{"total":172,"rows":[{"id":"2311.05608","title":"FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts","created":"2023-11-09","cited_by_count":398,"area":"mllm"},{"id":"2309.11751","title":"How Robust is Google's Bard to Adversarial Image Attacks?","created":"2023-09-21","cited_by_count":183,"area":"mllm"},{"id":"2402.08567","title":"Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast","created":"2024-02-13","cited_by_count":153,"area":"mllm"},{"id":"2403.09792","title":"Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models","created":"2024-03-14","cited_by_count":136,"area":"mllm"},{"id":"2411.10414","title":"Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations","created":"2024-11-15","cited_by_count":129,"area":"mllm"},{"id":"2402.12336","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","created":"2024-02-19","cited_by_count":120,"area":"mllm"},{"id":"2406.04031","title":"Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt","created":"2024-06-06","cited_by_count":109,"area":"mllm"},{"id":"2312.03777","title":"On the Robustness of Large Multimodal Models Against Image Adversarial Attacks","created":"2023-12-06","cited_by_count":92,"area":"mllm"},{"id":"2406.12030","title":"SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model","created":"2024-06-17","cited_by_count":85,"area":"mllm"},{"id":"2407.07403","title":"A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends","created":"2024-07-10","cited_by_count":84,"area":"mllm"},{"id":"2407.01599","title":"JailbreakZoo: Survey, Landscapes, and Horizons in Jailbreaking Large Language and Vision-Language Models","created":"2024-06-26","cited_by_count":70,"area":"mllm"},{"id":"2502.05206","title":"Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety","created":"2025-02-02","cited_by_count":67,"area":"mllm"},{"id":"2401.12915","title":"Red Teaming Visual Language Models","created":"2024-01-23","cited_by_count":65,"area":"mllm"},{"id":"2310.17419","title":"AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors","created":"2023-10-26","cited_by_count":64,"area":"mllm"},{"id":"2410.06625","title":"ETA: Evaluating Then Aligning Safety of Vision Language Models at Inference Time","created":"2024-10-09","cited_by_count":60,"area":"mllm"},{"id":"2405.17894","title":"White-box Multimodal Jailbreaks Against Large Vision-Language Models","created":"2024-05-28","cited_by_count":59,"area":"mllm"},{"id":"2403.02910","title":"ImgTrojan: Jailbreaking Vision-Language Models with ONE Image","created":"2024-03-05","cited_by_count":57,"area":"mllm"},{"id":"2406.07057","title":"MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models","created":"2024-06-11","cited_by_count":53,"area":"mllm"},{"id":"2501.04931","title":"Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency","created":"2025-01-09","cited_by_count":51,"area":"mllm"},{"id":"2402.06659","title":"Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models","created":"2024-02-05","cited_by_count":50,"area":"mllm"},{"id":"2406.18844","title":"Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift","created":"2024-06-27","cited_by_count":49,"area":"mllm"},{"id":"2411.16721","title":"Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreaks","created":"2024-11-23","cited_by_count":48,"area":"mllm"},{"id":"2310.02224","title":"Can Language Models be Instructed to Protect Personal Information?","created":"2023-10-03","cited_by_count":46,"area":"mllm"},{"id":"2403.09766","title":"An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models","created":"2024-03-14","cited_by_count":45,"area":"mllm"},{"id":"2504.14348","title":"Manipulating Multimodal Agents via Cross-Modal Prompt Injection","created":"2025-04-19","cited_by_count":44,"area":"mllm"},{"id":"2406.11171","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","created":"2024-06-17","cited_by_count":42,"area":"mllm"},{"id":"2407.15050","title":"Arondight: Red Teaming Large Vision Language Models with Auto-generated Multi-modal Jailbreak Prompts","created":"2024-07-21","cited_by_count":42,"area":"mllm"},{"id":"2402.08577","title":"Test-Time Backdoor Attacks on Multimodal Large Language Models","created":"2024-02-13","cited_by_count":40,"area":"mllm"},{"id":"2506.14697","title":"AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions","created":"2025-06-17","cited_by_count":38,"area":"mllm"},{"id":"2404.10618","title":"Private Attribute Inference from Images with Vision-Language Models","created":"2024-04-16","cited_by_count":37,"area":"mllm"},{"id":"2411.00827","title":"IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves","created":"2024-10-29","cited_by_count":37,"area":"mllm"},{"id":"2502.12520","title":"SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning","created":"2025-02-18","cited_by_count":32,"area":"mllm"},{"id":"2503.17682","title":"Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback","created":"2025-03-22","cited_by_count":30,"area":"mllm"},{"id":"2405.13581","title":"Safety Alignment for Vision Language