{"total":80,"rows":[{"id":"2412.05934","title":"Heuristic-Induced Multimodal Risk Distribution Jailbreak Attack for Multimodal Large Language Models","created":"2024-12-08","cited_by_count":33,"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":"2503.16431","title":"OpenAI's Approach to External Red Teaming for AI Models and Systems","created":"2025-01-24","cited_by_count":28,"area":"safety"},{"id":"2501.13772","title":"Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models","created":"2025-01-23","cited_by_count":23,"area":"safety"},{"id":"2502.11090","title":"SafeDialBench: A Fine-Grained Safety Evaluation Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks","created":"2025-02-16","cited_by_count":23,"area":"safety"},{"id":"2509.02563","title":"DynaGuard: A Dynamic Guardian Model With User-Defined Policies","created":"2025-09-02","cited_by_count":19,"area":"safety"},{"id":"2502.21059","title":"FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowcharts","created":"2025-02-28","cited_by_count":18,"area":"safety"},{"id":"2508.07173","title":"Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models","created":"2025-08-10","cited_by_count":18,"area":"safety"},{"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":"2504.20472","title":"Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction","created":"2025-04-29","cited_by_count":16,"area":"safety"},{"id":"2506.16349","title":"Watermarking Autoregressive Image Generation","created":"2025-06-19","cited_by_count":16,"area":"safety"},{"id":"2509.24384","title":"HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment","created":"2025-09-29","cited_by_count":15,"area":"safety"},{"id":"2505.06493","title":"System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection","created":"2025-05-10","cited_by_count":14,"area":"safety"},{"id":"2511.10222","title":"Speech-Audio Compositional Attacks on Multimodal LLMs and Their Mitigation with SALMONN-Guard","created":"2025-11-13","cited_by_count":13,"area":"safety"},{"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":"2509.22292","title":"Jailbreaking on Text-to-Video Models via Scene Splitting Strategy","created":"2025-09-26","cited_by_count":12,"area":"safety"},{"id":"2411.11407","title":"The Dark Side of Trust: Authority Citation-Driven Jailbreak Attacks on Large Language Models","created":"2024-11-18","cited_by_count":10,"area":"safety"},{"id":"2501.18632","title":"Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare","created":"2025-01-27","cited_by_count":10,"area":"safety"},{"id":"2505.17601","title":"Revisiting Backdoor Attacks on LLMs: A Stealthy and Practical Poisoning Framework via Harmless Inputs","created":"2025-05-23","cited_by_count":10,"area":"safety"},{"id":"2504.16907","title":"BadVideo: Stealthy Backdoor Attack against Text-to-Video Generation","created":"2025-04-23","cited_by_count":9,"area":"safety"},{"id":"2505.23814","title":"Watermarking Without Standards Is Not AI Governance","created":"2025-05-27","cited_by_count":9,"area":"safety"},{"id":"2510.09694","title":"Kelp: A Streaming Safeguard for Large Models via Latent Dynamics-Guided Risk Detection","created":"2025-10-09","cited_by_count":9,"area":"safety"},{"id":"2511.04934","title":"Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding","created":"2025-11-07","cited_by_count":9,"area":"safety"},{"id":"2507.21134","title":"TRIDENT: Benchmarking LLM Safety in Finance, Medicine, and Law","created":"2025-07-22","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":"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":"2508.08211","title":"SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders","created":"2025-08-11","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":"2505.14368","title":"From ASR to ASP: Evaluating Prompt Attack Vulnerabilities Against Open-Source LLMs","created":"2025-05-20","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":"2505.18864","title":"Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework","created":"2025-05-24","cited_by_count":5,"area":"safety"},{"id":"2602.13597","title":"AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks","created":"2026-02-14","cited_by_count":5,"area":"safety"},{"id":"2503.01926","title":"Unnatural Languages Are Not Bugs but Features for LLMs","created":"2025-03-02","cited_by_count":4,"area":"safety"},{"id":"2504.14985","title":"aiXamine: Simplified LLM Safety and Security","created":"2025-04-21","cited_by_count":4,"area":"safety"},{"id":"2509.24675","title":"Understanding the Dilemma of Unlearning for Large Language Models","created":"2025-09-29","cited_by_count":4,"area":"safety"},{"id":"2510.02334","title":"Where Did It Go Wrong? Attributing Undesirable LLM Behaviors via Representation Gradient Tracing","created":"2025-09-26","cited_by_count":4,"area":"safety"},{"id":"2510.12119","title":"ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation","created":"2025-10-14","cited_by_count":4,"area":"safety"},{"id":"2510.18728","title":"HarmNet: A Framework for Adaptive Multi-Turn Jailbreak Attacks on Large Language Models","created":"2025-10-21","cited_by_count":4,"area":"safety"},{"id":"2511.13127","title":"SPARK: Jailbreaking T2V Models by Synergistically Prompting Auditory and Recontextualized Knowledge","created":"2025-11-17","cited_by_count":4,"area":"safety"},{"id":"2506.16792","title":"MIST: Jailbreaking Black-box Large Language Models via Iterative Semantic Tuning","created":"2025-06-20","cited_by_count":3,"area":"safety"},{"id":"2510.05310","title":"RAG Makes Guardrails Unsafe? Investigating Robustness of