{"total":167,"rows":[{"id":"2404.14219","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","created":"2024-04-22","cited_by_count":1917,"area":null},{"id":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521,"area":"mllm"},{"id":"2408.17003","title":"Safety Layers in Aligned Large Language Models: The Key to LLM Security","created":"2024-08-30","cited_by_count":134,"area":"alignment"},{"id":"2410.12761","title":"SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation","created":"2024-10-16","cited_by_count":133,"area":"diffusion"},{"id":"2403.09513","title":"AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting","created":"2024-03-14","cited_by_count":125,"area":"mllm"},{"id":"2403.09572","title":"Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation","created":"2024-03-14","cited_by_count":124,"area":"lr"},{"id":"2402.18540","title":"Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates","created":"2024-02-28","cited_by_count":96,"area":null},{"id":"2405.14577","title":"Representation Noising: A Defence Mechanism Against Harmful Finetuning","created":"2024-05-23","cited_by_count":96,"area":"safety"},{"id":"2405.18641","title":"Lisa: Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning Attack","created":"2024-05-28","cited_by_count":92,"area":"alignment"},{"id":"2409.01586","title":"Booster: Tackling Harmful Fine-tuning for Large Language Models via Attenuating Harmful Perturbation","created":"2024-09-03","cited_by_count":92,"area":null},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90,"area":"alignment"},{"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":"2502.10391","title":"MM-RLHF: The Next Step Forward in Multimodal LLM Alignment","created":"2025-02-14","cited_by_count":83,"area":"mllm"},{"id":"2408.09600","title":"Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning","created":"2024-08-18","cited_by_count":72,"area":"alignment"},{"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":"2405.20773","title":"Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Character","created":"2024-05-25","cited_by_count":68,"area":"safety"},{"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":"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":"2501.04931","title":"Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency","created":"2025-01-09","cited_by_count":51,"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":"2411.18688","title":"Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment","created":"2024-11-27","cited_by_count":44,"area":"lr"},{"id":"2505.11049","title":"GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning","created":"2025-05-16","cited_by_count":42,"area":"lr"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2403.17830","title":"Assessment of Multimodal Large Language Models in Alignment with Human Values","created":"2024-03-26","cited_by_count":36,"area":"mllm"},{"id":"2412.15206","title":"AutoTrust: Benchmarking Trustworthiness in Large Vision Language Models for Autonomous Driving","created":"2024-12-19","cited_by_count":35,"area":"lr"},{"id":"2505.16916","title":"Backdoor Cleaning without External Guidance in MLLM Fine-tuning","created":"2025-05-22","cited_by_count":35,"area":"mllm"},{"id":"2410.15236","title":"Jailbreaking and Mitigation of Vulnerabilities in Large Language Models","created":"2024-10-20","cited_by_count":34,"area":"safety"},{"id":"2411.09259","title":"Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey","created":"2024-11-14","cited_by_count":32,"area":"safety"},{"id":"2404.10501","title":"Self-Supervised Visual Preference Alignment","created":"2024-04-16","cited_by_count":31,"area":"mllm"},{"id":"2406.09321","title":"JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models","created":"2024-06-13","cited_by_count":31,"area":"safety"},{"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":"2506.13666","title":"We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systems","created":"2025-06-16","cited_by_count":27,"area":"agents"},{"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":"2503.17239","title":"SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model Merging","created":"2025-03-21","cited_by_count":25,"area":"alignment"},{"id":"2410.09047","title":"Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Models","created":"2024-10-11","cited_by_count":23,"area":"mllm"},{"id":"2411.08410","title":"The VLLM Safety Paradox: Dual Ease in Jailbreak Attack and Defense","created":"2024-11-13","cited_by_count":21,"area":"safety"},{"id":"2501.18533","title":"Rethinking Bottlenecks in Safety Fine-Tuning of Vision Language Models","created":"2025-01-30","cited_by_count":21,"area":"lr"},{"id":"2501.18100","title":"Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation","created":"2025-01-30","cited_by_count":20,"area":null},{"id":"2502.09927","title":"Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence","created":"2025-02-14","cited_by_count":20,"area":null},{"id":"2410.11459","title":"Jigsaw Puzzles: Splitting Harmful Questions to Jailbreak Large Language Models","created":"2024-10-15","cited_by_count":19,"area":"lr"},{"id":"2410.12662","title":"Cross-Modal Safety Mechanism Transfer in Large Vision-Language Models","created":"2024-10-16","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":"2412.18826","title":"RapGuard: Safeguarding Multimodal Large Language Models via Rationale-aware Defensive Prompting","created":"2024-12-25","cited_by_count":19,"area":"mllm"},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2505.06538","title":"Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model","created":"2025-05-10","cited_by_count":19,"area":"lr"},{"id":"2410.00296","title":"VLMGuard: Bootstrapping Malicious Prompt Detectors from Unlabeled Vision-Language Prompts in the Wild","created":"2024-10-01","cited_by_count":18,"area":"mllm"},{"id":"2508.07173","title":"Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models","created":"2025-08-10","cited_by_count":18,"area":"safety"},{"id":"2502.13095","title":"Understanding and Rectifying Safety Perception Distortion in VLMs","created":"2025-02-18","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":"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":"2508.12815","title":"Learning to Steer: Input-dependent Steering for Multimodal LLMs","created":"2025-08-18","cited_by_count":15,"area":"mllm"},{"id":"2403.13507","title":"FMM-Attack: A Flow-based