{"total":113,"rows":[{"id":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240,"area":"alignment"},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173,"area":"safety"},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151,"area":"safety"},{"id":"2503.03704","title":"Memory Injection Attacks on LLM Agents via Query-Only Interaction","created":"2025-03-05","cited_by_count":144,"area":"agents"},{"id":"2502.17420","title":"The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence","created":"2025-02-24","cited_by_count":115,"area":"alignment"},{"id":"2409.20089","title":"Robust LLM safeguarding via refusal feature adversarial training","created":"2024-09-30","cited_by_count":64,"area":null},{"id":"2406.05498","title":"SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner","created":"2024-06-08","cited_by_count":63,"area":"safety"},{"id":"2601.11893","title":"Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework","created":"2026-01-17","cited_by_count":54,"area":"agents"},{"id":"2406.09324","title":"Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs","created":"2024-06-13","cited_by_count":51,"area":"safety"},{"id":"2504.04022","title":"Rethinking Reflection in Pre-Training","created":"2025-04-05","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":"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":"2502.01633","title":"Adversarial Reasoning at Jailbreaking Time","created":"2025-02-03","cited_by_count":29,"area":"lr"},{"id":"2408.10682","title":"Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models","created":"2024-08-20","cited_by_count":27,"area":"safety"},{"id":"2406.06622","title":"Adversarial Tuning: Defending Against Jailbreak Attacks for LLMs","created":"2024-06-07","cited_by_count":26,"area":"safety"},{"id":"2506.14922","title":"FORTRESS: Frontier Risk Evaluation for National Security and Public Safety","created":"2025-06-17","cited_by_count":24,"area":"safety"},{"id":"2408.04585","title":"Towards Resilient and Efficient LLMs: A Comparative Study of Efficiency, Performance, and Adversarial Robustness","created":"2024-08-08","cited_by_count":22,"area":null},{"id":"2411.14033","title":"LLM-based Multi-Agent Systems: Techniques and Business Perspectives","created":"2024-11-21","cited_by_count":22,"area":"agents"},{"id":"2412.03597","title":"The Vulnerability of Language Model Benchmarks: Do They Accurately Reflect True LLM Performance?","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2505.16120","title":"LLM-Powered AI Agent Systems and Their Applications in Industry","created":"2025-05-22","cited_by_count":22,"area":"agents"},{"id":"2410.03523","title":"A Probabilistic Perspective on Unlearning and Alignment for Large Language Models","created":"2024-10-04","cited_by_count":21,"area":"alignment"},{"id":"2506.10597","title":"SoK: Evaluating Jailbreak Guardrails for Large Language Models","created":"2025-06-12","cited_by_count":21,"area":"alignment"},{"id":"2603.06594","title":"A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness","created":"2026-02-04","cited_by_count":20,"area":"safety"},{"id":"2410.01294","title":"Endless Jailbreaks with Bijection Learning","created":"2024-10-02","cited_by_count":19,"area":"safety"},{"id":"2503.02574","title":"LLM-Safety Evaluations Lack Robustness","created":"2025-03-04","cited_by_count":18,"area":"alignment"},{"id":"2502.13141","title":"UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models","created":"2025-02-18","cited_by_count":16,"area":"safety"},{"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":"2502.15865","title":"Standard Benchmarks Fail -- Auditing LLM Agents in Finance Must Prioritize Risk","created":"2025-02-21","cited_by_count":13,"area":"agents"},{"id":"2502.11455","title":"Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training","created":"2025-02-17","cited_by_count":12,"area":"alignment"},{"id":"2505.18658","title":"Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metrics","created":"2025-05-24","cited_by_count":12,"area":null},{"id":"2505.16947","title":"MixAT: Combining Continuous and Discrete Adversarial Training for LLMs","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2505.17406","title":"Robust Answers, Fragile Logic: Probing the Decoupling Hypothesis in LLM Reasoning","created":"2025-05-23","cited_by_count":11,"area":"lr"},{"id":"2512.12069","title":"Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring","created":"2025-12-12","cited_by_count":11,"area":"lr"},{"id":"2503.09241","title":"In-Context Defense in Computer Agents: An Empirical Study","created":"2025-03-12","cited_by_count":10,"area":"mllm"},{"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":"2502.09638","title":"Jailbreaking