Models","created":"2024-05-22","cited_by_count":28,"area":"mllm"},{"id":"2410.20971","title":"BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks","created":"2024-10-28","cited_by_count":28,"area":"mllm"},{"id":"2505.11842","title":"Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs","created":"2025-05-17","cited_by_count":28,"area":"mllm"},{"id":"2405.10529","title":"Safeguarding Vision-Language Models Against Patched Visual Prompt Injectors","created":"2024-05-17","cited_by_count":27,"area":"mllm"},{"id":"2403.09346","title":"B-AVIBench: Towards Evaluating the Robustness of Large Vision-Language Model on Black-box Adversarial Visual-Instructions","created":"2024-03-14","cited_by_count":26,"area":"mllm"},{"id":"2406.02575","title":"Cross-Modal Safety Alignment: Is textual unlearning all you need?","created":"2024-05-27","cited_by_count":25,"area":"mllm"},{"id":"2410.23687","title":"Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey","created":"2024-10-31","cited_by_count":23,"area":"mllm"},{"id":"2601.01592","title":"OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs","created":"2026-01-04","cited_by_count":21,"area":"mllm"},{"id":"2410.08174","title":"Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models","created":"2024-10-10","cited_by_count":19,"area":"mllm"},{"id":"2411.01703","title":"UniGuard: Towards Universal Safety Guardrails for Jailbreak Attacks on Multimodal Large Language Models","created":"2024-11-03","cited_by_count":19,"area":"mllm"},{"id":"2411.02708","title":"Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenarios","created":"2024-11-05","cited_by_count":19,"area":"mllm"},{"id":"2405.08317","title":"SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models","created":"2024-05-14","cited_by_count":18,"area":"mllm"},{"id":"2412.05892","title":"PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization","created":"2024-12-08","cited_by_count":17,"area":"mllm"},{"id":"2503.11832","title":"Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning","created":"2025-03-14","cited_by_count":16,"area":"mllm"},{"id":"2402.10340","title":"On the Vulnerability of LLM/VLM-Controlled Robotics","created":"2024-02-15","cited_by_count":15,"area":"mllm"},{"id":"2409.07353","title":"Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks","created":"2024-09-11","cited_by_count":15,"area":"mllm"},{"id":"2309.07120","title":"Sight Beyond Text: Multi-Modal Training Enhances LLMs in Truthfulness and Ethics","created":"2023-09-13","cited_by_count":14,"area":"mllm"},{"id":"2405.17423","title":"Privacy-Aware Visual Language Models","created":"2024-05-27","cited_by_count":12,"area":"mllm"},{"id":"2411.18000","title":"Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models","created":"2024-11-27","cited_by_count":12,"area":"mllm"},{"id":"2503.04833","title":"E$^2$AT: Multimodal Jailbreak Defense via Dynamic Joint Optimization for Multimodal Large Language Models","created":"2025-03-05","cited_by_count":12,"area":"mllm"},{"id":"2505.19911","title":"Attention! Your Vision Language Model Could Be Maliciously Manipulated","created":"2025-05-26","cited_by_count":12,"area":"mllm"},{"id":"2506.12430","title":"Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025","created":"2025-06-14","cited_by_count":12,"area":"mllm"},{"id":"2402.03757","title":"The Instinctive Bias: Spurious Images lead to Illusion in MLLMs","created":"2024-02-06","cited_by_count":11,"area":"mllm"},{"id":"2407.07392","title":"Malicious Path Manipulations via Exploitation of Representation Vulnerabilities of Vision-Language Navigation Systems","created":"2024-07-10","cited_by_count":11,"area":"mllm"},{"id":"2502.12562","title":"SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings","created":"2025-02-18","cited_by_count":11,"area":"mllm"},{"id":"2508.05087","title":"JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual Steering","created":"2025-08-07","cited_by_count":11,"area":"mllm"},{"id":"2509.21029","title":"FORCE: Transferable Visual Jailbreaking Attacks via Feature Over-Reliance CorrEction","created":"2025-09-25","cited_by_count":11,"area":"mllm"},{"id":"2405.20775","title":"Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models","created":"2024-05-26","cited_by_count":10,"area":"mllm"},{"id":"2501.09446","title":"Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness","created":"2025-01-16","cited_by_count":10,"area":"mllm"},{"id":"2505.19610","title":"JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models","created":"2025-05-26","cited_by_count":10,"area":"mllm"},{"id":"2602.12158","title":"SafeNeuron: Neuron-Level Safety Alignment for Large Language Models","created":"2026-02-12","cited_by_count":10,"area":"mllm"},{"id":"2504.10000","title":"Do We Really Need Curated Malicious Data for Safety Alignment in Multi-modal Large Language Models?","created":"2025-04-14","cited_by_count":9,"area":"mllm"},{"id":"2505.11926","title":"SafeVid: Toward Safety Aligned Video Large Multimodal