{"total":88,"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":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80,"area":"safety"},{"id":"2405.18540","title":"Learning diverse attacks on large language models for robust red-teaming and safety tuning","created":"2024-05-28","cited_by_count":54,"area":"safety"},{"id":"2405.14125","title":"ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation","created":"2024-05-23","cited_by_count":47,"area":"agents"},{"id":"2406.08705","title":"When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search","created":"2024-06-13","cited_by_count":47,"area":"safety"},{"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":"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":"2405.19360","title":"ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users","created":"2024-05-24","cited_by_count":35,"area":"safety"},{"id":"2409.00598","title":"Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models","created":"2024-09-01","cited_by_count":35,"area":"alignment"},{"id":"2404.13968","title":"Protecting Your LLMs with Information Bottleneck","created":"2024-04-22","cited_by_count":29,"area":"safety"},{"id":"2503.18929","title":"Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training","created":"2025-03-24","cited_by_count":29,"area":"lr"},{"id":"2412.18693","title":"Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning","created":"2024-12-24","cited_by_count":25,"area":"safety"},{"id":"2408.01420","title":"Mission Impossible: A Statistical Perspective on Jailbreaking LLMs","created":"2024-08-02","cited_by_count":24,"area":"alignment"},{"id":"2410.01432","title":"Adaptive teachers for amortized samplers","created":"2024-10-02","cited_by_count":23,"area":null},{"id":"2410.10343","title":"Locking Down the Finetuned LLMs Safety","created":"2024-10-14","cited_by_count":22,"area":null},{"id":"2508.10880","title":"Searching for Privacy Risks in LLM Agents via Simulation","created":"2025-08-14","cited_by_count":22,"area":"agents"},{"id":"2410.01524","title":"HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models","created":"2024-10-02","cited_by_count":19,"area":"distill"},{"id":"2509.01909","title":"Oyster-I: Beyond Refusal -- Constructive Safety Alignment for Responsible Language Models","created":"2025-09-02","cited_by_count":19,"area":"alignment"},{"id":"2406.14230","title":"Raising the Bar: Investigating the Values of Large Language Models via Generative Evolving Testing","created":"2024-06-20","cited_by_count":17,"area":null},{"id":"2410.10862","title":"Superficial Safety Alignment Hypothesis","created":"2024-10-07","cited_by_count":14,"area":"alignment"},{"id":"2406.10977","title":"Toward Optimal LLM Alignments Using Two-Player Games","created":"2024-06-16","cited_by_count":13,"area":"alignment"},{"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":"2411.16554","title":"Generating Out-Of-Distribution Scenarios Using Language Models","created":"2024-11-25","cited_by_count":10,"area":null},{"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":"2408.02632","title":"SEAS: Self-Evolving Adversarial Safety Optimization for Large Language Models","created":"2024-08-05","cited_by_count":9,"area":"synth"},{"id":"2505.17072","title":"Safety Alignment Can Be Not Superficial With Explicit Safety Signals","created":"2025-05-19","cited_by_count":9,"area":"alignment"},{"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":"2605.22817","title":"Vector Policy Optimization: Training for Diversity Improves Test-Time Search","created":"2026-05-21","cited_by_count":8,"area":null},{"id":"2410.16736","title":"Forewarned is Forearmed: Leveraging LLMs for Data Synthesis through Failure-Inducing Exploration","created":"2024-10-22","cited_by_count":7,"area":"synth"},{"id":"2412.02818","title":"RoboMD: Uncovering Robot Vulnerabilities through Semantic Potential Fields","created":"2024-12-03","cited_by_count":7,"area":"deeprl"},{"id":"2506.11083","title":"RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates","created":"2025-06-04","cited_by_count":7,"area":"agents"},{"id":"2508.14904","title":"Efficient Switchable Safety Control in LLMs via Magic-Token-Guided Co-Training","created":"2025-08-12","cited_by_count":7,"area":"alignment"},{"id":"2509.21947","title":"Active