{"total":125,"rows":[{"id":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"area":"alignment"},{"id":"2602.16901","title":"AgentLAB: Benchmarking LLM Agents against Long-Horizon Attacks","created":"2026-02-18","cited_by_count":39,"area":"agents"},{"id":"2509.22830","title":"ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents","created":"2025-09-26","cited_by_count":31,"area":"agents"},{"id":"2602.13379","title":"Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents","created":"2026-02-13","cited_by_count":30,"area":"agents"},{"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":"2507.00971","title":"Reasoning as an Adaptive Defense for Safety","created":"2025-07-01","cited_by_count":23,"area":"lr"},{"id":"2506.10597","title":"SoK: Evaluating Jailbreak Guardrails for Large Language Models","created":"2025-06-12","cited_by_count":21,"area":"alignment"},{"id":"2601.01592","title":"OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs","created":"2026-01-04","cited_by_count":21,"area":"mllm"},{"id":"2602.01539","title":"MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety","created":"2026-02-02","cited_by_count":21,"area":"alignment"},{"id":"2505.16186","title":"SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning","created":"2025-05-22","cited_by_count":20,"area":"lr"},{"id":"2511.12997","title":"WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidance","created":"2025-11-17","cited_by_count":16,"area":"agents"},{"id":"2512.07761","title":"TROJail: Trajectory-Level Optimization for Multi-Turn Large Language Model Jailbreaks with Process Rewards","created":"2025-12-08","cited_by_count":14,"area":"safety"},{"id":"2506.00781","title":"CoP: Agentic Red-teaming for Large Language Models using Composition of Principles","created":"2025-06-01","cited_by_count":13,"area":"agents"},{"id":"2508.04039","title":"Large Reasoning Models Are Autonomous Jailbreak Agents","created":"2025-08-04","cited_by_count":13,"area":"lr"},{"id":"2508.17450","title":"Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD","created":"2025-08-24","cited_by_count":13,"area":null},{"id":"2509.23614","title":"PSG-Agent: Personality-Aware Safety Guardrail for LLM-based Agents","created":"2025-09-28","cited_by_count":12,"area":"agents"},{"id":"2602.06854","title":"SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks","created":"2026-02-06","cited_by_count":12,"area":"safety"},{"id":"2507.05248","title":"Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models","created":"2025-07-07","cited_by_count":10,"area":"safety"},{"id":"2510.14312","title":"Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies","created":"2025-10-16","cited_by_count":10,"area":"agents"},{"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":"2509.25624","title":"STAC: When Innocent Tools Form Dangerous Chains for LLM Agents","created":"2025-09-30","cited_by_count":8,"area":"agents"},{"id":"2510.02286","title":"Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks","created":"2025-10-02","cited_by_count":8,"area":"safety"},{"id":"2511.12710","title":"Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs","created":"2025-11-16","cited_by_count":8,"area":"safety"},{"id":"2602.16935","title":"DeepContext: Stateful Real-Time Detection of Multi-Turn Adversarial Intent Drift in LLMs","created":"2026-02-18","cited_by_count":8,"area":"safety"},{"id":"2605.01687","title":"MultiBreak: A Scalable and Diverse Multi-turn Jailbreak Benchmark for Evaluating LLM Safety","created":"2026-05-03","cited_by_count":8,"area":"safety"},{"id":"2506.00668","title":"SafeTy Reasoning Elicitation Alignment for Multi-Turn Dialogues","created":"2025-05-31","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":"2511.19517","title":"Automating Deception: Scalable Multi-Turn LLM Jailbreaks","created":"2025-11-24","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":"2605.03228","title":"Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory","created":"2026-05-04","cited_by_count":7,"area":"agents"},{"id":"2605.30883","title":"TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking","created":"2026-05-29","cited_by_count":7,"area":"agents"},{"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":"2512.10449","title":"When Reject Turns into Accept: Quantifying the Vulnerability of LLM-Based Scientific Reviewers to Indirect Prompt Injection","created":"2025-12-11","cited_by_count":6,"area":"safety"},{"id":"2601.20903","title":"ICON: Intent-Context Coupling for Efficient Multi-Turn Jailbreak