{"total":86,"rows":[{"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":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80,"area":"safety"},{"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":"2410.21965","title":"SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Types","created":"2024-10-29","cited_by_count":60,"area":"safety"},{"id":"2502.07557","title":"JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation","created":"2025-02-11","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":"2407.16667","title":"RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent","created":"2024-07-23","cited_by_count":44,"area":"agents"},{"id":"2407.20242","title":"BadRobot: Jailbreaking Embodied LLM Agents in the Physical World","created":"2024-07-16","cited_by_count":43,"area":"agents"},{"id":"2406.09519","title":"Talking Heads: Understanding Inter-layer Communication in Transformer Language Models","created":"2024-06-13","cited_by_count":41,"area":null},{"id":"2410.15236","title":"Jailbreaking and Mitigation of Vulnerabilities in Large Language Models","created":"2024-10-20","cited_by_count":34,"area":"safety"},{"id":"2406.09321","title":"JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models","created":"2024-06-13","cited_by_count":31,"area":"safety"},{"id":"2409.08045","title":"Unleashing Worms and Extracting Data: Escalating the Outcome of Attacks against RAG-based Inference in Scale and Severity Using Jailbreaking","created":"2024-09-12","cited_by_count":30,"area":"safety"},{"id":"2410.14826","title":"SPRIG: Improving Large Language Model Performance by System Prompt Optimization","created":"2024-10-18","cited_by_count":29,"area":null},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2504.09420","title":"SaRO: Enhancing LLM Safety through Reasoning-based Alignment","created":"2025-04-13","cited_by_count":26,"area":"lr"},{"id":"2408.04811","title":"h4rm3l: A language for Composable Jailbreak Attack Synthesis","created":"2024-08-09","cited_by_count":24,"area":"safety"},{"id":"2411.07404","title":"Controllable Context Sensitivity and the Knob Behind It","created":"2024-11-11","cited_by_count":23,"area":null},{"id":"2407.07342","title":"Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture","created":"2024-07-10","cited_by_count":22,"area":"alignment"},{"id":"2509.11864","title":"NeuroStrike: Neuron-Level Attacks on Aligned LLMs","created":"2025-09-15","cited_by_count":22,"area":"alignment"},{"id":"2409.14866","title":"PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs","created":"2024-09-23","cited_by_count":21,"area":"safety"},{"id":"2508.12538","title":"MCPXKIT: The Unified Toolkit for Analyzing Model Context Protocol Security","created":"2025-08-18","cited_by_count":21,"area":"agents"},{"id":"2504.15512","title":"T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models","created":"2025-04-22","cited_by_count":18,"area":"safety"},{"id":"2511.15304","title":"Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models","created":"2025-11-19","cited_by_count":15,"area":"safety"},{"id":"2406.03805","title":"AutoJailbreak: Exploring Jailbreak Attacks and Defenses through a Dependency Lens","created":"2024-06-06","cited_by_count":14,"area":"safety"},{"id":"2503.08195","title":"Dialogue Injection Attack: Jailbreaking LLMs through Context Manipulation","created":"2025-03-11","cited_by_count":14,"area":"safety"},{"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":"2506.15170","title":"From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem","created":"2025-06-18","cited_by_count":12,"area":"agents"},{"id":"2504.21038","title":"Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models","created":"2025-04-28","cited_by_count":10,"area":"safety"},{"id":"2505.12981","title":"From Assistants to Adversaries: Exploring the Security Risks of Mobile LLM Agents","created":"2025-05-19","cited_by_count":10,"area":"agents"},{"id":"2508.05775","title":"Guardians and Offenders: A Survey on Harmful Content Generation and Safety Mitigation of LLM","created":"2025-08-07","cited_by_count":9,"area":"alignment"},{"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":"2412.08099","title":"Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting","created":"2024-12-11","cited_by_count":6,"area":null},{"id":"2603.01291","title":"JailNewsBench: Multi-Lingual and Regional Benchmark for Fake News Generation under Jailbreak Attacks","created":"2026-03-01","cited_by_count":6,"area":"safety"},{"id":"2605.06812","title":"Towards Security-Auditable LLM Agents: A Unified Graph Representation","created":"2026-05-07","cited_by_count":6,"area":"agents"},{"id":"2410.09569","title":"Are You Human? An Adversarial Benchmark to Expose LLMs","created":"2024-10-12","cited_by_count":5,"area":null},{"id":"2504.08104","title":"Geneshift: Impact of different scenario shift on Jailbreaking LLM","created":"2025-04-10","cited_by_count":5,"area":"safety"},{"id":"2509.18557","title":"LLMZ+: Contextual Prompt Whitelist Principles for Agentic LLMs","created":"2025-09-23","cited_by_count":5,"area":"agents"},{"id":"2510.13893","title":"Guarding the Guardrails: A Taxonomy-Driven Approach to Jailbreak Detection","created":"2025-10-14","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":"2412.10807","title":"Towards Action Hijacking of Large Language Model-based Agent","created":"2024-12-14","cited_by_count":4,"area":"agents"},{"id":"2602.21223","title":"Measuring Pragmatic Influence in Large Language Model Instructions","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2501.16534","title":"Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs","created":"2025-01-27","cited_by_count":3,"area":"safety"},{"id":"2504.21700","title":"XBreaking: Understanding how LLMs security alignment can be broken","created":"2025-04-30","cited_by_count":3,"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":"2602.16729","title":"Intent Laundering: AI Safety Datasets Are Not What They Seem","created":"2026-02-17","cited_by_count":3,"area":null},{"id":"2604.18487","title":"Adversarial