{"total":230,"rows":[{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2502.12893","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","created":"2025-02-18","cited_by_count":99,"area":"lr"},{"id":"2411.11296","title":"Steering Language Model Refusal with Sparse Autoencoders","created":"2024-11-18","cited_by_count":95,"area":"mechinterp"},{"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":"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":"2504.17704","title":"Safety in Large Reasoning Models: A Survey","created":"2025-04-24","cited_by_count":64,"area":"lr"},{"id":"2502.07557","title":"JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation","created":"2025-02-11","cited_by_count":54,"area":"safety"},{"id":"2502.08745","title":"IHEval: Evaluating Language Models on Following the Instruction Hierarchy","created":"2025-02-12","cited_by_count":53,"area":null},{"id":"2502.02716","title":"A Unified Understanding and Evaluation of Steering Methods","created":"2025-02-04","cited_by_count":46,"area":"mechinterp"},{"id":"2502.15806","title":"A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos","created":"2025-02-19","cited_by_count":43,"area":"lr"},{"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":"2412.13879","title":"Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings","created":"2024-12-18","cited_by_count":35,"area":null},{"id":"2512.23738","title":"Enforcing Temporal Constraints for LLM Agents","created":"2025-12-25","cited_by_count":34,"area":"agents"},{"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":"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":"2505.00551","title":"100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2411.03343","title":"What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks","created":"2024-11-02","cited_by_count":29,"area":"safety"},{"id":"2603.11619","title":"Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats","created":"2026-03-12","cited_by_count":29,"area":"agents"},{"id":"2506.11094","title":"The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMs","created":"2025-06-06","cited_by_count":26,"area":null},{"id":"2507.19227","title":"Jailbreaking Large Language Diffusion Models: Revealing Hidden Safety Flaws in Diffusion-Based Text Generation","created":"2025-07-25","cited_by_count":26,"area":"lr"},{"id":"2602.14211","title":"SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents","created":"2026-02-15","cited_by_count":25,"area":"agents"},{"id":"2504.07887","title":"Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge","created":"2025-04-10","cited_by_count":23,"area":"safety"},{"id":"2504.13626","title":"Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models","created":"2025-04-18","cited_by_count":23,"area":"lr"},{"id":"2511.20703","title":"PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach","created":"2025-11-24","cited_by_count":22,"area":"agents"},{"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":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2505.06679","title":"T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks","created":"2025-05-10","cited_by_count":21,"area":"diffusion"},{"id":"2502.09990","title":"X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability","created":"2025-02-14","cited_by_count":20,"area":"alignment"},{"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":"2502.21059","title":"FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts","created":"2025-02-28","cited_by_count":18,"area":"safety"},{"id":"2504.15512","title":"T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models","created":"2025-04-22","cited_by_count":18,"area":"safety"},{"id":"2505.14103","title":"AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models","created":"2025-05-20","cited_by_count":18,"area":"safety"},{"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":"2502.04951","title":"Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search","created":"2025-02-07","cited_by_count":16,"area":null},{"id":"2505.17568","title":"JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models","created":"2025-05-23","cited_by_count":16,"area":"safety"},{"id":"2512.04864","title":"Are Your Agents Upward Deceivers?","created":"2025-12-04","cited_by_count":16,"area":"agents"},{"id":"2506.05739","title":"To Protect the LLM Agent Against the Prompt Injection Attack with Polymorphic Prompt","created":"2025-06-06","cited_by_count":15,"area":"agents"},{"id":"2509.24384","title":"HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment","created":"2025-09-29","cited_by_count":15,"area":"safety"},{"id":"2501.13080","title":"Refining Input Guardrails: Enhancing LLM-as-a-Judge Efficiency Through Chain-of-Thought Fine-Tuning and Alignment","created":"2025-01-22","cited_by_count":14,"area":"lr"},{"id":"2506.24068","title":"STACK: Adversarial Attacks on LLM Safeguard Pipelines","created":"2025-06-30","cited_by_count":14,"area":null},{"id":"2603.04474","title":"From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration","created":"2026-03-04","cited_by_count":14,"area":"agents"},{"id":"2501.14250","title":"Siren: A Learning-Based Multi-Turn Attack Framework for Simulating Real-World Human Jailbreak Behaviors","created":"2025-01-24","cited_by_count":13,"area":"safety"},{"id":"2507.04724","title":"Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems","created":"2025-07-07","cited_by_count":13,"area":"agents"},{"id":"2410.21083","title":"Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring","created":"2024-10-28","cited_by_count":12,"area":"safety"},{"id":"2411.19530","title":"Quantized Delta Weight Is Safety Keeper","created":"2024-11-29","cited_by_count":12,"area":"safety"},{"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":"2504.05804","title":"StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimization","created":"2025-04-08","cited_by_count":12,"area":null},{"id":"2504.14556","title":"LLM-Enabled In-Context Learning for Data Collection Scheduling in UAV-assisted Sensor Networks","created":"2025-04-20","cited_by_count":12,"area":null},{"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":"2412.15623","title":"JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs","created":"2024-12-20","cited_by_count":11,"area":"alignment"},{"id":"2508.19277","title":"POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization","created":"2025-08-23","cited_by_count":11,"area":"lr"},{"id":"2510.01270","title":"Think Twice, Generate Once: Safeguarding by Progressive