{"total":68,"rows":[{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651,"area":"safety"},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026,"area":"safety"},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672,"area":"safety"},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560,"area":"safety"},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509,"area":"safety"},{"id":"2311.08268","title":"A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily","created":"2023-11-14","cited_by_count":259,"area":"safety"},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186,"area":"safety"},{"id":"2401.17263","title":"Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks","created":"2024-01-30","cited_by_count":156,"area":"safety"},{"id":"2404.16873","title":"AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs","created":"2024-04-21","cited_by_count":156,"area":"safety"},{"id":"2402.02309","title":"Jailbreaking Attack against Multimodal Large Language Model","created":"2024-02-04","cited_by_count":135,"area":"safety"},{"id":"2306.09442","title":"Explore, Establish, Exploit: Red Teaming Language Models from Scratch","created":"2023-06-15","cited_by_count":114,"area":"safety"},{"id":"2402.18104","title":"Making Them Ask and Answer: Jailbreaking Large Language Models in Few Queries via Disguise and Reconstruction","created":"2024-02-28","cited_by_count":107,"area":"safety"},{"id":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80,"area":"safety"},{"id":"2304.12298","title":"BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT","created":"2023-02-21","cited_by_count":76,"area":"safety"},{"id":"2406.10794","title":"Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis","created":"2024-06-16","cited_by_count":64,"area":"safety"},{"id":"2310.15851","title":"Self-Guard: Empower the LLM to Safeguard Itself","created":"2023-10-24","cited_by_count":54,"area":"safety"},{"id":"2401.06824","title":"Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective","created":"2024-01-12","cited_by_count":48,"area":"safety"},{"id":"2311.15766","title":"Knowledge Unlearning for LLMs: Tasks, Methods, and Challenges","created":"2023-11-27","cited_by_count":38,"area":"safety"},{"id":"2406.09289","title":"Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models","created":"2024-06-13","cited_by_count":37,"area":"safety"},{"id":"2402.12991","title":"TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification","created":"2024-02-20","cited_by_count":36,"area":"safety"},{"id":"2505.04806","title":"Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs","created":"2025-05-07","cited_by_count":34,"area":"safety"},{"id":"2309.13322","title":"From Text to Source: Results in Detecting Large Language Model-Generated Content","created":"2023-09-23","cited_by_count":26,"area":"safety"},{"id":"2309.11830","title":"Goal-Oriented Prompt Attack and Safety Evaluation for LLMs","created":"2023-09-21","cited_by_count":24,"area":"safety"},{"id":"2410.14827","title":"Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment","created":"2024-10-18","cited_by_count":21,"area":"safety"},{"id":"2407.00869","title":"Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks","created":"2024-07-01","cited_by_count":19,"area":"safety"},{"id":"2405.09113","title":"Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization","created":"2024-05-15","cited_by_count":18,"area":"safety"},{"id":"2601.02671","title":"Extracting books from production language models","created":"2026-01-06","cited_by_count":17,"area":"safety"},{"id":"2311.05074","title":"GRASP: A Disagreement Analysis Framework to Assess Group Associations in Perspectives","created":"2023-11-09","cited_by_count":16,"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":"2506.07891","title":"Video Unlearning via Low-Rank Refusal Vector","created":"2025-06-09","cited_by_count":13,"area":"safety"},{"id":"2309.14054","title":"Adapt then Unlearn: Exploring Parameter Space Semantics for Unlearning in Generative Adversarial Networks","created":"2023-09-25","cited_by_count":11,"area":"safety"},{"id":"2403.14988","title":"Risk and Response in Large Language Models: Evaluating Key Threat Categories","created":"2024-03-22","cited_by_count":10,"area":"safety"},{"id":"2501.19202","title":"Improving LLM Unlearning Robustness via Random Perturbations","created":"2025-01-31","cited_by_count":9,"area":"safety"},{"id":"2408.14853","title":"Atoxia: