on benign inputs, validated through both automated and human evaluations (via 13 trained annotators). Together, these results highlight CASA as a simple and generalizable framework to improve multimodal LLM safety.

Anurag Kumar, Raghuveer Peri, Jon Burnsky +4

The Ohio State University · AWS

MLLM Safety LLM Safety Alignment Multimodal Large Language Models Language Model Decoding Adversarial Attacks on VLMs Multimodal Robustness+1

Mar 31, 2026

Covert Visual Prompt Injection against Commercial Multimodal Large Language Models

Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks. Existing prompt injection methods predominantly rely on textual prompts or perceptible visual prompts that are observable by human users. In this work, we study imperceptible visual prompt injection against powerful closed-source MLLMs, where adversarial instructions are embedded in the visual modality. Our method adaptively embeds the malicious prompt into the input image via a bounded text overlay to provide semantic guidance. Meanwhile, the imperceptible visual perturbation is iteratively optimized to align the feature representation of the attacked image with those of the malicious visual and textual targets at both coarse- and fine-grained levels. Specifically, the visual target is instantiated as a text-rendered image and progressively refined during optimization to more faithfully represent the desired semantics and improve transferability. Extensive experiments on two multimodal understanding tasks across multiple closed-source MLLMs demonstrate the superior performance of our approach compared to existing methods.

Meiwen Ding, Song Xia, Chenqi Kong +1

Rapid-Rich Object Search Lab, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore.

Adversarial Attacks on VLMs Prompt Injection Attacks Prompt Injection Attacks on LLMs Multimodal Large Language Models

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.

Chengyin Hu, Jiaju Han, Xuemeng Sun +6

China University of Petroleum-Beijing at Karamay · Shenzhen Research Institute of Big Data · Shanghai Jiao Tong University +2

Adversarial Attacks on VLMs VLM Robustness Transfer-Based Adversarial Attacks

Mar 29, 2026

When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language Models

Visual-Language Models (VLMs) have demonstrated exceptional cross-modal understanding across various tasks, including zero-shot classification, image captioning, and visual question answering. However, their robustness to physically plausible non-rigid deformations-such as wrinkles on flexible surfaces-remains poorly understood. In this work, we propose a parametric structural perturbation method inspired by the mechanics of three-dimensional fabric wrinkles. Specifically, our method generates photorealistic non-rigid perturbations by constructing multi-scale wrinkle fields and integrating displacement field distortion with surface-consistent appearance variations. To achieve an optimal balance between visual naturalness and adversarial effectiveness, we design a hierarchical fitness function in a low-dimensional parameter space and employ an optimization-based search strategy. We evaluate our approach using a two-stage framework: perturbations are first optimized on a zero-shot classification proxy task and subsequently assessed for transferability on generative tasks. Experimental results demonstrate that our method significantly degrades the performance of various state-of-the-art VLMs, consistently outperforming baselines in both image captioning and visual question-answering tasks.

Chengyin Hu, Xuemeng Sun, Jiaju Han +5

Adversarial Attacks on VLMs Adversarial Attacks VLM Robustness Physical Adversarial Attacks

Mar 29, 2026

Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models

Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this recommendation-seeking behavior to inject unauthorized advertisements. Unlike traditional pattern-triggered backdoors that rely on artificial triggers such as pixel patches or special tokens, Hidden Ads activates on natural user behaviors: when users upload images containing semantic content of interest (e.g., food, cars, animals) and ask recommendation-seeking questions, the backdoored model provides correct, helpful answers while seamlessly appending attacker-specified promotional slogans. This design preserves model utility and produces natural-sounding injections, making the attack practical for real-world deployment in consumer-facing recommendation services. We propose a multi-tier threat framework to systematically evaluate Hidden Ads across three adversary capability levels: hard prompt injection, soft prompt optimization, and supervised fine-tuning. Our poisoned data generation pipeline uses teacher VLM-generated chain-of-thought reasoning to create natural trigger--slogan associations across multiple semantic domains. Experiments on three VLM architectures demonstrate that Hidden Ads achieves high injection efficacy with near-zero false positives while maintaining task accuracy. Ablation studies confirm that the attack is data-efficient, transfers effectively to unseen datasets, and scales to multiple concurrent domain-slogan pairs. We evaluate defenses including instruction-based filtering and clean fine-tuning, finding that both fail to remove the backdoor without causing significant utility degradation.