Attack","created":"2026-01-28","cited_by_count":6,"area":"safety"},{"id":"2510.02677","title":"ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks","created":"2025-10-03","cited_by_count":5,"area":"mllm"},{"id":"2510.08646","title":"Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy","created":"2025-10-09","cited_by_count":5,"area":"alignment"},{"id":"2511.04694","title":"Reasoning Up the Instruction Ladder for Controllable Language Models","created":"2025-10-30","cited_by_count":5,"area":"lr"},{"id":"2601.13518","title":"AgenticRed: Evolving Agentic Systems for Red-Teaming","created":"2026-01-20","cited_by_count":5,"area":"agents"},{"id":"2510.08859","title":"Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models","created":"2025-10-09","cited_by_count":4,"area":"safety"},{"id":"2511.07315","title":"JPRO: Automated Multimodal Jailbreaking via Multi-Agent Collaboration Framework","created":"2025-11-10","cited_by_count":4,"area":"agents"},{"id":"2601.06757","title":"MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues","created":"2026-01-11","cited_by_count":4,"area":"mllm"},{"id":"2603.15684","title":"State-Dependent Safety Failures in Multi-Turn Language Model Interaction","created":"2026-03-15","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"},{"id":"2510.17947","title":"PLAGUE: Plug-and-play framework for Lifelong Adaptive Generation of Multi-turn Exploits","created":"2025-10-20","cited_by_count":3,"area":"safety"},{"id":"2512.22082","title":"Agent-based simulation of online social networks and disinformation","created":"2025-12-26","cited_by_count":3,"area":"agents"},{"id":"2601.19726","title":"RvB: Automating AI System Hardening via Iterative Red-Blue Games","created":"2026-01-27","cited_by_count":3,"area":"safety"},{"id":"2602.04448","title":"RASA: Routing-Aware Safety Alignment for Mixture-of-Experts Models","created":"2026-02-04","cited_by_count":3,"area":"alignment"},{"id":"2602.08874","title":"Do Reasoning LLMs Refuse What They Infer in Long Contexts?","created":"2026-02-09","cited_by_count":3,"area":"lr"},{"id":"2604.17730","title":"MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2604.27093","title":"Useless but Safe? Benchmarking Utility Recovery with User Intent Clarification in Multi-Turn Conversations","created":"2026-04-29","cited_by_count":3,"area":"alignment"},{"id":"2605.08778","title":"Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking","created":"2026-05-09","cited_by_count":3,"area":"safety"},{"id":"2605.11002","title":"MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks","created":"2026-05-10","cited_by_count":3,"area":"safety"},{"id":"2608.16465","title":"JailbreakSkill: Scaling Automated Red-Teaming with Reusable and Ever-Evolving Skills","created":"2026-08-17","cited_by_count":3,"area":"safety"},{"id":"2609.09090","title":"SPINE: Measuring LLM Sycophancy under Sustained Multi-Turn Pressure","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2506.17266","title":"Securing Generative AI Agentic Workflows: Risks, Mitigation, and a Proposed Firewall Architecture","created":"2025-06-10","cited_by_count":2,"area":"agents"},{"id":"2511.06396","title":"Efficient LLM Safety Evaluation through Multi-Agent Debate","created":"2025-11-09","cited_by_count":2,"area":"agents"},{"id":"2602.16346","title":"Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents","created":"2026-02-18","cited_by_count":2,"area":"agents"},{"id":"2604.16543","title":"Conjunctive Prompt Attacks in Multi-Agent LLM Systems","created":"2026-04-17","cited_by_count":2,"area":"agents"},{"id":"2604.16824","title":"SafeDream: Safety World Model for Proactive Early Jailbreak Detection","created":"2026-04-18","cited_by_count":2,"area":"wm"},{"id":"2604.16916","title":"When Choices Become Risks: Safety Failures of Large Language Models under Multiple-Choice Constraints","created":"2026-04-18","cited_by_count":2,"area":"alignment"},{"id":"2606.01738","title":"THRD: A Training-Free Multi-Turn Defense Framework for Jailbreak Attacks on Large Language Models","created":"2026-06-01","cited_by_count":2,"area":"safety"},{"id":"2606.02423","title":"Investigating and Alleviating Harm Amplification in LLM Interactions","created":"2026-06-01","cited_by_count":2,"area":"safety"},{"id":"2606.06797","title":"Korean Culture into LLM Alignment: Toward Cultural Coherence","created":"2026-06-05","cited_by_count":2,"area":"alignment"},{"id":"2607.13394","title":"GFlowRL: Scaling Distribution-Matching RL to Large Language Models","created":"2026-07-15","cited_by_count":2,"area":"lr"},{"id":"2607.19424","title":"JailMeter: An Evidence-Based Evaluation Framework for Jailbreak Attacks on Large Language