{"total":199,"rows":[{"id":"2504.15585","title":"A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment","created":"2025-04-22","cited_by_count":116,"area":"lr"},{"id":"2502.12659","title":"The Hidden Risks of Large Reasoning Models: A Safety Assessment of R1","created":"2025-02-18","cited_by_count":91,"area":"lr"},{"id":"2503.15754","title":"AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration","created":"2025-03-20","cited_by_count":43,"area":"safety"},{"id":"2503.05021","title":"Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety","created":"2025-03-06","cited_by_count":39,"area":"lr"},{"id":"2601.17548","title":"Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems","created":"2026-01-24","cited_by_count":31,"area":"agents"},{"id":"2502.01633","title":"Adversarial Reasoning at Jailbreaking Time","created":"2025-02-03","cited_by_count":29,"area":"lr"},{"id":"2504.18838","title":"Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarks","created":"2025-04-26","cited_by_count":28,"area":null},{"id":"2410.15362","title":"Faster-GCG: Efficient Discrete Optimization Jailbreak Attacks against Aligned Large Language Models","created":"2024-10-20","cited_by_count":25,"area":"alignment"},{"id":"2506.07564","title":"SAFEFLOW: A Principled Protocol for Trustworthy and Transactional Autonomous Agent Systems","created":"2025-06-09","cited_by_count":25,"area":"agents"},{"id":"2507.20526","title":"Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition","created":"2025-07-28","cited_by_count":24,"area":"lr"},{"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":"2602.09222","title":"MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks","created":"2026-02-09","cited_by_count":21,"area":"agents"},{"id":"2503.00187","title":"Steering Dialogue Dynamics for Robustness against Multi-turn Jailbreaking Attacks","created":"2025-02-28","cited_by_count":20,"area":"safety"},{"id":"2505.16186","title":"SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning","created":"2025-05-22","cited_by_count":20,"area":"lr"},{"id":"2510.21189","title":"Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency","created":"2025-10-24","cited_by_count":17,"area":"safety"},{"id":"2505.20259","title":"Lifelong Safety Alignment for Language Models","created":"2025-05-26","cited_by_count":15,"area":"alignment"},{"id":"2502.04204","title":"Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence","created":"2025-02-06","cited_by_count":14,"area":"safety"},{"id":"2504.19373","title":"Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models","created":"2025-04-27","cited_by_count":14,"area":null},{"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":"2602.20720","title":"AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs","created":"2026-02-24","cited_by_count":13,"area":"agents"},{"id":"2602.22983","title":"Obscure but Effective: Classical Chinese Jailbreak Prompt Optimization via Bio-Inspired Search","created":"2026-02-26","cited_by_count":13,"area":"safety"},{"id":"2411.14133","title":"GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs","created":"2024-11-21","cited_by_count":12,"area":"safety"},{"id":"2502.16776","title":"AISafetyLab: A Comprehensive Framework for AI Safety Evaluation and Improvement","created":"2025-02-24","cited_by_count":12,"area":null},{"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":"2509.22292","title":"Jailbreaking on Text-to-Video Models via Scene Splitting Strategy","created":"2025-09-26","cited_by_count":12,"area":"safety"},{"id":"2501.18638","title":"Graph of Attacks with Pruning: Optimizing Stealthy Jailbreak Prompt Generation for Enhanced LLM Content Moderation","created":"2025-01-28","cited_by_count":11,"area":"safety"},{"id":"2503.02174","title":"Adversarial Tokenization","created":"2025-03-04","cited_by_count":11,"area":"safety"},{"id":"2504.15047","title":"RainbowPlus: Enhancing Adversarial Prompt Generation via Evolutionary Quality-Diversity Search","created":"2025-04-21","cited_by_count":11,"area":"safety"},{"id":"2604.08499","title":"PIArena: A Platform for Prompt Injection Evaluation","created":"2026-04-09","cited_by_count":11,"area":"safety"},{"id":"2410.22143","title":"AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts","created":"2024-10-29","cited_by_count":10,"area":"safety"},{"id":"2502.09755","title":"Jailbreak Attack Initializations as Extractors of Compliance