Attacks: Red-teaming LLMs via Adaptive Environments","created":"2025-09-26","cited_by_count":7,"area":"safety"},{"id":"2405.12604","title":"Tiny Refinements Elicit Resilience: Toward Efficient Prefix-Model Against LLM Red-Teaming","created":"2024-05-21","cited_by_count":6,"area":"safety"},{"id":"2501.02997","title":"CALM: Curiosity-Driven Auditing for Large Language Models","created":"2025-01-06","cited_by_count":6,"area":null},{"id":"2509.12434","title":"Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization","created":"2025-09-15","cited_by_count":6,"area":"lr"},{"id":"2501.08246","title":"Text-Diffusion Red-Teaming of Large Language Models: Unveiling Harmful Behaviors with Proximity Constraints","created":"2025-01-14","cited_by_count":5,"area":"safety"},{"id":"2502.20309","title":"EAIRA: Establishing a Methodology for Evaluating AI Models as Scientific Research Assistants","created":"2025-02-27","cited_by_count":5,"area":null},{"id":"2507.16329","title":"DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling","created":"2025-07-22","cited_by_count":5,"area":"alignment"},{"id":"2510.07239","title":"Red-Bandit: Test-Time Adaptation for LLM Red-Teaming via Bandit-Guided LoRA Experts","created":"2025-10-08","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"},{"id":"2412.05232","title":"LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds","created":"2024-12-06","cited_by_count":4,"area":"safety"},{"id":"2412.10807","title":"Towards Action Hijacking of Large Language Model-based Agent","created":"2024-12-14","cited_by_count":4,"area":"agents"},{"id":"2506.10047","title":"GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models","created":"2025-06-11","cited_by_count":4,"area":"diffusion"},{"id":"2507.11155","title":"Bridging the Gap in Vision Language Models in Identifying Unsafe Concepts Across Modalities","created":"2025-07-15","cited_by_count":4,"area":"lr"},{"id":"2509.12379","title":"Geometric Red-Teaming for Robotic Manipulation","created":"2025-09-15","cited_by_count":4,"area":null},{"id":"2509.16950","title":"Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving","created":"2025-09-21","cited_by_count":4,"area":"safety"},{"id":"2511.00030","title":"Probing Knowledge Holes in Unlearned LLMs","created":"2025-10-27","cited_by_count":4,"area":"safety"},{"id":"2511.12429","title":"Tailored Primitive Initialization is the Secret Key to Reinforcement Learning","created":"2025-11-16","cited_by_count":4,"area":"lr"},{"id":"2512.23701","title":"Eliciting Behaviors in Multi-Turn Conversations","created":"2025-12-29","cited_by_count":4,"area":null},{"id":"2602.01025","title":"Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models","created":"2026-02-01","cited_by_count":4,"area":"mllm"},{"id":"2407.03995","title":"ROER: Regularized Optimal Experience Replay","created":"2024-07-04","cited_by_count":3,"area":"deeprl"},{"id":"2502.14037","title":"DiffSampling: Enhancing Diversity and Accuracy in Neural Text Generation","created":"2025-02-19","cited_by_count":3,"area":null},{"id":"2511.21145","title":"TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models","created":"2025-11-26","cited_by_count":3,"area":"safety"},{"id":"2603.26676","title":"Evaluating Human-AI Safety: A Framework for Measuring Harmful Capability Uplift","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2507.11968","title":"Watch, Listen, Understand, Mislead: Tri-modal Adversarial Attacks on Short Videos for Content Appropriateness Evaluation","created":"2025-07-16","cited_by_count":2,"area":"mllm"},{"id":"2507.18053","title":"Resource Consumption Red-Teaming for Large Vision-Language Models","created":"2025-07-24","cited_by_count":2,"area":"mllm"},{"id":"2512.01037","title":"How Semantically Stable Are LLM Refusals? Measuring Confusion in Local Safety Boundaries","created":"2025-11-30","cited_by_count":2,"area":"alignment"},{"id":"2603.12510","title":"Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies","created":"2026-03-12","cited_by_count":2,"area":"vla"},{"id":"2605.11891","title":"Proteus: A Self-Evolving Red Team for Agent Skill Ecosystems","created":"2026-05-12","cited_by_count":2,"area":"agents"},{"id":"2609.07529","title":"CoER: