{"total":100,"rows":[{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496,"area":"safety"},{"id":"2407.04295","title":"Jailbreak Attacks and Defenses Against Large Language Models: A Survey","created":"2024-07-05","cited_by_count":230,"area":"safety"},{"id":"2402.02207","title":"Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models","created":"2024-02-03","cited_by_count":167,"area":"safety"},{"id":"2501.09004","title":"Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails","created":"2025-01-15","cited_by_count":132,"area":"safety"},{"id":"2507.11878","title":"LLMs Encode Harmfulness and Refusal Separately","created":"2025-07-16","cited_by_count":88,"area":"safety"},{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2404.05399","title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","created":"2024-04-08","cited_by_count":77,"area":"safety"},{"id":"2406.18682","title":"The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm","created":"2024-06-26","cited_by_count":70,"area":"safety"},{"id":"2402.09091","title":"Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues","created":"2024-02-14","cited_by_count":68,"area":"safety"},{"id":"2402.06255","title":"Fight Back Against Jailbreaking via Prompt Adversarial Tuning","created":"2024-02-09","cited_by_count":67,"area":"safety"},{"id":"2406.17092","title":"BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models","created":"2024-06-24","cited_by_count":58,"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":"2406.09324","title":"Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs","created":"2024-06-13","cited_by_count":51,"area":"safety"},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"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":"2407.02855","title":"From Theft to Bomb-Making: The Ripple Effect of Unlearning in Defending Against Jailbreak Attacks","created":"2024-07-03","cited_by_count":29,"area":"safety"},{"id":"2506.10949","title":"Monitoring Decomposition Attacks in LLMs with Lightweight Sequential Monitors","created":"2025-06-12","cited_by_count":25,"area":"safety"},{"id":"2408.04811","title":"h4rm3l: A language for Composable Jailbreak Attack Synthesis","created":"2024-08-09","cited_by_count":24,"area":"safety"},{"id":"2505.06843","title":"Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety","created":"2025-05-11","cited_by_count":22,"area":"safety"},{"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":"2401.10647","title":"Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models","created":"2024-01-19","cited_by_count":20,"area":"safety"},{"id":"2505.17568","title":"JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models","created":"2025-05-23","cited_by_count":16,"area":"safety"},{"id":"2410.03857","title":"You Know What I'm Saying: Jailbreak Attack via Implicit Reference","created":"2024-10-04","cited_by_count":14,"area":"safety"},{"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":"2506.15606","title":"LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning","created":"2025-06-18","cited_by_count":12,"area":"safety"},{"id":"2502.05911","title":"GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation","created":"2025-02-09","cited_by_count":11,"area":"safety"},{"id":"2505.16559","title":"CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning","created":"2025-05-22","cited_by_count":11,"area":"safety"},{"id":"2408.10668","title":"Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation","created":"2024-08-20","cited_by_count":10,"area":"safety"},{"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":"2505.12186","title":"Self-Destructive Language Model","created":"2025-05-18","cited_by_count":10,"area":"safety"},{"id":"2402.13926","title":"Large Language Models are Vulnerable to Bait-and-Switch Attacks for Generating Harmful Content","created":"2024-02-21","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":"2409.15361","title":"Multitask Mayhem: Unveiling and Mitigating Safety Gaps in LLMs Fine-tuning","created":"2024-09-18","cited_by_count":8,"area":"safety"},{"id":"2505.19773","title":"What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMs","created":"2025-05-26","cited_by_count":8,"area":"safety"},{"id":"2510.07835","title":"MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation","created":"2025-10-09","cited_by_count":8,"area":"safety"},{"id":"2505.23856","title":"OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities","created":"2025-05-29","cited_by_count":7,"area":"safety"},{"id":"2509.21947","title":"Active