{"total":21,"rows":[{"id":"2502.14881","title":"A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations","created":"2025-02-14","cited_by_count":67,"area":"mllm"},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2502.13095","title":"Understanding and Rectifying Safety Perception Distortion in VLMs","created":"2025-02-18","cited_by_count":17,"area":"mllm"},{"id":"2508.12815","title":"Learning to Steer: Input-dependent Steering for Multimodal LLMs","created":"2025-08-18","cited_by_count":15,"area":"mllm"},{"id":"2510.04217","title":"MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering","created":"2025-10-05","cited_by_count":10,"area":"mllm"},{"id":"2506.09353","title":"DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt","created":"2025-06-11","cited_by_count":8,"area":"mllm"},{"id":"2512.05745","title":"ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior","created":"2025-12-05","cited_by_count":7,"area":"mllm"},{"id":"2505.24519","title":"AMIA: Automatic Masking and Joint Intention Analysis Makes LVLMs Robust Jailbreak Defenders","created":"2025-05-30","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":"2512.15926","title":"DSO: Direct Steering Optimization for Bias Mitigation","created":"2025-12-17","cited_by_count":3,"area":"mllm"},{"id":"2603.22094","title":"Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models","created":"2026-03-23","cited_by_count":2,"area":"mllm"},{"id":"2607.09697","title":"Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs","created":"2026-06-20","cited_by_count":2,"area":"mllm"},{"id":"2607.22716","title":"Visual Token Compression Enhances Robustness of MLLMs","created":"2026-07-21","cited_by_count":2,"area":"mllm"},{"id":"2509.25533","title":"VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models","created":"2025-09-29","cited_by_count":1,"area":"mllm"},{"id":"2601.23041","title":"One-shot Optimized Steering Vector for Hallucination Mitigation for VLMs","created":"2026-01-30","cited_by_count":1,"area":"mllm"},{"id":"2603.14825","title":"Two Birds, One Projection: Harmonizing Safety and Utility in LVLMs via Inference-time Feature Projection","created":"2026-03-16","cited_by_count":1,"area":"mllm"},{"id":"2508.08521","title":"VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models","created":"2025-08-11","cited_by_count":0,"area":"mllm"},{"id":"2603.14219","title":"Safety-Potential Pruning for Enhancing Safety Prompts Against VLM Jailbreaking Without Retraining","created":"2026-03-15","cited_by_count":0,"area":"mllm"},{"id":"2604.06502","title":"VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts","created":"2026-04-07","cited_by_count":0,"area":"mllm"},{"id":"2608.07535","title":"Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards","created":"2026-07-27","cited_by_count":0,"area":"mllm"},{"id":"2608.09928","title":"Multimodal Model Diffing for Feature Discovery and Control","created":"2026-08-10","cited_by_count":0,"area":"mllm"}],"next_cursor":null}