Directions","created":"2025-02-13","cited_by_count":10,"area":"safety"},{"id":"2503.06269","title":"Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models","created":"2025-03-08","cited_by_count":10,"area":"mechinterp"},{"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":"2507.22063","title":"RedCoder: Automated Multi-Turn Red Teaming for Code LLMs","created":"2025-06-25","cited_by_count":9,"area":"safety"},{"id":"2509.03728","title":"PersonaTeaming: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming","created":"2025-09-03","cited_by_count":9,"area":"safety"},{"id":"2509.26100","title":"AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models","created":"2025-09-30","cited_by_count":9,"area":"agents"},{"id":"2510.04398","title":"SECA: Semantically Equivalent and Coherent Attacks for Eliciting LLM Hallucinations","created":"2025-10-05","cited_by_count":9,"area":null},{"id":"2604.22167","title":"Estimating Tail Risks in Language Model Output Distributions","created":"2026-04-24","cited_by_count":9,"area":"safety"},{"id":"2507.01020","title":"AutoAdv: Automated Adversarial Prompting for Multi-Turn Jailbreaking of Large Language Models","created":"2025-04-18","cited_by_count":8,"area":"safety"},{"id":"2507.11500","title":"ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning","created":"2025-07-14","cited_by_count":8,"area":"alignment"},{"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":"2602.04896","title":"Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models","created":"2026-02-03","cited_by_count":8,"area":"alignment"},{"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":"2510.01529","title":"Bypassing Prompt Guards in Production with Controlled-Release Prompting","created":"2025-10-02","cited_by_count":7,"area":null},{"id":"2510.21910","title":"Adversarial D\\'ej\\`a Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks","created":"2025-10-24","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":"2601.10141","title":"Understanding and Preserving Safety in Fine-Tuned LLMs","created":"2026-01-15","cited_by_count":7,"area":"safety"},{"id":"2605.30883","title":"TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking","created":"2026-05-29","cited_by_count":7,"area":"agents"},{"id":"2502.18504","title":"TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice","created":"2025-02-21","cited_by_count":6,"area":"safety"},{"id":"2504.05652","title":"Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking","created":"2025-04-08","cited_by_count":6,"area":"safety"},{"id":"2506.15065","title":"HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models","created":"2025-06-18","cited_by_count":6,"area":"agents"},{"id":"2508.19292","title":"Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience","created":"2025-08-25","cited_by_count":6,"area":"safety"},{"id":"2509.11629","title":"Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2601.10589","title":"Be Your Own Red Teamer: Safety Alignment via Self-Play and Reflective Experience Replay","created":"2026-01-15","cited_by_count":6,"area":"alignment"},{"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":"2602.22554","title":"Multilingual Safety Alignment Via Sparse Weight Editing","created":"2026-02-26","cited_by_count":6,"area":"alignment"},{"id":"2607.19829","title":"DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection","created":"2026-07-22","cited_by_count":6,"area":"safety"},{"id":"2502.05223","title":"KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs","created":"2025-02-05","cited_by_count":5,"area":"safety"},{"id":"2505.22037","title":"Jailbreak Distillation: Renewable Safety Benchmarking","created":"2025-05-28","cited_by_count":5,"area":"safety"},{"id":"2507.02332","title":"PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage","created":"2025-07-03","cited_by_count":5,"area":"alignment"},{"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":"2510.26037","title":"SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning","created":"2025-10-30","cited_by_count":5,"area":"lr"},{"id":"2512.03771","title":"In-Context Representation Hijacking","created":"2025-12-03","cited_by_count":5,"area":"safety"},{"id":"2601.13518","title":"AgenticRed: Evolving Agentic Systems for Red-Teaming","created":"2026-01-20","cited_by_count":5,"area":"agents"},{"id":"2605.09594","title":"Trust Me, Import This: Dependency Steering Attacks via Malicious Agent Skills","created":"2026-05-10","cited_by_count":5,"area":"agents"},{"id":"2503.14281","title":"XOXO: