{"total":76,"rows":[{"id":"2407.09121","title":"Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training","created":"2024-07-12","cited_by_count":69,"area":null},{"id":"2502.19820","title":"Foot-In-The-Door: A Multi-turn Jailbreak for LLMs","created":"2025-02-27","cited_by_count":54,"area":"safety"},{"id":"2406.15481","title":"Code-Switching Red-Teaming: LLM Evaluation for Safety and Multilingual Understanding","created":"2024-06-17","cited_by_count":34,"area":"safety"},{"id":"2407.17915","title":"The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models","created":"2024-07-25","cited_by_count":20,"area":"agents"},{"id":"2502.09723","title":"QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language","created":"2025-02-13","cited_by_count":18,"area":"alignment"},{"id":"2505.20259","title":"Lifelong Safety Alignment for Language Models","created":"2025-05-26","cited_by_count":15,"area":"alignment"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2408.02509","title":"Black-Box Adversarial Attacks on LLM-Based Code Completion","created":"2024-08-05","cited_by_count":14,"area":null},{"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":"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":"2507.05248","title":"Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models","created":"2025-07-07","cited_by_count":10,"area":"safety"},{"id":"2507.22063","title":"RedCoder: Automated Multi-Turn Red Teaming for Code LLMs","created":"2025-06-25","cited_by_count":9,"area":"safety"},{"id":"2410.12999","title":"POROver: Improving Safety and Reducing Overrefusal in Large Language Models with Overgeneration and Preference Optimization","created":"2024-10-16","cited_by_count":8,"area":"alignment"},{"id":"2505.12060","title":"Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement","created":"2025-05-17","cited_by_count":8,"area":"safety"},{"id":"2507.11500","title":"ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning","created":"2025-07-14","cited_by_count":8,"area":"alignment"},{"id":"2502.15334","title":"Attention Eclipse: Manipulating Attention to Bypass LLM Safety-Alignment","created":"2025-02-21","cited_by_count":7,"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":"2510.01359","title":"Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks","created":"2025-10-01","cited_by_count":7,"area":"agents"},{"id":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2501.13677","title":"HumorReject: Decoupling LLM Safety from Refusal Prefix via A Little Humor","created":"2025-01-23","cited_by_count":6,"area":"safety"},{"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":"2503.17953","title":"Smoke and Mirrors: Jailbreaking LLM-based Code Generation via Implicit Malicious Prompts","created":"2025-03-23","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":"2410.08776","title":"FATS: A Prompt Injection Attack Utilizing Feign Security Agents with Deceptive Few-shots Learning","created":"2024-10-11","cited_by_count":4,"area":"agents"},{"id":"2411.01565","title":"SQL Injection Jailbreak: A Structural Disaster of Large Language Models","created":"2024-11-03","cited_by_count":4,"area":"safety"},{"id":"2503.24191","title":"When Grammar Guides the Attack: Uncovering Control-Plane Vulnerabilities in LLMs with Structured Output","created":"2025-03-31","cited_by_count":4,"area":"safety"},{"id":"2510.05025","title":"Imperceptible Jailbreaking against Large Language Models","created":"2025-10-06","cited_by_count":4,"area":"safety"},{"id":"2510.27087","title":"Characterizing Selective Refusal Bias in Large Language Models","created":"2025-10-31","cited_by_count":4,"area":"safety"},{"id":"2601.10543","title":"Defending Large Language Models Against Jailbreak Attacks via In-Decoding Safety-Awareness Probing","created":"2026-01-15","cited_by_count":4,"area":"safety"},{"id":"2605.30777","title":"What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code Assistants","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2510.15499","title":"HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment","created":"2025-10-17","cited_by_count":3,"area":"alignment"},{"id":"2601.03537","title":"STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules","created":"2026-01-07","cited_by_count":3,"area":"lr"},{"id":"2605.05058","title":"SoK: Robustness in Large Language Models against Jailbreak Attacks","created":"2026-05-06","cited_by_count":3,"area":"safety"},{"id":"2502.11853","title":"StructTransform: A Scalable Attack Surface for Safety-Aligned Large Language Models","created":"2025-02-17","cited_by_count":2,"area":"alignment"},{"id":"2506.12274","title":"InfoFlood: Jailbreaking Large Language Models with Information Overload","created":"2025-06-13","cited_by_count":2,"area":"safety"},{"id":"2509.11128","title":"ERIS: Evolutionary Real-world Interference Scheme for Jailbreaking Audio Large Models","created":"2025-09-14","cited_by_count":2,"area":"safety"},{"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":"2510.10281","title":"ArtPerception: ASCII Art-based Jailbreak on LLMs with Recognition Pre-test","created":"2025-10-11","cited_by_count":2,"area":"safety"},{"id":"2604.00310","title":"CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment","created":"2026-03-31","cited_by_count":2,"area":"alignment"},{"id":"2604.19461","title":"Involuntary In-Context Learning: Exploiting Few-Shot Pattern