Multi-modal Adversarial Attack on Video-based LLMs","created":"2024-03-20","cited_by_count":14,"area":null},{"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":"2506.15606","title":"LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning","created":"2025-06-18","cited_by_count":12,"area":"safety"},{"id":"2510.27172","title":"Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler","created":"2025-10-31","cited_by_count":12,"area":null},{"id":"2511.12982","title":"SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization","created":"2025-11-17","cited_by_count":12,"area":"lr"},{"id":"2412.00142","title":"Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features","created":"2024-11-28","cited_by_count":11,"area":"mllm"},{"id":"2505.01456","title":"Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation","created":"2025-05-01","cited_by_count":11,"area":"mllm"},{"id":"2505.16559","title":"CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2505.17196","title":"Shape it Up! Restoring LLM Safety during Finetuning","created":"2025-05-22","cited_by_count":11,"area":"alignment"},{"id":"2508.07172","title":"Gradient Surgery for Safe LLM Fine-Tuning","created":"2025-08-10","cited_by_count":11,"area":"alignment"},{"id":"2512.06589","title":"OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation","created":"2025-12-06","cited_by_count":11,"area":"safety"},{"id":"2504.03770","title":"JailDAM: Jailbreak Detection with Adaptive Memory for Vision-Language Model","created":"2025-04-03","cited_by_count":10,"area":"mllm"},{"id":"2504.12661","title":"VLMGuard-R1: Proactive Safety Alignment for VLMs via Reasoning-Driven Prompt Optimization","created":"2025-04-17","cited_by_count":10,"area":"lr"},{"id":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","cited_by_count":10,"area":"safety"},{"id":"2505.23793","title":"USB: A Comprehensive and Unified Safety Evaluation Benchmark for Multimodal Large Language Models","created":"2025-05-26","cited_by_count":10,"area":"mllm"},{"id":"2510.06871","title":"SaFeR-VLM: Toward Safety-aware Fine-grained Reasoning in Multimodal Models","created":"2025-10-08","cited_by_count":10,"area":"lr"},{"id":"2603.03975","title":"Phi-4-reasoning-vision-15B Technical Report","created":"2026-03-04","cited_by_count":10,"area":"lr"},{"id":"2502.11361","title":"VLDBench Evaluating Multimodal Disinformation with Regulatory Alignment","created":"2025-02-17","cited_by_count":9,"area":null},{"id":"2503.01887","title":"When Continue Learning Meets Multimodal Large Language Model: A Survey","created":"2025-02-27","cited_by_count":9,"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":"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":"2504.09066","title":"Hyperlocal disaster damage assessment using bi-temporal street-view imagery and pre-trained vision models","created":"2025-04-12","cited_by_count":8,"area":null},{"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":"2509.22745","title":"Defending MoE LLMs against Harmful Fine-Tuning via Safety Routing Alignment","created":"2025-09-26","cited_by_count":8,"area":"moe"},{"id":"2510.17633","title":"SARSteer: Safeguarding Large Audio-Language Models via Safe-Ablated Refusal Steering","created":"2025-10-20","cited_by_count":8,"area":"safety"},{"id":"2407.02411","title":"Video Watermarking: Safeguarding Your Video from (Unauthorized) Annotations by Video-based LLMs","created":"2024-07-02","cited_by_count":7,"area":"safety"},{"id":"2412.12722","title":"Defending LVLMs Against Vision Attacks through Partial-Perception Supervision","created":"2024-12-17","cited_by_count":7,"area":"mllm"},{"id":"2502.13593","title":"Toward Robust Non-Transferable Learning: A Survey and Benchmark","created":"2025-02-19","cited_by_count":7,"area":null},{"id":"2512.01353","title":"The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search","created":"2025-12-01","cited_by_count":7,"area":"safety"},{"id":"2410.06154","title":"GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models","created":"2024-10-08","cited_by_count":6,"area":"mllm"},{"id":"2502.19537","title":"No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms","created":"2025-02-26","cited_by_count":6,"area":"safety"},{"id":"2602.10161","title":"Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment","created":"2026-02-10","cited_by_count":6,"area":null},{"id":"2602.16931","title":"Narrow Fine-Tuning Erodes Safety Alignment in Vision-Language Agents","created":"2026-02-18","cited_by_count":6,"area":"mllm"},{"id":"2603.00498","title":"Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence","created":"2026-02-28","cited_by_count":6,"area":"safety"},{"id":"2606.22873","title":"SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic Reasoning","created":"2026-06-22","cited_by_count":6,"area":"lr"},{"id":"2411.19335","title":"PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning","created":"2024-11-28","cited_by_count":5,"area":"safety"},{"id":"2502.00653","title":"Towards Robust Multimodal Large Language Models Against Jailbreak Attacks","created":"2025-02-02","cited_by_count":5,"area":"safety"},{"id":"2502.04757","title":"ELITE: Enhanced Language-Image Toxicity Evaluation for Safety","created":"2025-02-07","cited_by_count":5,"area":"mllm"},{"id":"2510.15476","title":"SoK: Systematizing LLM Prompt Security: Taxonomies, Datasets, and Unified Evaluation of Attacks and Defenses","created":"2025-10-17","cited_by_count":5,"area":"safety"},{"id":"2511.11301","title":"EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment","created":"2025-11-14","cited_by_count":5,"area":"lr"},{"id":"2603.15800","title":"Evolving Contextual Safety in Multi-Modal Large Language Models via Inference-Time Self-Reflective Memory","created":"2026-03-16","cited_by_count":5,"area":"lr"},{"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":"2412.06843","title":"Semantic Loss Guided Data Efficient Supervised Fine Tuning for Safe Responses in LLMs","created":"2024-12-07","cited_by_count":4,"area":null},{"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":"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":"2602.05228","title":"Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention Sink","created":"2026-02-05","cited_by_count":4,"area":"alignment"},{"id":"2603.20198","title":"Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic Planning","created":"2026-02-05","cited_by_count":4,"area":"agents"}],"next_cursor":"100"}