Stealthy Cross-Origin Context Poisoning Attacks against AI Coding Assistants","created":"2025-03-18","cited_by_count":4,"area":null},{"id":"2503.24191","title":"When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output","created":"2025-03-31","cited_by_count":4,"area":"safety"},{"id":"2505.14607","title":"sudoLLM: On Multi-role Alignment of Language Models","created":"2025-05-20","cited_by_count":4,"area":"alignment"},{"id":"2506.22557","title":"MetaCipher: A Time-Persistent and Universal Multi-Agent Framework for Cipher-Based Jailbreak Attacks for LLMs","created":"2025-06-27","cited_by_count":4,"area":"agents"},{"id":"2506.22666","title":"VERA: Variational Inference Framework for Jailbreaking Large Language Models","created":"2025-06-27","cited_by_count":4,"area":"safety"},{"id":"2510.04257","title":"AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents","created":"2025-10-05","cited_by_count":4,"area":"mllm"},{"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":"2601.03578","title":"PsychEthicsBench: Evaluating Large Language Models Against Australian Mental Health Ethics","created":"2026-01-07","cited_by_count":4,"area":"alignment"},{"id":"2601.10543","title":"Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing","created":"2026-01-15","cited_by_count":4,"area":"safety"},{"id":"2601.21233","title":"Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs","created":"2026-01-29","cited_by_count":4,"area":"agents"},{"id":"2602.00388","title":"Safer by Diffusion, Broken by Context: Diffusion LLM's Safety Blessing and Its Failure Mode","created":"2026-01-30","cited_by_count":4,"area":"safety"},{"id":"2605.31140","title":"EvoDefense: Co-Evolving Black-Box Defense with Large Language Models","created":"2026-05-29","cited_by_count":4,"area":null},{"id":"2506.07402","title":"Beyond Jailbreaks: Revealing Stealthier and Broader LLM Security Risks Stemming from Alignment Failures","created":"2025-06-09","cited_by_count":3,"area":"alignment"},{"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":"2510.21190","title":"The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning","created":"2025-10-24","cited_by_count":3,"area":"alignment"},{"id":"2601.03699","title":"RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models","created":"2026-01-07","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":"2602.11528","title":"Stop Tracking Me! Proactive Defense Against Attribute Inference Attack in LLMs","created":"2026-02-12","cited_by_count":3,"area":null},{"id":"2602.13547","title":"AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks","created":"2026-02-14","cited_by_count":3,"area":"safety"},{"id":"2602.20170","title":"CAGE: A Framework for Culturally Adaptive Red-Teaming Benchmark Generation","created":"2026-02-09","cited_by_count":3,"area":"safety"},{"id":"2603.01185","title":"Token-level Data Selection for Safe LLM Fine-tuning","created":"2026-03-01","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":"2605.00706","title":"FinSafetyBench: Evaluating LLM Safety in Real-World Financial Scenarios","created":"2026-05-01","cited_by_count":3,"area":"safety"},{"id":"2605.05058","title":"SoK: Robustness in Large Language Models against Jailbreak Attacks","created":"2026-05-06","cited_by_count":3,"area":"safety"},{"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":"2605.29237","title":"Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking","created":"2026-05-28","cited_by_count":3,"area":"safety"},{"id":"2606.05743","title":"Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense","created":"2026-06-04","cited_by_count":3,"area":"agents"},{"id":"2606.11671","title":"Runtime Skill Audit: Targeted Runtime Probing for Agent Skill Security","created":"2026-06-10","cited_by_count":3,"area":"agents"},{"id":"2503.08990","title":"Effective and Efficient Jailbreaks of Black-Box LLMs with Cross-Behavior Attacks","created":"2025-03-12","cited_by_count":2,"area":"safety"},{"id":"2508.10032","title":"The Cost of Thinking: Increased Jailbreak Risk in Large Language Models","created":"2025-08-09","cited_by_count":2,"area":"lr"},{"id":"2508.16325","title":"ConceptGuard: Neuro-Symbolic Safety Guardrails via Sparse Interpretable Jailbreak Concepts","created":"2025-08-22","cited_by_count":2,"area":"safety"},{"id":"2508.16484","title":"HAMSA: Hijacking Aligned Compact Models via Stealthy Automation","created":"2025-08-22","cited_by_count":2,"area":"safety"}],"next_cursor":"100"}