Defending against Adaptive Indirect Prompt Injection via Adversarial Co-Evolution and Refinement","created":"2026-09-07","cited_by_count":2,"area":"agents"},{"id":"2411.16769","title":"Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting","created":"2024-11-25","cited_by_count":1,"area":"safety"},{"id":"2502.13207","title":"Thinking Outside the (Gray) Box: A Context-Based Score for Assessing Value and Originality in Neural Text Generation","created":"2025-02-18","cited_by_count":1,"area":"lr"},{"id":"2503.06253","title":"MAD-MAX: Modular And Diverse Malicious Attack MiXtures for Automated LLM Red Teaming","created":"2025-03-08","cited_by_count":1,"area":"safety"},{"id":"2506.04302","title":"RedRFT: A Light-Weight Benchmark for Reinforcement Fine-Tuning-Based Red Teaming","created":"2025-06-04","cited_by_count":1,"area":"safety"},{"id":"2507.00026","title":"RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models","created":"2025-06-17","cited_by_count":1,"area":"safety"},{"id":"2508.06111","title":"SKATE, a Scalable Tournament Eval: Weaker LLMs differentiate between stronger ones using verifiable challenges","created":"2025-08-08","cited_by_count":1,"area":null},{"id":"2510.08329","title":"AutoRed: A Free-form Adversarial Prompt Generation Framework for Automated Red Teaming","created":"2025-10-09","cited_by_count":1,"area":"safety"},{"id":"2512.07342","title":"PrivORL: Differentially Private Synthetic Dataset for Offline Reinforcement Learning","created":"2025-12-08","cited_by_count":1,"area":"diffusion"},{"id":"2604.04733","title":"Discovering Failure Modes in Vision-Language Models using RL","created":"2026-04-06","cited_by_count":1,"area":"lr"},{"id":"2605.00553","title":"Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance","created":"2026-05-01","cited_by_count":1,"area":"safety"},{"id":"2605.08427","title":"The Attacker in the Mirror: Breaking Self-Consistency in Safety via Anchored Bipolicy Self-Play","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2406.11785","title":"CELL your Model: Contrastive Explanations for Large Language Models","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2408.10474","title":"LeCov: Multi-level Testing Criteria for Large Language Models","created":"2024-08-20","cited_by_count":0,"area":null},{"id":"2504.13947","title":"From job titles to jawlines: Using context voids to study generative AI systems","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2506.18213","title":"A Conceptual Framework for AI Capability Evaluations","created":"2025-06-23","cited_by_count":0,"area":null},{"id":"2510.02194","title":"UpSafe$^\\circ$C: Upcycling for Controllable Safety in Large Language Models","created":"2025-10-02","cited_by_count":0,"area":"moe"},{"id":"2510.21184","title":"Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2605.07032","title":"A Systematic Investigation of RL-Jailbreaking in LLMs","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2606.05101","title":"FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors","created":"2026-06-03","cited_by_count":0,"area":"safety"},{"id":"2607.08837","title":"Prompt-Driven Exploration: Language as an Exploration Space for VLA Reinforcement Learning","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.11070","title":"MJ: Multi-turn LLM Jailbreaking via Decomposed Credit Assignment","created":"2026-07-13","cited_by_count":0,"area":"safety"},{"id":"2608.06933","title":"Ask-E: An Environment for Calibrated Question Generation","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.10171","title":"Generating Attacks for LLMs with GFlowNets","created":"2026-08-10","cited_by_count":0,"area":"safety"},{"id":"2609.34920","title":"RISE: Red-teaming via Iterative Strategy Evolution for Modern Text-to-Image Models","created":"2026-09-28","cited_by_count":0,"area":"safety"},{"id":"2610.05346","title":"Reflections and Fragments: Securing LLMs Against Sequential Mosaic Attacks","created":"2026-10-04","cited_by_count":0,"area":"safety"},{"id":"2610.12233","title":"ReSI: Recursive Safety Improvement toward Resistant and Resilient AI","created":"2026-10-08","cited_by_count":0,"area":"alignment"},{"id":"2610.13886","title":"X-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}