Attacks: Red-teaming LLMs via Adaptive Environments","created":"2025-09-26","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":"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":"2410.02916","title":"LLM Safeguard is a Double-Edged Sword: Exploiting False Positives for Denial-of-Service Attacks","created":"2024-10-03","cited_by_count":6,"area":"safety"},{"id":"2502.19537","title":"No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms","created":"2025-02-26","cited_by_count":6,"area":"safety"},{"id":"2506.07452","title":"When Style Breaks Safety: Defending LLMs Against Superficial Style Alignment","created":"2025-06-09","cited_by_count":6,"area":"safety"},{"id":"2512.16602","title":"Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics","created":"2025-12-18","cited_by_count":6,"area":"safety"},{"id":"2603.00498","title":"Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence","created":"2026-02-28","cited_by_count":6,"area":"safety"},{"id":"2411.19335","title":"PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning","created":"2024-11-28","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":"2601.00588","title":"CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns","created":"2026-01-02","cited_by_count":5,"area":"safety"},{"id":"2505.13500","title":"Noise Injection Systemically Degrades Large Language Model Safety Guardrails","created":"2025-05-16","cited_by_count":4,"area":"safety"},{"id":"2508.12072","title":"Mitigating Jailbreaks with Intent-Aware LLMs","created":"2025-08-16","cited_by_count":4,"area":"safety"},{"id":"2508.15182","title":"SafeLLM: Unlearning Harmful Outputs from Large Language Models against Jailbreak Attacks","created":"2025-08-21","cited_by_count":4,"area":"safety"},{"id":"2510.01088","title":"Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense","created":"2025-10-01","cited_by_count":4,"area":"safety"},{"id":"2410.02220","title":"Data to Defense: The Role of Curation in Customizing LLMs Against Jailbreaking Attacks","created":"2024-10-03","cited_by_count":3,"area":"safety"},{"id":"2411.16642","title":"Preventing Jailbreak Prompts as Malicious Tools for Cybercriminals: A Cyber Defense Perspective","created":"2024-11-25","cited_by_count":3,"area":"safety"},{"id":"2504.12321","title":"AttentionDefense: Leveraging System Prompt Attention for Explainable Defense Against Novel Jailbreaks","created":"2025-04-10","cited_by_count":3,"area":"safety"},{"id":"2601.03594","title":"Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense","created":"2026-01-07","cited_by_count":3,"area":"safety"},{"id":"2601.03600","title":"ALERT: Zero-shot LLM Jailbreak Detection via Internal Discrepancy Amplification","created":"2026-01-07","cited_by_count":3,"area":"safety"},{"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":"2603.03323","title":"Discern Truth from Falsehood: Reducing Over-Refusal via Contrastive Refinement","created":"2026-02-10","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":"2605.11002","title":"MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks","created":"2026-05-10","cited_by_count":3,"area":"safety"},{"id":"2502.14486","title":"How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigation","created":"2025-02-20","cited_by_count":2,"area":"safety"},{"id":"2502.19883","title":"Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models","created":"2025-02-27","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":"2508.09190","title":"Multi-Level Safety Continual Projection for Fine-Tuned Large Language Models without Retraining","created":"2025-08-08","cited_by_count":2,"area":"safety"},{"id":"2510.01342","title":"Fine-Tuning Jailbreaks under Highly Constrained Black-Box Settings: A Three-Pronged Approach","created":"2025-10-01","cited_by_count":2,"area":"safety"},{"id":"2510.07775","title":"The Unintended Trade-off of AI Alignment:Balancing Hallucination Mitigation and Safety in LLMs","created":"2025-10-09","cited_by_count":2,"area":"safety"},{"id":"2601.22620","title":"Layer-wise Swapping for Generalizable Multilingual Safety","created":"2026-01-30","cited_by_count":2,"area":"safety"},{"id":"2603.20206","title":"Enhancing Safety of Large Language Models via Embedding Space Separation","created":"2026-03-01","cited_by_count":2,"area":"safety"},{"id":"2604.09222","title":"GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking","created":"2026-04-10","cited_by_count":2,"area":"safety"},{"id":"2501.11183","title":"Can Safety Fine-Tuning Be More Principled? Lessons Learned from