Self-Reflection","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2407.11843","title":"Preemptive Detection and Correction of Misaligned Actions in LLM Agents","created":"2024-07-16","cited_by_count":10,"area":"agents"},{"id":"2411.04223","title":"Diversity Helps Jailbreak Large Language Models","created":"2024-11-06","cited_by_count":10,"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":"2412.17242","title":"On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writing","created":"2024-12-23","cited_by_count":10,"area":null},{"id":"2501.12210","title":"You Can't Eat Your Cake and Have It Too: The Performance Degradation of LLMs with Jailbreak Defense","created":"2025-01-21","cited_by_count":10,"area":"safety"},{"id":"2501.18632","title":"Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare","created":"2025-01-27","cited_by_count":10,"area":"safety"},{"id":"2502.15435","title":"Single-pass Detection of Jailbreaking Input in Large Language Models","created":"2025-02-21","cited_by_count":10,"area":"alignment"},{"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":"2504.16489","title":"Amplified Vulnerabilities: Structured Jailbreak Attacks on LLM-based Multi-Agent Debate","created":"2025-04-23","cited_by_count":10,"area":"lr"},{"id":"2505.12981","title":"From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents","created":"2025-05-19","cited_by_count":10,"area":"agents"},{"id":"2602.07398","title":"AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management","created":"2026-02-07","cited_by_count":10,"area":"agents"},{"id":"2502.19041","title":"Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs","created":"2025-02-26","cited_by_count":9,"area":"safety"},{"id":"2505.14316","title":"Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion","created":"2025-05-20","cited_by_count":9,"area":"safety"},{"id":"2506.07121","title":"Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models","created":"2025-06-08","cited_by_count":9,"area":"safety"},{"id":"2510.02609","title":"RedCodeAgent: Automatic Red-teaming Agent against Diverse Code Agents","created":"2025-10-02","cited_by_count":9,"area":"agents"},{"id":"2510.24966","title":"Sequences of Logits Reveal the Low Rank Structure of Language Models","created":"2025-10-28","cited_by_count":9,"area":null},{"id":"2602.12966","title":"ProbeLLM: Automating Principled Diagnosis of LLM Failures","created":"2026-02-13","cited_by_count":9,"area":null},{"id":"2603.00131","title":"Thought Virus: Viral Misalignment via Subliminal Prompting in Multi-Agent Systems","created":"2026-02-23","cited_by_count":9,"area":"lr"},{"id":"2412.11934","title":"Stepwise Reasoning Error Disruption Attack of LLMs","created":"2024-12-16","cited_by_count":8,"area":"lr"},{"id":"2502.00718","title":"\"I am bad\": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models","created":"2025-02-02","cited_by_count":8,"area":"safety"},{"id":"2505.23839","title":"GeneBreaker: Jailbreak Attacks against DNA Language Models with Pathogenicity Guidance","created":"2025-05-28","cited_by_count":8,"area":"safety"},{"id":"2602.08401","title":"On Protecting Agentic Systems' Intellectual Property via Watermarking","created":"2026-02-09","cited_by_count":8,"area":"agents"},{"id":"2501.00055","title":"LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models","created":"2024-12-28","cited_by_count":7,"area":"safety"},{"id":"2504.02458","title":"Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendation","created":"2025-04-03","cited_by_count":7,"area":"rag"},{"id":"2505.10846","title":"AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models","created":"2025-05-16","cited_by_count":7,"area":"lr"},{"id":"2510.05052","title":"Proactive defense against LLM Jailbreak","created":"2025-10-06","cited_by_count":7,"area":"alignment"},{"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":"2601.05445","title":"Knowledge-Driven Multi-Turn Jailbreaking on Large Language Models","created":"2026-01-09","cited_by_count":7,"area":"safety"},{"id":"2605.23723","title":"MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection","created":"2026-05-22","cited_by_count":7,"area":"agents"},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2501.02997","title":"CALM: Curiosity-Driven Auditing for Large Language Models","created":"2025-01-06","cited_by_count":6,"area":null},{"id":"2508.11222","title":"ORFuzz: Fuzzing the \"Other Side\" of LLM Safety -- Testing Over-Refusal","created":"2025-08-15","cited_by_count":6,"area":"safety"},{"id":"2509.06982","title":"CARE: Decoding Time Safety Alignment via Rollback and Introspection Intervention","created":"2025-09-01","cited_by_count":6,"area":"alignment"},{"id":"2602.22554","title":"Multilingual Safety Alignment Via Sparse Weight Editing","created":"2026-02-26","cited_by_count":6,"area":"alignment"},{"id":"2605.02946","title":"RouteHijack: Routing-Aware Attack on Mixture-of-Experts LLMs","created":"2026-05-01","cited_by_count":6,"area":"alignment"},{"id":"2410.09569","title":"Are You Human? An Adversarial Benchmark to Expose LLMs","created":"2024-10-12","cited_by_count":5,"area":null},{"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":"2410.11283","title":"AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment","created":"2024-10-15","cited_by_count":5,"area":"alignment"},{"id":"2505.16789","title":"Accidental Vulnerability: Factors in Fine-Tuning that Shift Model Safeguards","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2507.04365","title":"Attention Slipping: A Mechanistic Understanding of Jailbreak Attacks and Defenses in LLMs","created":"2025-07-06","cited_by_count":5,"area":"safety"},{"id":"2507.06043","title":"CAVGAN: Unifying Jailbreak and Defense of LLMs via Generative Adversarial Attacks on their Internal Representations","created":"2025-07-08","cited_by_count":5,"area":"safety"},{"id":"2507.08207","title":"Toward a Dynamic Stackelberg Game-Theoretic Framework for Agentic AI Defense Against LLM Jailbreaking","created":"2025-07-10","cited_by_count":5,"area":"agents"},{"id":"2510.04891","title":"SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests","created":"2025-10-06","cited_by_count":5,"area":"safety"},{"id":"2510.07642","title":"Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2510.13893","title":"Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection","created":"2025-10-14","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":"2511.22047","title":"Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks","created":"2025-11-27","cited_by_count":5,"area":"safety"}],"next_cursor":"100"}