Duanyi Yao, Changyue Li, Zhicong Huang +2

Hong Kong University of Science and Technology · The Chinese University of Hong Kong, Shenzhen, China · Ant Group +1

Adversarial Attacks on VLMs Backdoor Attacks Backdoor Attacks on VLMs

Mar 26, 2026

Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models

On-device Vision-Language Models (VLMs) promise data privacy via local execution. However, we show that the architectural shift toward Dynamic High-Resolution preprocessing (e.g., AnyRes) introduces an inherent algorithmic side-channel. Unlike static models, dynamic preprocessing decomposes images into a variable number of patches based on their aspect ratio, creating workload-dependent inputs. We demonstrate a dual-layer attack framework against local VLMs. In Tier 1, an unprivileged attacker can exploit significant execution-time variations using standard unprivileged OS metrics to reliably fingerprint the input's geometry. In Tier 2, by profiling Last-Level Cache (LLC) contention, the attacker can resolve semantic ambiguity within identical geometries, distinguishing between visually dense (e.g., medical X-rays) and sparse (e.g., text documents) content. By evaluating state-of-the-art models such as LLaVA-NeXT and Qwen2-VL, we show that combining these signals enables reliable inference of privacy-sensitive contexts. Finally, we analyze the security engineering trade-offs of mitigating this vulnerability, reveal substantial performance overhead with constant-work padding, and propose practical design recommendations for secure Edge AI deployments.

Eyal Hadad, Mordechai Guri

Ben-Gurion University of the Negev, Israel Faculty of Computer and Information Science

Privacy Protection in VLMs Adversarial Attacks on VLMs

Mar 24, 2026

TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration

The rapid advancement of Vision-Language Models (VLMs) has brought their safety vulnerabilities into sharp focus. However, existing red teaming methods are fundamentally constrained by an inherent linear exploration paradigm, confining them to optimizing within a predefined strategy set and preventing the discovery of novel, diverse exploits. To transcend this limitation, we introduce TreeTeaming, an automated red teaming framework that reframes strategy exploration from static testing to a dynamic, evolutionary discovery process. At its core lies a strategic Orchestrator, powered by a Large Language Model (LLM), which autonomously decides whether to evolve promising attack paths or explore diverse strategic branches, thereby dynamically constructing and expanding a strategy tree. A multimodal actuator is then tasked with executing these complex strategies. In the experiments across 12 prominent VLMs, TreeTeaming achieves state-of-the-art attack success rates on 11 models, outperforming existing methods and reaching up to 87.60% on GPT-4o. The framework also demonstrates superior strategic diversity over the union of previously public jailbreak strategies. Furthermore, the generated attacks exhibit an average toxicity reduction of 23.09%, showcasing their stealth and subtlety. Our work introduces a new paradigm for automated vulnerability discovery, underscoring the necessity of proactive exploration beyond static heuristics to secure frontier AI models.

Chunxiao Li, Lijun Li, Jing Shao

Shanghai Artificial Intelligence Laboratory

Cultural Safety Evaluation of VLMs Automated Red Teaming Adversarial Attacks on VLMs VLM Evaluation

Mar 23, 2026

Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models

As vision-language models (VLMs) are increasingly deployed in open-world scenarios, they can be easily induced by visual jailbreak attacks to generate harmful content, posing serious risks to model safety and trustworthy usage. Recent activation steering methods inject directional vectors into model activations during inference to induce refusal behaviors and have demonstrated effectiveness. However, a steering vector may both enhance refusal ability and cause over-refusal, thereby degrading model performance on benign inputs. Moreover, due to the lack of theoretical interpretability, these methods still suffer from limited robustness and effectiveness. To better balance safety and utility, we propose NullSteer, a null-space projected activation defense framework. Our method constructs refusal directions within model activations through a linear transformation: it maintains zero perturbation within the benign subspace while dynamically inducing refusal along potentially harmful directions, thereby theoretically achieving safety enhancement without impairing the model's general capabilities. Extensive experiments show that NullSteer significantly reduces harmful outputs under various jailbreak attacks (average ASR reduction over 15 percent on MiniGPT-4) while maintaining comparable performance to the original model on general benchmarks.

