{"total":56,"rows":[{"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":"2411.11296","title":"Steering Language Model Refusal with Sparse Autoencoders","created":"2024-11-18","cited_by_count":95,"area":"mechinterp"},{"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":"2411.18688","title":"Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment","created":"2024-11-27","cited_by_count":44,"area":"lr"},{"id":"2509.13782","title":"Who is Introducing the Failure? Automatically Attributing Failures of Multi-Agent Systems via Spectrum Analysis","created":"2025-09-17","cited_by_count":33,"area":"agents"},{"id":"2405.16229","title":"No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks","created":"2024-05-25","cited_by_count":29,"area":"alignment"},{"id":"2504.09420","title":"SaRO: Enhancing LLM Safety through Reasoning-based Alignment","created":"2025-04-13","cited_by_count":26,"area":"lr"},{"id":"2412.10321","title":"AdvPrefix: An Objective for Nuanced LLM Jailbreaks","created":"2024-12-13","cited_by_count":25,"area":"safety"},{"id":"2407.07342","title":"Multilingual Blending: LLM Safety Alignment Evaluation with Language Mixture","created":"2024-07-10","cited_by_count":22,"area":"alignment"},{"id":"2405.13068","title":"Uncovering Logit Suppression Vulnerabilities in LLM Safety Alignment","created":"2024-05-20","cited_by_count":18,"area":"alignment"},{"id":"2410.19160","title":"Adversarial Attacks on Large Language Models Using Regularized Relaxation","created":"2024-10-24","cited_by_count":12,"area":null},{"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":"2406.14393","title":"Jailbreaking as a Reward Misspecification Problem","created":"2024-06-20","cited_by_count":11,"area":"alignment"},{"id":"2409.19381","title":"HYBRIDMIND: Meta Selection of Natural Language and Symbolic Language for Enhanced LLM Reasoning","created":"2024-09-28","cited_by_count":11,"area":"lr"},{"id":"2506.07524","title":"TAI3: Testing Agent Integrity in Interpreting User Intent","created":"2025-06-09","cited_by_count":9,"area":"agents"},{"id":"2602.08621","title":"Sparse Models, Sparse Safety: Unsafe Routes in Mixture-of-Experts LLMs","created":"2026-02-09","cited_by_count":9,"area":"moe"},{"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":"2510.07835","title":"MetaDefense: Defending Finetuning-based Jailbreak Attack Before and During Generation","created":"2025-10-09","cited_by_count":8,"area":"safety"},{"id":"2501.03266","title":"LLM Content Moderation and User Satisfaction: Evidence from Response Refusals in Chatbot Arena","created":"2025-01-04","cited_by_count":6,"area":"safety"},{"id":"2502.18504","title":"TurboFuzzLLM: Turbocharging Mutation-based Fuzzing for Effectively Jailbreaking Large Language Models in Practice","created":"2025-02-21","cited_by_count":6,"area":"safety"},{"id":"2510.09871","title":"CoBia: Constructed Conversations Can Trigger Otherwise Concealed Societal Biases in LLMs","created":"2025-10-10","cited_by_count":5,"area":"safety"},{"id":"2510.10161","title":"Large Language Model Sourcing: A Survey","created":"2025-10-11","cited_by_count":5,"area":null},{"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":"2407.00075","title":"Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference","created":"2024-06-21","cited_by_count":4,"area":"safety"},{"id":"2412.05232","title":"LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds","created":"2024-12-06","cited_by_count":4,"area":"safety"},{"id":"2512.23881","title":"Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack","created":"2025-12-29","cited_by_count":4,"area":"lr"},{"id":"2408.08464","title":"$\\textit{MMJ-Bench}$: A Comprehensive Study on Jailbreak Attacks and Defenses for Multimodal Large Language Models","created":"2024-08-16","cited_by_count":3,"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":"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":"2510.02999","title":"NonTextual Target Attack","created":"2025-10-03","cited_by_count":3,"area":"safety"},{"id":"2510.21190","title":"The Trojan Example: Jailbreaking LLMs through Template Filling and Unsafety Reasoning","created":"2025-10-24","cited_by_count":3,"area":"alignment"},{"id":"2602.13547","title":"AISA: Awakening Intrinsic Safety Awareness in Large Language Models against Jailbreak Attacks","created":"2026-02-14","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":"2603.27332","title":"Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models","created":"2026-03-28","cited_by_count":2,"area":null},{"id":"2410.04454","title":"Inner-Probe: Discovering Copyright-related Data Generation in LLM Architecture","created":"2024-10-06","cited_by_count":1,"area":null},{"id":"2506.18543","title":"SoK: A Comprehensive Security Analysis of Jailbreak Resilience in GPT and DeepSeek Models","created":"2025-06-23","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":"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":"2604.11309","title":"The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems","created":"2026-04-13","cited_by_count":1,"area":"safety"},{"id":"2604.11666","title":"Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind","created":"2026-04-13","cited_by_count":1,"area":"agents"},{"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":"2504.13947","title":"From job titles to jawlines: Using context voids to study generative AI systems","created":"2025-04-16","cited_by_count":0,"area":null},{"id":"2506.06391","title":"From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law","created":"2025-06-05","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":"2511.13548","title":"ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Models","created":"2025-11-17","cited_by_count":0,"area":"alignment"},{"id":"2603.06025","title":"Sensitivity-Aware Retrieval-Augmented Intent Clarification","created":"2026-03-06","cited_by_count":0,"area":"rag"},{"id":"2603.21697","title":"Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models","created":"2026-03-23","cited_by_count":0,"area":"lr"},{"id":"2605.07399","title":"GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability Optimization","created":"2026-05-08","cited_by_count":0,"area":"mllm"},{"id":"2605.14750","title":"EVA: Editing for Versatile Alignment against Jailbreaks","created":"2026-05-14","cited_by_count":0,"area":"mllm"},{"id":"2605.20286","title":"Adaptive Probe-based Steering for Robust LLM Jailbreaking","created":"2026-05-19","cited_by_count":0,"area":"safety"},{"id":"2605.21674","title":"Adversarial Reframing: A Framework for Targeted Generation in Language Models","created":"2026-05-20","cited_by_count":0,"area":"safety"},{"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":"2608.05409","title":"Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment","created":"2026-08-05","cited_by_count":0,"area":"alignment"},{"id":"2609.02172","title":"Breadth Beats Depth: Improving GCG-Based Jailbreak Optimization with Breadth-Oriented Suffix Search","created":"2026-09-02","cited_by_count":0,"area":"safety"},{"id":"2609.10594","title":"An Empirical Measurement of Jailbreaking Evaluators","created":"2026-09-07","cited_by_count":0,"area":"safety"}],"next_cursor":null}