Models","created":"2025-05-17","cited_by_count":9,"area":"mllm"},{"id":"2506.01307","title":"Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models","created":"2025-06-02","cited_by_count":9,"area":"mllm"},{"id":"2506.04704","title":"HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model","created":"2025-06-05","cited_by_count":9,"area":"mllm"},{"id":"2410.07571","title":"How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?","created":"2024-10-10","cited_by_count":8,"area":"mllm"},{"id":"2410.22888","title":"Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector","created":"2024-10-30","cited_by_count":8,"area":"mllm"},{"id":"2504.01444","title":"PiCo: Jailbreaking Multimodal Large Language Models via Pictorial Code Contextualization","created":"2025-04-02","cited_by_count":8,"area":"mllm"},{"id":"2512.20168","title":"Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual Steganography","created":"2025-12-23","cited_by_count":8,"area":"mllm"},{"id":"2403.10492","title":"Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning","created":"2024-03-15","cited_by_count":7,"area":"mllm"},{"id":"2411.07559","title":"Zer0-Jack: A Memory-efficient Gradient-based Jailbreaking Method for Black-box Multi-modal Large Language Models","created":"2024-11-12","cited_by_count":7,"area":"mllm"},{"id":"2506.00548","title":"Con Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities","created":"2025-05-31","cited_by_count":7,"area":"mllm"},{"id":"2509.19212","title":"Steering Multimodal Large Language Models Decoding for Context-Aware Safety","created":"2025-09-23","cited_by_count":7,"area":"mllm"},{"id":"2502.07987","title":"Universal Adversarial Attack on Aligned Multimodal LLMs","created":"2025-02-11","cited_by_count":6,"area":"mllm"},{"id":"2503.00037","title":"Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs","created":"2025-02-25","cited_by_count":6,"area":"mllm"},{"id":"2505.17455","title":"Towards Evaluating Proactive Risk Awareness of Multimodal Language Models","created":"2025-05-23","cited_by_count":6,"area":"mllm"},{"id":"2506.16760","title":"Cross-Modal Obfuscation for Jailbreak Attacks on Large Vision-Language Models","created":"2025-06-20","cited_by_count":6,"area":"mllm"},{"id":"2405.20090","title":"Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models","created":"2024-05-30","cited_by_count":5,"area":"mllm"},{"id":"2505.17654","title":"EVADE-Bench: Multimodal Benchmark for Evaluating and Enhancing Evasive Content Detection","created":"2025-05-23","cited_by_count":5,"area":"mllm"},{"id":"2505.21967","title":"Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack","created":"2025-05-28","cited_by_count":5,"area":"mllm"},{"id":"2509.00373","title":"Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Models","created":"2025-08-30","cited_by_count":5,"area":"mllm"},{"id":"2406.13294","title":"Enhancing Cross-Prompt Transferability in Vision-Language Models through Contextual Injection of Target Tokens","created":"2024-06-19","cited_by_count":4,"area":"mllm"},{"id":"2410.01438","title":"The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models?","created":"2024-10-02","cited_by_count":4,"area":"mllm"},{"id":"2411.04291","title":"Layer-wise Alignment: Examining Safety Alignment Across Image Encoder Layers in Vision Language Models","created":"2024-11-06","cited_by_count":4,"area":"mllm"},{"id":"2411.05056","title":"Seeing is Deceiving: Exploitation of Visual Pathways in Multi-Modal Language Models","created":"2024-11-07","cited_by_count":4,"area":"mllm"},{"id":"2504.03714","title":"Breach in the Shield: Unveiling the Vulnerabilities of Large Language Models","created":"2025-03-28","cited_by_count":4,"area":"mllm"},{"id":"2504.03735","title":"Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots","created":"2025-04-01","cited_by_count":4,"area":"mllm"},{"id":"2506.17265","title":"SUA: Stealthy Multimodal Large Language Model Unlearning Attack","created":"2025-06-10","cited_by_count":4,"area":"mllm"},{"id":"2508.01741","title":"Simulated Ensemble Attack: Transferring Jailbreaks Across Fine-tuned Vision-Language Models","created":"2025-08-03","cited_by_count":4,"area":"mllm"},{"id":"2508.09218","title":"Towards Effective MLLM Jailbreaking Through Balanced On-Topicness and OOD-Intensity","created":"2025-08-11","cited_by_count":4,"area":"mllm"},{"id":"2508.15370","title":"Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation","created":"2025-08-21","cited_by_count":4,"area":"mllm"},{"id":"2510.04257","title":"AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents","created":"2025-10-05","cited_by_count":4,"area":"mllm"},{"id":"2601.06460","title":"Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMs","created":"2026-01-10","cited_by_count":4,"area":"mllm"},{"id":"2601.17383","title":"Physical Prompt Injection Attacks on Large Vision-Language Models","created":"2026-01-24","cited_by_count":4,"area":"mllm"},{"id":"2602.01025","title":"Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models","created":"2026-02-01","cited_by_count":4,"area":"mllm"},{"id":"2603.13385","title":"VisualLeakBench: Auditing the Fragility of Large Vision-Language Models against PII Leakage and Social Engineering","created":"2026-03-11","cited_by_count":4,"area":"mllm"},{"id":"2605.00583","title":"Jailbreaking Vision-Language Models Through the Visual Modality","created":"2026-05-01","cited_by_count":4,"area":"mllm"}],"next_cursor":"100"}