to Jailbreak","created":"2025-02-09","cited_by_count":9,"area":"safety"},{"id":"2506.01307","title":"Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models","created":"2025-06-02","cited_by_count":9,"area":"mllm"},{"id":"2502.11910","title":"Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives","created":"2025-02-17","cited_by_count":8,"area":null},{"id":"2505.14585","title":"Context Reasoner: Incentivizing Reasoning Capability for Contextualized Privacy and Safety Compliance via Reinforcement Learning","created":"2025-05-20","cited_by_count":8,"area":"lr"},{"id":"2506.11938","title":"Improving Large Language Model Safety with Contrastive Representation Learning","created":"2025-06-13","cited_by_count":8,"area":"mechinterp"},{"id":"2509.15202","title":"Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism via Probabilistically Ablating Refusal Direction","created":"2025-09-18","cited_by_count":8,"area":"alignment"},{"id":"2504.02458","title":"Retrieval-Augmented Purifier for Robust LLM-Empowered Recommendation","created":"2025-04-03","cited_by_count":7,"area":"rag"},{"id":"2505.24369","title":"Adversarial Preference Learning for Robust LLM Alignment","created":"2025-05-30","cited_by_count":7,"area":"alignment"},{"id":"2506.02442","title":"Should LLM Safety Be More Than Refusing Harmful Instructions?","created":"2025-06-03","cited_by_count":7,"area":"safety"},{"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":"2511.00203","title":"Diffusion LLMs are Natural Adversaries for any LLM","created":"2025-10-31","cited_by_count":7,"area":"safety"},{"id":"2512.05485","title":"TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations","created":"2025-12-05","cited_by_count":7,"area":"safety"},{"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":"2508.20737","title":"Rethinking Testing for LLM Applications: Characteristics, Challenges, and a Lightweight Interaction Protocol","created":"2025-08-28","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":"2502.00653","title":"Towards Robust Multimodal Large Language Models Against Jailbreak Attacks","created":"2025-02-02","cited_by_count":5,"area":"safety"},{"id":"2502.04643","title":"Confidence Elicitation: A New Attack Vector for Large Language Models","created":"2025-02-07","cited_by_count":5,"area":null},{"id":"2503.01345","title":"Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness","created":"2025-03-03","cited_by_count":5,"area":null},{"id":"2503.11185","title":"Bleeding Pathways: Vanishing Discriminability in LLM Hidden States Fuels Jailbreak Attacks","created":"2025-03-14","cited_by_count":5,"area":"safety"},{"id":"2505.09602","title":"Adversarial Suffix Filtering: a Defense Pipeline for LLMs","created":"2025-05-14","cited_by_count":5,"area":"safety"},{"id":"2510.15975","title":"Generative AI for Biosciences: Emerging Threats and Roadmap to Biosecurity","created":"2025-10-13","cited_by_count":5,"area":"safety"},{"id":"2504.17421","title":"Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks","created":"2025-04-24","cited_by_count":4,"area":null},{"id":"2508.13214","title":"Too Easily Fooled? Prompt Injection Breaks LLMs on Frustratingly Simple Multiple-Choice Questions","created":"2025-08-16","cited_by_count":4,"area":"safety"},{"id":"2511.19218","title":"Adversarial Attack-Defense Co-Evolution for LLM Safety Alignment via Tree-Group Dual-Aware Search and Optimization","created":"2025-11-24","cited_by_count":4,"area":"alignment"},{"id":"2604.08169","title":"Activation Steering for Aligned Open-ended Generation without Sacrificing Coherence","created":"2026-04-09","cited_by_count":4,"area":"safety"},{"id":"2501.16534","title":"Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs","created":"2025-01-27","cited_by_count":3,"area":"safety"},{"id":"2502.10487","title":"Fast Proxies for LLM Robustness Evaluation","created":"2025-02-14","cited_by_count":3,"area":"safety"},{"id":"2502.11863","title":"FedEAT: A Robustness Optimization Framework for Federated LLMs","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2503.17932","title":"STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models","created":"2025-03-23","cited_by_count":3,"area":"safety"},{"id":"2602.16729","title":"Intent Laundering: AI Safety Datasets Are Not What They Seem","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2606.05523","title":"CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning","created":"2026-06-04","cited_by_count":3,"area":"alignment"},{"id":"2406.13283","title":"Large-Scale Dataset Pruning in Adversarial Training through Data Importance Extrapolation","created":"2024-06-19","cited_by_count":2,"area":null},{"id":"2505.01315","title":"Helping