{"total":23,"rows":[{"id":"2307.14539","title":"Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models","created":"2023-07-26","cited_by_count":273,"area":"mllm"},{"id":"2401.02906","title":"MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance","created":"2024-01-05","cited_by_count":117,"area":"mllm"},{"id":"2403.08730","title":"Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization","created":"2024-03-13","cited_by_count":75,"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":"2504.14348","title":"Manipulating Multimodal Agents via Cross-Modal Prompt Injection","created":"2025-04-19","cited_by_count":44,"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":"2312.04913","title":"SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation","created":"2023-12-08","cited_by_count":39,"area":"mllm"},{"id":"2409.11365","title":"CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration","created":"2024-09-17","cited_by_count":31,"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":"2505.15389","title":"Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study","created":"2025-05-21","cited_by_count":12,"area":"mllm"},{"id":"2507.13868","title":"When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models","created":"2025-07-18","cited_by_count":11,"area":"mllm"},{"id":"2508.12687","title":"EGOILLUSION: Benchmarking Hallucinations in Egocentric Video Understanding","created":"2025-08-18","cited_by_count":10,"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":"2601.17383","title":"Physical Prompt Injection Attacks on Large Vision-Language Models","created":"2026-01-24","cited_by_count":4,"area":"mllm"},{"id":"2501.19017","title":"Benchmarking Gaslighting Negation Attacks Against Multimodal Large Language Models","created":"2025-01-31","cited_by_count":3,"area":"mllm"},{"id":"2507.11968","title":"Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation","created":"2025-07-16","cited_by_count":2,"area":"mllm"},{"id":"2508.05083","title":"MedMKEB: A Comprehensive Knowledge Editing Benchmark for Medical Multimodal Large Language Models","created":"2025-08-07","cited_by_count":2,"area":"mllm"},{"id":"2509.12521","title":"Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time","created":"2025-09-15","cited_by_count":2,"area":"mllm"},{"id":"2602.07104","title":"Extended to Reality: Prompt Injection in 3D Environments","created":"2026-02-06","cited_by_count":1,"area":"mllm"},{"id":"2604.17318","title":"When Background Matters: Breaking Medical Vision Language Models by Transferable Attack","created":"2026-04-19","cited_by_count":1,"area":"mllm"},{"id":"2602.18154","title":"FENCE: A Financial and Multimodal Jailbreak Detection Dataset","created":"2026-02-20","cited_by_count":0,"area":"mllm"},{"id":"2603.29418","title":"Covert Visual Prompt Injection against Commercial Multimodal Large Language Models","created":"2026-03-31","cited_by_count":0,"area":"mllm"},{"id":"2608.05495","title":"PromptShield Home: Ambient Multimodal Prompt Injection Defense for Smart-Home Agents","created":"2026-08-06","cited_by_count":0,"area":"mllm"}],"next_cursor":null}