Cybersecurity","created":"2025-01-19","cited_by_count":1,"area":"safety"},{"id":"2512.14751","title":"One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs","created":"2025-12-14","cited_by_count":1,"area":"safety"},{"id":"2601.12460","title":"TrojanPraise: Jailbreak LLMs via Benign Fine-Tuning","created":"2026-01-18","cited_by_count":1,"area":"safety"},{"id":"2603.24857","title":"AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective","created":"2026-03-25","cited_by_count":1,"area":"safety"},{"id":"2603.28817","title":"GUARD-SLM: Token Activation-Based Defense Against Jailbreak Attacks for Small Language Models","created":"2026-03-28","cited_by_count":1,"area":"safety"},{"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":"2605.01034","title":"A Theoretical Game of Attacks via Compositional Skills","created":"2026-05-01","cited_by_count":1,"area":"safety"},{"id":"2605.25073","title":"Security in the Fine-Tuning Lifecycle of Large Language Models: Threats, Defenses,Evaluation, and Future Directions","created":"2026-05-24","cited_by_count":1,"area":"safety"},{"id":"2605.26954","title":"AlbanianLLMSafety: A Safety Evaluation Dataset for Large Language Models in Albanian","created":"2026-05-26","cited_by_count":1,"area":"safety"},{"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":"2609.25049","title":"Mitigating LLM Over-Refusal via Dynamic Semantic Routing Calibration","created":"2026-09-06","cited_by_count":1,"area":"safety"},{"id":"2609.26185","title":"Dynamic Deep Prompt Optimization for Defending Against Jailbreak Attacks on LLMs","created":"2026-08-10","cited_by_count":1,"area":"safety"},{"id":"2406.11682","title":"Knowledge-to-Jailbreak: Investigating Knowledge-driven Jailbreaking Attacks for Large Language Models","created":"2024-06-17","cited_by_count":0,"area":"safety"},{"id":"2503.16740","title":"Automated Harmfulness Testing for Code Large Language Models","created":"2025-03-20","cited_by_count":0,"area":"safety"},{"id":"2505.09974","title":"Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data","created":"2025-05-15","cited_by_count":0,"area":"safety"},{"id":"2505.11835","title":"Multilingual Collaborative Defense for Large Language Models","created":"2025-05-17","cited_by_count":0,"area":"safety"},{"id":"2506.00062","title":"SafeCOMM: A Study on Safety Degradation in Fine-Tuned Telecom Large Language Models","created":"2025-05-29","cited_by_count":0,"area":"safety"},{"id":"2511.18581","title":"TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization","created":"2025-11-23","cited_by_count":0,"area":"safety"},{"id":"2512.08185","title":"A Practical Framework for Evaluating Medical AI Security: Reproducible Assessment of Jailbreaking and Privacy Vulnerabilities Across Clinical Specialties","created":"2025-12-09","cited_by_count":0,"area":"safety"},{"id":"2605.21539","title":"DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models","created":"2026-05-20","cited_by_count":0,"area":"safety"},{"id":"2605.24550","title":"Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models","created":"2026-05-23","cited_by_count":0,"area":"safety"},{"id":"2606.04612","title":"Hybrid Adversarial Defence for Natural Language Understanding Tasks","created":"2026-06-03","cited_by_count":0,"area":"safety"},{"id":"2606.05614","title":"Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack","created":"2026-06-04","cited_by_count":0,"area":"safety"},{"id":"2606.23375","title":"Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts","created":"2026-06-22","cited_by_count":0,"area":"safety"},{"id":"2606.28525","title":"A Gravitational Interpretation of Safety Reversion under Fine-Tuning","created":"2026-06-26","cited_by_count":0,"area":"safety"},{"id":"2607.19894","title":"Defense Against LLM Backdoors using Critical Neuron Isolation Pruning","created":"2026-07-22","cited_by_count":0,"area":"safety"},{"id":"2608.13304","title":"Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety","created":"2026-08-13","cited_by_count":0,"area":"safety"},{"id":"2608.26506","title":"A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model Families","created":"2026-08-27","cited_by_count":0,"area":"safety"},{"id":"2609.00790","title":"RISA: Response Inspection and Selective Actions for Refusal Calibration in Large Language Models","created":"2026-09-01","cited_by_count":0,"area":"safety"},{"id":"2610.10276","title":"PatchBench: Measuring Collateral Damage in Activation Patching","created":"2026-10-07","cited_by_count":0,"area":"safety"}],"next_cursor":null}