Models","created":"2026-07-20","cited_by_count":2,"area":"safety"},{"id":"2509.08729","title":"X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates","created":"2025-09-10","cited_by_count":1,"area":"safety"},{"id":"2509.22732","title":"Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks","created":"2025-09-25","cited_by_count":1,"area":"alignment"},{"id":"2509.26473","title":"The Plot Twist: Jailbreaking Unified Multimodal Models with a Three-Act NarrativeAttack","created":"2025-09-30","cited_by_count":1,"area":"safety"},{"id":"2511.14195","title":"N-GLARE: An Non-Generative Latent Representation-Efficient LLM Safety Evaluator","created":"2025-11-18","cited_by_count":1,"area":"safety"},{"id":"2601.02670","title":"Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting","created":"2026-01-06","cited_by_count":1,"area":"safety"},{"id":"2601.10971","title":"AJAR: Adaptive Jailbreak Architecture for Red-teaming","created":"2026-01-16","cited_by_count":1,"area":"safety"},{"id":"2602.02395","title":"David vs. Goliath: Verifiable Agent-to-Agent Jailbreaking via Reinforcement Learning","created":"2026-02-02","cited_by_count":1,"area":"agents"},{"id":"2603.10807","title":"Risk-Adjusted Harm Scoring for Automated Red Teaming for LLMs in Financial Services","created":"2026-03-11","cited_by_count":1,"area":"safety"},{"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":"2604.11666","title":"Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind","created":"2026-04-13","cited_by_count":1,"area":"agents"},{"id":"2604.15717","title":"Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries","created":"2026-04-17","cited_by_count":1,"area":"alignment"},{"id":"2606.02640","title":"D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting","created":"2026-05-31","cited_by_count":1,"area":"safety"},{"id":"2608.01117","title":"SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks","created":"2026-08-02","cited_by_count":1,"area":"safety"},{"id":"2608.17605","title":"Multi-turn Conversational AI from Text to Multimodal Interaction: Data, Models, Evaluation, and Open Challenges","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2608.23028","title":"PsychJail: Exploring Psychological Jailbreaks via Multi-Turn Persuasion of LLM Policies","created":"2026-08-24","cited_by_count":1,"area":"safety"},{"id":"2511.05018","title":"Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2601.04736","title":"Towards Multi-modal Multi-turn Safety: From Agentic Interaction to Strategic Alignment","created":"2026-01-08","cited_by_count":0,"area":"mllm"},{"id":"2602.04856","title":"CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News Generation","created":"2026-02-04","cited_by_count":0,"area":"lr"},{"id":"2602.06630","title":"TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking","created":"2026-02-06","cited_by_count":0,"area":"safety"},{"id":"2603.18637","title":"MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment","created":"2026-03-19","cited_by_count":0,"area":"alignment"},{"id":"2604.01473","title":"SelfGrader: LLM Jailbreak Detection via Anchored Token-Level Logits","created":"2026-04-01","cited_by_count":0,"area":"safety"},{"id":"2604.23067","title":"Training a General Purpose Automated Red Teaming Model","created":"2026-04-24","cited_by_count":0,"area":"safety"},{"id":"2605.05630","title":"One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.08277","title":"Mitigating Many-shot Jailbreak Attacks with One Single Demonstration","created":"2026-05-08","cited_by_count":0,"area":"alignment"},{"id":"2605.13411","title":"Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution","created":"2026-05-13","cited_by_count":0,"area":"safety"},{"id":"2605.22373","title":"Boundary-targeted Membership Inference Attacks on Safety Classifiers","created":"2026-05-21","cited_by_count":0,"area":"safety"},{"id":"2605.29224","title":"Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM Agents","created":"2026-05-28","cited_by_count":0,"area":"agents"},{"id":"2606.11470","title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.24267","title":"Pigeonholing: how bad prompts hurt models, causing collapse and mistakes","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2607.11070","title":"MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment","created":"2026-07-13","cited_by_count":0,"area":"safety"},{"id":"2607.11151","title":"AMT-X: Phase-Structured Multi-Turn Red-Teaming with Checklist-Gated Evaluation","created":"2026-07-13","cited_by_count":0,"area":"safety"},{"id":"2607.14256","title":"Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation","created":"2026-07-15","cited_by_count":0,"area":"mllm"},{"id":"2607.18622","title":"CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization","created":"2026-07-21","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}