{"total":70,"rows":[{"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":"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":"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":"2506.02456","title":"VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents","created":"2025-06-03","cited_by_count":45,"area":"agents"},{"id":"2411.15720","title":"Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks","created":"2024-11-24","cited_by_count":39,"area":"mllm"},{"id":"2502.05209","title":"Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities","created":"2025-02-03","cited_by_count":39,"area":null},{"id":"2502.10794","title":"Distraction is All You Need for Multimodal Large Language Model Jailbreaking","created":"2025-02-15","cited_by_count":36,"area":"mllm"},{"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":"2507.02844","title":"Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection","created":"2025-07-03","cited_by_count":25,"area":"mllm"},{"id":"2504.18041","title":"RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models","created":"2025-04-25","cited_by_count":24,"area":"rag"},{"id":"2410.02298","title":"Jailbreak Antidote: Runtime Safety-Utility Balance via Sparse Representation Adjustment in Large Language Models","created":"2024-10-03","cited_by_count":23,"area":"safety"},{"id":"2411.11114","title":"JailbreakLens: Interpreting Jailbreak Mechanism in the Lens of Representation and Circuit","created":"2024-11-17","cited_by_count":22,"area":"safety"},{"id":"2409.18991","title":"Surveying the MLLM Landscape: A Meta-Review of Current Surveys","created":"2024-09-17","cited_by_count":20,"area":"mllm"},{"id":"2412.16633","title":"Easier Said Than Done: Unpacking Intent-Behavior Gap in Jailbreaking LLM-Based Robots","created":"2024-12-21","cited_by_count":15,"area":"safety"},{"id":"2502.04322","title":"Speak Easy: Eliciting Harmful Jailbreaks from LLMs with Simple Interactions","created":"2025-02-06","cited_by_count":15,"area":"alignment"},{"id":"2407.13621","title":"Differential Privacy Mechanisms in Neural Tangent Kernel Regression","created":"2024-07-18","cited_by_count":14,"area":null},{"id":"2407.14717","title":"Provable Differentially Private Computation of the Cross-Attention Mechanism","created":"2024-07-20","cited_by_count":14,"area":"diffusion"},{"id":"2502.16903","title":"GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods","created":"2025-02-24","cited_by_count":12,"area":"safety"},{"id":"2506.15170","title":"From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem","created":"2025-06-18","cited_by_count":12,"area":"agents"},{"id":"2409.14177","title":"PathSeeker: Exploring LLM Security Vulnerabilities with a Reinforcement Learning-Based Jailbreak Approach","created":"2024-09-21","cited_by_count":11,"area":"safety"},{"id":"2411.11407","title":"The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models","created":"2024-11-18","cited_by_count":10,"area":"safety"},{"id":"2411.11496","title":"Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models","created":"2024-11-18","cited_by_count":10,"area":"lr"},{"id":"2504.08974","title":"Mixed Signals: Decoding VLMs' Reasoning and Underlying Bias in Vision-Language Conflict","created":"2025-04-11","cited_by_count":10,"area":"lr"},{"id":"2506.20702","title":"The Singapore Consensus on Global AI Safety Research Priorities","created":"2025-06-25","cited_by_count":10,"area":null},{"id":"2502.01576","title":"Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models","created":"2025-02-03","cited_by_count":9,"area":"mllm"},{"id":"2510.02609","title":"RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents","created":"2025-10-02","cited_by_count":9,"area":"agents"},{"id":"2407.20181","title":"Blockchain for Large Language Model Security and Safety: A Holistic Survey","created":"2024-07-26","cited_by_count":8,"area":"safety"},{"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":"2601.04034","title":"HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense","created":"2026-01-07","cited_by_count":8,"area":"agents"},{"id":"2502.15334","title":"Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment","created":"2025-02-21","cited_by_count":7,"area":"safety"},{"id":"2506.07452","title":"When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment","created":"2025-06-09","cited_by_count":6,"area":"safety"},{"id":"2509.10546","title":"Learning to Conceal Risk: Controllable Multi-turn Red Teaming for LLMs in the Financial Domain","created":"2025-09-07","cited_by_count":6,"area":"safety"},{"id":"2410.09804","title":"BlackDAN: A Black-Box Multi-Objective Approach for Effective and Contextual Jailbreaking of Large Language Models","created":"2024-10-13","cited_by_count":5,"area":"safety"},{"id":"2510.09871","title":"CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs","created":"2025-10-10","cited_by_count":5,"area":"safety"},{"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":"2410.04190","title":"Harnessing Task Overload for Scalable Jailbreak Attacks on Large Language