Xingyu Zhu, Beier Zhu, Shuo Wang +4

MoE Key Lab of BIPC, University of Science and Technology of China · National University of Singapore · Nanyang Technological University

VLM Robustness Activation Steering Adversarial Attacks on VLMs

Mar 23, 2026

Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models

Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually grounded instructions. We study comic-template jailbreaks that embed harmful goals inside simple three-panel visual narratives and prompt the model to role-play and "complete the comic." Building on JailbreakBench and JailbreakV, we introduce ComicJailbreak, a comic-based jailbreak benchmark with 1,167 attack instances spanning 10 harm categories and 5 task setups. Across 15 state-of-the-art MLLMs (six commercial and nine open-source), comic-based attacks achieve success rates comparable to strong rule-based jailbreaks and substantially outperform plain-text and random-image baselines, with ensemble success rates exceeding 90% on several commercial models. Then, with the existing defense methodologies, we show that these methods are effective against the harmful comics, they will induce a high refusal rate when prompted with benign prompts. Finally, using automatic judging and targeted human evaluation, we show that current safety evaluators can be unreliable on sensitive but non-harmful content. Our findings highlight the need for safety alignment robust to narrative-driven multimodal jailbreaks.

Rui Yang Tan, Yujia Hu, Roy Ka-Wei Lee

Singapore University of Technology and Design. · University of British Colombia.

MLLM Safety Adversarial Attacks on VLMs Adversarial Attacks on LLMs LLM Safety Alignment LLM Safety Benchmarks Language Model Safety Evaluation

Mar 22, 2026

JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization

Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed safety filters. Existing jailbreak attacks either rely on proxy-loss optimization instead of the true end-to-end objective, or depend on large-scale and costly RL-trained generators. Motivated by these limitations, we propose JANUS , a lightweight framework that formulates jailbreak as optimizing a structured prompt distribution under a black-box, end-to-end reward from the T2I system and its safety filters. JANUS replaces a high-capacity generator with a low-dimensional mixing policy over two semantically anchored prompt distributions, enabling efficient exploration while preserving the target semantics. On modern T2I models, we outperform state-of-the-art jailbreak methods, improving ASR-8 from 25.30% to 43.15% on Stable Diffusion 3.5 Large Turbo with consistently higher CLIP and NSFW scores. JANUS succeeds across both open-source and commercial models. These findings expose structural weaknesses in current T2I safety pipelines and motivate stronger, distribution-aware defenses. Warning: This paper contains model outputs that may be offensive.

Haolun Zheng, Yu He, Tailun Chen +6

The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Hangzhou HighTech Zone (Binjiang) Blockchain and Data Security Research Institute, China · Alibaba Group

Adversarial Attacks on VLMs Black-Box Adversarial Attacks Prompt Optimization T2I Diffusion Models

Mar 22, 2026

When Minor Edits Matter: LLM-Driven Prompt Attack for Medical VLM Robustness in Ultrasound

Ultrasound is widely used in clinical practice due to its portability, cost-effectiveness, safety, and real-time imaging capabilities. However, image acquisition and interpretation remain highly operator dependent, motivating the development of robust AI-assisted analysis methods. Vision-language models (VLMs) have recently demonstrated strong multimodal reasoning capabilities and competitive performance in medical image analysis, including ultrasound. However, emerging evidence highlights significant concerns about their trustworthiness. In particular, adversarial robustness is critical because Med-VLMs operate via natural-language instructions, rendering prompt formulation a realistic and practically exploitable point of vulnerability. Small variations (typos, shorthand, underspecified requests, or ambiguous wording) can meaningfully shift model outputs. We propose a scalable adversarial evaluation framework that leverages a large language model (LLM) to generate clinically plausible adversarial prompt variants via "humanized" rewrites and minimal edits that mimic routine clinical communication. Using ultrasound multiple-choice question answering benchmarks, we systematically assess the vulnerability of SOTA Med-VLMs to these attacks, examine how attacker LLM capacity influences attack success, analyze the relationship between attack success and model confidence, and identify consistent failure patterns across models. Our results highlight realistic robustness gaps that must be addressed for safe clinical translation. Code will be released publicly following the review process.

Yasamin Medghalchi, Milad Yazdani, Amirhossein Dabiriaghdam +7

University of British Columbia, Vancouver, Canada

VLM Robustness Adversarial Attacks on VLMs Medical VLMs