Completion to Bypass Safety Alignment in GPT-5.4","created":"2026-04-21","cited_by_count":2,"area":"alignment"},{"id":"2605.26158","title":"Furina: Fragmented Uncertainty-Driven Refusal Instability Attack","created":"2026-05-24","cited_by_count":2,"area":"alignment"},{"id":"2607.01250","title":"Structuring the Space of Sociotechnical Alignment","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2501.07959","title":"Self-Instruct Few-Shot Jailbreaking: Decompose the Attack into Pattern and Behavior Learning","created":"2025-01-14","cited_by_count":1,"area":"synth"},{"id":"2504.13052","title":"GraphAttack: Exploiting Representational Blindspots in LLM Safety Mechanisms","created":"2025-04-17","cited_by_count":1,"area":"safety"},{"id":"2508.00555","title":"Activation-Guided Local Editing for Jailbreaking Attacks","created":"2025-08-01","cited_by_count":1,"area":"safety"},{"id":"2508.10404","title":"Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation","created":"2025-08-14","cited_by_count":1,"area":"safety"},{"id":"2508.15526","title":"SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking","created":"2025-08-21","cited_by_count":1,"area":"agents"},{"id":"2511.02356","title":"ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs","created":"2025-11-04","cited_by_count":1,"area":"alignment"},{"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":"2511.19009","title":"Understanding and Mitigating Over-refusal for Large Language Models via Representation Intervention","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2512.21236","title":"Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking","created":"2025-12-24","cited_by_count":1,"area":"safety"},{"id":"2604.20930","title":"SafeRedirect: Defeating Internal Safety Collapse via Task-Completion Redirection in Frontier LLMs","created":"2026-04-22","cited_by_count":1,"area":"safety"},{"id":"2605.09070","title":"Single-Configuration Attack Success Rate Is Not Enough: Jailbreak Evaluations Should Report Distributional Attack Success","created":"2026-05-09","cited_by_count":1,"area":"safety"},{"id":"2606.16527","title":"DoubtProbe: Black-Box Jailbreak Defense via Structural Verification and Semantic Auditing","created":"2026-06-15","cited_by_count":1,"area":"safety"},{"id":"2609.21793","title":"CASCADE Against Jailbreaks: Combination Across Stages with Controlled Attack-Defense Evaluation","created":"2026-09-18","cited_by_count":1,"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":"2507.19743","title":"What Makes Code Generation Ethically Sourced?","created":"2025-07-26","cited_by_count":0,"area":null},{"id":"2508.15648","title":"SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Models","created":"2025-08-21","cited_by_count":0,"area":"safety"},{"id":"2510.17904","title":"BreakFun: Jailbreaking LLMs via Object Instantiation under Simulated Code Execution","created":"2025-10-19","cited_by_count":0,"area":"safety"},{"id":"2511.21569","title":"AI Identity Disclosure Under Professional Personas: A Gap Between Capacity and Consistency","created":"2025-11-26","cited_by_count":0,"area":null},{"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":"2604.24082","title":"Jailbreaking Frontier Foundation Models Through Intention Deception","created":"2026-04-27","cited_by_count":0,"area":"safety"},{"id":"2605.00236","title":"Attention Is Where You Attack","created":"2026-04-30","cited_by_count":0,"area":"alignment"},{"id":"2605.00974","title":"SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking","created":"2026-05-01","cited_by_count":0,"area":"alignment"},{"id":"2605.13411","title":"Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution","created":"2026-05-13","cited_by_count":0,"area":"safety"},{"id":"2605.24497","title":"Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"id":"2606.00686","title":"Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing","created":"2026-05-30","cited_by_count":0,"area":"moe"},{"id":"2607.00572","title":"HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment","created":"2026-07-01","cited_by_count":0,"area":"alignment"},{"id":"2607.03968","title":"Refused in Chat, Written in Code: Workflow-Level Jailbreak Construction in IDE Coding Agents","created":"2026-07-04","cited_by_count":0,"area":"agents"},{"id":"2608.01043","title":"Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks","created":"2026-08-02","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":"2609.02215","title":"ASCII Attack: Recontextualising Harmful Requests as Artistic Critique in Large Language Models","created":"2026-09-02","cited_by_count":0,"area":"alignment"},{"id":"2609.02414","title":"Before the Script, Set the Stage: How Worldview Simulation Amplifies Psychologically Grounded Persuasion in Multi-Turn Jailbreaking","created":"2026-09-02","cited_by_count":0,"area":"safety"},{"id":"2609.26174","title":"The Uncontrolled Variable: Vision-Language Model Refusal Responds to Image Presence in Ways Risk Cannot Explain","created":"2026-08-12","cited_by_count":0,"area":"mllm"},{"id":"2609.36657","title":"Constitutional adapters: Inference-time interventions for misalignment and misuse","created":"2026-09-29","cited_by_count":0,"area":"safety"},{"id":"2609.39902","title":"CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code Completion","created":"2026-09-30","cited_by_count":0,"area":"alignment"}],"next_cursor":null}