Guardrails under RAG-style Contexts","created":"2025-10-06","cited_by_count":3,"area":"safety"},{"id":"2510.17277","title":"PolyJailbreak: Cross-Modal Jailbreaking Attacks on Black-Box Multimodal LLMs","created":"2025-10-20","cited_by_count":3,"area":"safety"},{"id":"2511.16278","title":"\"To Survive, I Must Defect\": Jailbreaking LLMs via the Game-Theory Scenarios","created":"2025-11-20","cited_by_count":3,"area":"safety"},{"id":"2601.05339","title":"Multi-turn Jailbreaking Attack in Multi-Modal Large Language Models","created":"2026-01-08","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":"2605.08778","title":"Not All Turns Matter: Credit Assignment for Multi-Turn Jailbreaking","created":"2026-05-09","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":"2505.16643","title":"From Evaluation to Defense: Advancing Safety in Video Large Language Models","created":"2025-05-22","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":"2512.02711","title":"CREST: Universal Safety Guardrails Through Cluster-Guided Cross-Lingual Transfer","created":"2025-12-02","cited_by_count":2,"area":"safety"},{"id":"2505.00843","title":"OET: Optimization-based prompt injection Evaluation Toolkit","created":"2025-05-01","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":"2507.22160","title":"Strategic Deflection: Defending LLMs from Logit Manipulation","created":"2025-07-29","cited_by_count":1,"area":"safety"},{"id":"2510.13727","title":"From Refusal to Recovery: A Control-Theoretic Approach to Generative AI Guardrails","created":"2025-10-15","cited_by_count":1,"area":"safety"},{"id":"2511.08367","title":"Why Does Weak-OOD Help? A Further Step Towards Understanding Jailbreaking VLMs","created":"2025-11-11","cited_by_count":1,"area":"safety"},{"id":"2602.05401","title":"BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models","created":"2026-02-05","cited_by_count":1,"area":"safety"},{"id":"2602.06440","title":"TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking","created":"2026-02-06","cited_by_count":1,"area":"safety"},{"id":"2603.23269","title":"Not All Tokens Are Created Equal: Query-Efficient Jailbreak Fuzzing for LLMs","created":"2026-03-24","cited_by_count":1,"area":"safety"},{"id":"2605.01761","title":"TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks","created":"2026-05-03","cited_by_count":1,"area":"safety"},{"id":"2606.26036","title":"Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning","created":"2026-06-24","cited_by_count":1,"area":"safety"},{"id":"2607.18056","title":"An Early Warning of Emerging Biosecurity Risks in Frontier LLMs","created":"2026-07-20","cited_by_count":1,"area":"safety"},{"id":"2505.18672","title":"Concept Concentration for Faithful Representation Intervention","created":"2025-05-24","cited_by_count":0,"area":"safety"},{"id":"2506.11253","title":"Lifting Data-Tracing Machine Unlearning to Knowledge-Tracing for Foundation Models","created":"2025-06-12","cited_by_count":0,"area":"safety"},{"id":"2509.23381","title":"Guard Vector: Beyond English LLM Guardrails with Task-Vector Composition and Streaming-Aware Prefix SFT","created":"2025-09-27","cited_by_count":0,"area":"safety"},{"id":"2510.21214","title":"Enhanced MLLM Black-Box Jailbreaking Attacks and Defenses","created":"2025-10-24","cited_by_count":0,"area":"safety"},{"id":"2512.13325","title":"Security and Detectability Analysis of Unicode Text Watermarking Methods against Large Language Models","created":"2025-12-15","cited_by_count":0,"area":"safety"},{"id":"2601.21682","title":"FIT to Forget: Robust Continual Unlearning for Large Language Models","created":"2026-01-29","cited_by_count":0,"area":"safety"},{"id":"2604.20833","title":"AVISE: Framework for Evaluating the Security of AI Systems","created":"2026-04-22","cited_by_count":0,"area":"safety"},{"id":"2605.05687","title":"DataDignity: Training Data Attribution for Large Language Models","created":"2026-05-07","cited_by_count":0,"area":"safety"},{"id":"2605.10764","title":"Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization","created":"2026-05-11","cited_by_count":0,"area":"safety"},{"id":"2605.26409","title":"Jailbreak susceptibility prediction and mitigation via the behavioral geometry of models","created":"2026-05-26","cited_by_count":0,"area":"safety"},{"id":"2606.00150","title":"Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models","created":"2026-05-29","cited_by_count":0,"area":"safety"},{"id":"2606.13737","title":"FreoStream:Enhancing Stream Guardrails via Future-Aware Reasoning and Safety-Aligned Optimization","created":"2026-06-11","cited_by_count":0,"area":"safety"},{"id":"2606.19660","title":"A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots","created":"2026-06-17","cited_by_count":0,"area":"safety"},{"id":"2606.26936","title":"Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries","created":"2026-06-25","cited_by_count":0,"area":"safety"},{"id":"2608.17360","title":"Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call Budgets","created":"2026-08-18","cited_by_count":0,"area":"safety"},{"id":"2608.30362","title":"Will the User Ever Know? Covert Indirect Prompt Injection Attacks on Tool-Using LLM Agents","created":"2026-08-31","cited_by_count":0,"area":"safety"},{"id":"2609.06966","title":"MOLE: Detecting Insider Threats in AI Agents","created":"2026-09-07","cited_by_count":0,"area":"safety"},{"id":"2609.07216","title":"The Price of Consistency: Exploiting Visual Anchors for Multimodal Jailbreaking in Video Generation","created":"2026-09-07","cited_by_count":0,"area":"safety"}],"next_cursor":null}