Models","created":"2024-10-05","cited_by_count":4,"area":"safety"},{"id":"2605.15030","title":"WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections","created":"2026-05-14","cited_by_count":4,"area":"agents"},{"id":"2504.01308","title":"Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks","created":"2025-04-02","cited_by_count":3,"area":"mllm"},{"id":"2602.03608","title":"Controlling Output Rankings in Generative Engines for LLM-based Search","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2603.22882","title":"TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration","created":"2026-03-24","cited_by_count":3,"area":"mllm"},{"id":"2605.21948","title":"SCI-Defense: Defending Manipulation Attacks from Generative Engine Optimization","created":"2026-05-21","cited_by_count":3,"area":null},{"id":"2502.14976","title":"EigenShield: Causal Subspace Filtering via Random Matrix Theory for Adversarially Robust Vision-Language Models","created":"2025-02-20","cited_by_count":2,"area":"mllm"},{"id":"2505.16643","title":"From Evaluation to Defense: Advancing Safety in Video Large Language Models","created":"2025-05-22","cited_by_count":2,"area":"safety"},{"id":"2505.24232","title":"From Hallucinations to Jailbreaks: Rethinking the Vulnerability of Large Foundation Models","created":"2025-05-30","cited_by_count":2,"area":"safety"},{"id":"2506.03933","title":"Diffusion-based Cumulative Adversarial Purification for Vision Language Models","created":"2025-06-04","cited_by_count":2,"area":"mllm"},{"id":"2507.00239","title":"Linearly Decoding Refused Knowledge in Aligned Language Models","created":"2025-06-30","cited_by_count":2,"area":"alignment"},{"id":"2507.07735","title":"GuardVal: Dynamic Large Language Model Jailbreak Evaluation for Comprehensive Safety Testing","created":"2025-07-10","cited_by_count":2,"area":"safety"},{"id":"2508.09201","title":"Learning to Detect Unseen Jailbreak Attacks in Large Vision-Language Models","created":"2025-08-08","cited_by_count":2,"area":"mllm"},{"id":"2512.18244","title":"Breaking Minds, Breaking Systems: Jailbreaking Large Language Models via Human-like Psychological Manipulation","created":"2025-12-20","cited_by_count":2,"area":"safety"},{"id":"2602.10148","title":"Red-teaming the Multimodal Reasoning: Jailbreaking Vision-Language Models via Cross-modal Entanglement Attacks","created":"2026-02-09","cited_by_count":2,"area":"lr"},{"id":"2603.27240","title":"Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection","created":"2026-03-28","cited_by_count":2,"area":"mllm"},{"id":"2508.09230","title":"Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems","created":"2025-08-12","cited_by_count":1,"area":"mllm"},{"id":"2508.10404","title":"Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation","created":"2025-08-14","cited_by_count":1,"area":"safety"},{"id":"2509.16060","title":"SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection","created":"2025-09-19","cited_by_count":1,"area":"alignment"},{"id":"2510.15430","title":"Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models","created":"2025-10-17","cited_by_count":1,"area":"mllm"},{"id":"2510.22628","title":"Sentra-Guard: A Real-Time Multilingual Defense Against Adversarial LLM Prompts","created":"2025-10-26","cited_by_count":1,"area":"safety"},{"id":"2511.08367","title":"Why Does Weak-OOD Help? A Further Step Towards Understanding Jailbreaking VLMs","created":"2025-11-11","cited_by_count":1,"area":"safety"},{"id":"2601.03420","title":"Jailbreaking LLMs Without Gradients or Priors: Effective and Transferable Attacks","created":"2026-01-06","cited_by_count":1,"area":"safety"},{"id":"2602.24027","title":"GuardAlign: Test-time Safety Alignment in Multimodal Large Language Models","created":"2026-02-27","cited_by_count":1,"area":"mllm"},{"id":"2604.11309","title":"The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems","created":"2026-04-13","cited_by_count":1,"area":"safety"},{"id":"2507.13629","title":"Large Language Models in Cybersecurity: Applications, Vulnerabilities, and Defense Techniques","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2510.21214","title":"Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses","created":"2025-10-24","cited_by_count":0,"area":"safety"},{"id":"2511.22584","title":"Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive HIL Testing","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2512.15081","title":"Quantifying Return on Security Controls in LLM Systems","created":"2025-12-17","cited_by_count":0,"area":"safety"},{"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":"2606.03713","title":"Investigating Adversarial Robustness of Multi-modal Large Language Models","created":"2026-06-02","cited_by_count":0,"area":"mllm"},{"id":"2608.00134","title":"Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks","created":"2026-07-31","cited_by_count":0,"area":"agents"},{"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":"2608.19737","title":"TempJail: Temporal Jailbreak Attack against Large Vision-Language Models via Subtitle Scheduling","created":"2026-08-20","cited_by_count":0,"area":"mllm"}],"next_cursor":null}