Large Language Models Protect Themselves: An Enhanced Filtering and Summarization System","created":"2025-05-02","cited_by_count":2,"area":"safety"},{"id":"2506.07356","title":"Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks","created":"2025-06-09","cited_by_count":2,"area":"safety"},{"id":"2506.09010","title":"Effective Data Pruning through Score Extrapolation","created":"2025-06-10","cited_by_count":2,"area":null},{"id":"2507.10281","title":"Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence","created":"2025-07-14","cited_by_count":2,"area":"agents"},{"id":"2509.23362","title":"Dual-Space Smoothness for Robust and Balanced LLM Unlearning","created":"2025-09-27","cited_by_count":2,"area":"safety"},{"id":"2511.16229","title":"Q-MLLM: Vector Quantization for Robust Multimodal Large Language Model Security","created":"2025-11-20","cited_by_count":2,"area":"mllm"},{"id":"2602.16977","title":"Fail-Closed Alignment for Large Language Models","created":"2026-02-19","cited_by_count":2,"area":"alignment"},{"id":"2608.23959","title":"NeuronGuard: Robust LLM Safety Alignment via Ablation-Aware Safety Signal Redistribution","created":"2026-08-25","cited_by_count":2,"area":"alignment"},{"id":"2608.28327","title":"Layered LLM Defenses as an Ensemble: Access Tiers, Inference Cost, and the Measured Failure Correlation Between Defense Layers","created":"2026-08-28","cited_by_count":2,"area":null},{"id":"2412.13705","title":"Mitigating Adversarial Attacks in LLMs through Defensive Suffix Generation","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2502.16366","title":"A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens","created":"2025-02-22","cited_by_count":1,"area":null},{"id":"2602.09431","title":"Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models","created":"2026-02-10","cited_by_count":1,"area":"mllm"},{"id":"2603.04378","title":"Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization","created":"2026-03-04","cited_by_count":1,"area":"agents"},{"id":"2604.12817","title":"Understanding and Improving Continuous Adversarial Training for LLMs via In-context Learning Theory","created":"2026-04-14","cited_by_count":1,"area":"safety"},{"id":"2605.01605","title":"Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models","created":"2026-05-02","cited_by_count":1,"area":null},{"id":"2605.07977","title":"Self-Play Enhancement via Advantage-Weighted Refinement in Online Federated LLM Fine-Tuning with Real-Time Feedback","created":"2026-05-08","cited_by_count":1,"area":"synth"},{"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":"2605.08496","title":"Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms","created":"2026-05-08","cited_by_count":1,"area":"safety"},{"id":"2605.12813","title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2605.20519","title":"Codec-Robust Attacks on Audio LLMs","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2607.07918","title":"Efficient Safety Alignment of Language Models via Latent Personality Traits","created":"2026-07-08","cited_by_count":1,"area":"alignment"},{"id":"2607.14698","title":"Lights, Camera, Malfunction: When Illumination Robustness Leaves VLA Models Blind to Color","created":"2026-07-16","cited_by_count":1,"area":"vla"},{"id":"2506.22492","title":"Report on NSF Workshop on Science of Safe AI","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2509.06338","title":"Embedding Poisoning: Bypassing Safety Alignment via Embedding Semantic Shift","created":"2025-09-08","cited_by_count":0,"area":"alignment"},{"id":"2510.01929","title":"Inverse Language Modeling towards Robust and Grounded LLMs","created":"2025-10-02","cited_by_count":0,"area":null},{"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":"2512.04841","title":"SoK: a Comprehensive Causality Analysis Framework for Large Language Model Security","created":"2025-12-04","cited_by_count":0,"area":"safety"},{"id":"2601.16200","title":"Feature-Space Smoothing: Certified Robustness of Deep Representations","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2601.19487","title":"LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment","created":"2026-01-27","cited_by_count":0,"area":"safety"},{"id":"2602.00857","title":"Unifying Adversarial Robustness and Training Across Text Scoring Models","created":"2026-01-31","cited_by_count":0,"area":"alignment"},{"id":"2602.15238","title":"Closing the Distribution Gap in Adversarial Training for LLMs","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.05415","title":"Information Theoretic Adversarial Training of Large Language Models","created":"2026-05-06","cited_by_count":0,"area":"safety"}],"next_cursor":"100"}