Humanities Benchmark: Results on Stylistic Robustness in Frontier Model Safety","created":"2026-04-20","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":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2507.00239","title":"Linearly Decoding Refused Knowledge in Aligned Language Models","created":"2025-06-30","cited_by_count":2,"area":"alignment"},{"id":"2510.01223","title":"Jailbreaking LLMs via Semantically Relevant Nested Scenarios with Targeted Toxic Knowledge","created":"2025-09-22","cited_by_count":2,"area":"safety"},{"id":"2512.10687","title":"Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users","created":"2025-12-11","cited_by_count":2,"area":"lr"},{"id":"2605.06901","title":"Reflections and New Directions for Human-Centered Large Language Models","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2411.08884","title":"Quantifying Risk Propensities of Large Language Models: Ethical Focus and Bias Detection through Role-Play","created":"2024-10-26","cited_by_count":1,"area":null},{"id":"2412.16555","title":"Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models","created":"2024-12-21","cited_by_count":1,"area":"mllm"},{"id":"2502.01436","title":"Towards Safer Chatbots: Automated Policy Compliance Evaluation of Custom GPTs","created":"2025-02-03","cited_by_count":1,"area":null},{"id":"2505.11557","title":"AC-LoRA: (Almost) Training-Free Access Control-Aware Multi-Modal LLMs","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2603.13847","title":"Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs","created":"2026-03-14","cited_by_count":1,"area":"safety"},{"id":"2603.21975","title":"SecureBreak -- A dataset towards safe and secure models","created":"2026-03-23","cited_by_count":1,"area":"safety"},{"id":"2604.01444","title":"Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models","created":"2026-04-01","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":"2608.01117","title":"SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks","created":"2026-08-02","cited_by_count":1,"area":"safety"},{"id":"2609.07037","title":"Disentangling Steering Vectors","created":"2026-09-07","cited_by_count":1,"area":"mechinterp"},{"id":"2411.16730","title":"\"Moralized\" Multi-Step Jailbreak Prompts: Black-Box Testing of Guardrails in Large Language Models for Verbal Attacks","created":"2024-11-23","cited_by_count":0,"area":"safety"},{"id":"2506.11125","title":"ASRJam: Human-Friendly AI Speech Jamming to Prevent Automated Phone Scams","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2506.23930","title":"Leveraging the Potential of Prompt Engineering for Hate Speech Detection in Low-Resource Languages","created":"2025-06-30","cited_by_count":0,"area":null},{"id":"2508.00602","title":"LeakSealer: A Semisupervised Defense for LLMs Against Prompt Injection and Leakage Attacks","created":"2025-08-01","cited_by_count":0,"area":"safety"},{"id":"2510.01259","title":"In AI Sweet Harmony: Sociopragmatic Guardrail Bypasses and Evaluation-Awareness in OpenAI gpt-oss-20b","created":"2025-09-25","cited_by_count":0,"area":"safety"},{"id":"2601.14528","title":"LLM Security and Safety: Insights from Homotopy-Inspired Prompt Obfuscation","created":"2026-01-20","cited_by_count":0,"area":null},{"id":"2601.18998","title":"Malicious Repurposing of Open Science Artefacts by Using Large Language Models","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.05484","title":"Clouding the Mirror: Stealthy Prompt Injection Attacks Targeting LLM-based Phishing Detection","created":"2026-02-05","cited_by_count":0,"area":"safety"},{"id":"2602.06630","title":"TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking","created":"2026-02-06","cited_by_count":0,"area":"safety"},{"id":"2602.08062","title":"Efficient and Adaptable Detection of Malicious LLM Prompts via Bootstrap Aggregation","created":"2026-02-08","cited_by_count":0,"area":"synth"},{"id":"2603.20122","title":"Evolving Jailbreaks: Automated Multi-Objective Long-Tail Attacks on Large Language Models","created":"2026-03-20","cited_by_count":0,"area":"safety"},{"id":"2604.00014","title":"Disentangling Prompt Element Level Risk Factors for Hallucinations and Omissions in Mental Health LLM Responses","created":"2026-03-10","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":"2604.06954","title":"Compression as an Adversarial Amplifier Through Decision Space Reduction","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2604.08846","title":"Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2605.07414","title":"OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing","created":"2026-05-08","cited_by_count":0,"area":"agents"},{"id":"2605.11229","title":"Comment and Control: Hijacking Agentic Workflows via Context-Grounded Evolution","created":"2026-05-11","cited_by_count":0,"area":"agents"},{"id":"2605.11664","title":"Safety Context Injection: Inference-Time Safety Alignment via Static Filtering and Agentic Analysis","created":"2026-05-12","cited_by_count":0,"area":"agents"},{"id":"2605.12128","title":"Metaphor Is Not All Attention Needs","created":"2026-05-12","cited_by_count":0,"area":"safety"},{"id":"2605.26999","title":"Prompt Injection Detection is Regime-Dependent: A Deployment-Aware Evaluation with Interpretable Structural Signals","created":"2026-05-26","cited_by_count":0,"area":"safety"},{"id":"2606.10989","title":"Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model Unlearning","created":"2026-06-09","cited_by_count":0,"area":"safety"},{"id":"2608.07535","title":"Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards","created":"2026-07-27","cited_by_count":0,"area":"mllm"},{"id":"2609.19989","title":"Benchmarking LLM Compliance with China AI Generated Content Regulations","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.03857","title":"Beware EviLLM: Enabling Vulnerability Injection via Large Language Models","created":"2026-10-02","cited_by_count":0,"area":"safety"}],"next_cursor":null}