Red-teaming Large Language Models with Target Toxic Answers","created":"2024-08-27","cited_by_count":7,"area":"safety"},{"id":"2304.14364","title":"CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants","created":"2023-04-27","cited_by_count":5,"area":"safety"},{"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":"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":"2310.00892","title":"No Offense Taken: Eliciting Offensiveness from Language Models","created":"2023-10-02","cited_by_count":3,"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":"2506.17231","title":"Efficient and Stealthy Jailbreak Attacks via Adversarial Prompt Distillation from LLMs to SLMs","created":"2025-05-26","cited_by_count":3,"area":"safety"},{"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":"2404.19048","title":"A Framework for Real-time Safeguarding the Text Generation of Large Language Model","created":"2024-04-29","cited_by_count":2,"area":"safety"},{"id":"2410.13236","title":"SPIN: Self-Supervised Prompt INjection","created":"2024-10-17","cited_by_count":2,"area":"safety"},{"id":"2502.01154","title":"Jailbreaking with Universal Multi-Prompts","created":"2025-02-03","cited_by_count":2,"area":"safety"},{"id":"2508.16484","title":"HAMSA: Hijacking Aligned Compact Models via Stealthy Automation","created":"2025-08-22","cited_by_count":2,"area":"safety"},{"id":"2510.00125","title":"Direct Token Optimization: A Self-contained Approach to Large Language Model Unlearning","created":"2025-09-30","cited_by_count":2,"area":"safety"},{"id":"2510.10271","title":"MetaBreak: Jailbreaking Online LLM Services via Special Token Manipulation","created":"2025-10-11","cited_by_count":2,"area":"safety"},{"id":"2602.18782","title":"MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs","created":"2026-02-21","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":"2505.24252","title":"A Reward-driven Automated Webshell Malicious-code Generator for Red-teaming","created":"2025-05-30","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":"2512.21110","title":"Beyond Context: Large Language Models' Failure to Grasp Users' Intent","created":"2025-12-24","cited_by_count":1,"area":"safety"},{"id":"2601.02670","title":"Break Me If You Can: Self-Jailbreaking of Aligned LLMs via Lexical Insertion Prompting","created":"2026-01-06","cited_by_count":1,"area":"safety"},{"id":"2604.15780","title":"Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs","created":"2026-04-17","cited_by_count":1,"area":"safety"},{"id":"2503.12339","title":"A Closer Look at Adversarial Suffix Learning for Jailbreaking LLMs: Augmented Adversarial Trigger Learning","created":"2025-03-16","cited_by_count":0,"area":"safety"},{"id":"2512.03047","title":"Entropy-Based Measurement of Value Drift and Alignment Work in Large Language Models","created":"2025-11-19","cited_by_count":0,"area":"safety"},{"id":"2512.08131","title":"Universal Adversarial Suffixes for Language Models Using Reinforcement Learning with Calibrated Reward","created":"2025-12-09","cited_by_count":0,"area":"safety"},{"id":"2605.10582","title":"Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing","created":"2026-05-11","cited_by_count":0,"area":"safety"},{"id":"2605.10611","title":"Re-Triggering Safeguards within LLMs for Jailbreak Detection","created":"2026-05-11","cited_by_count":0,"area":"safety"},{"id":"2605.12128","title":"Metaphor Is Not All Attention Needs","created":"2026-05-12","cited_by_count":0,"area":"safety"},{"id":"2605.19321","title":"Exploring and Developing a Pre-Model Safeguard with Draft Models","created":"2026-05-19","cited_by_count":0,"area":"safety"},{"id":"2605.29629","title":"Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures","created":"2026-05-28","cited_by_count":0,"area":"safety"},{"id":"2605.30919","title":"De-attribute to Forget for LLM Unlearning","created":"2026-05-29","cited_by_count":0,"area":"safety"},{"id":"2606.00003","title":"Learning from Mistakes: Can LLM Self-Recover after Misalignment?","created":"2026-03-25","cited_by_count":0,"area":"safety"},{"id":"2606.15788","title":"GAS-Leak-LLM: Genetic Algorithm-Based Suffix Optimization for Black-Box LLM Jailbreaking","created":"2026-06-14","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":"2609.09553","title":"Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning","created":"2026-09-09","cited_by_count":0,"area":"safety"}],"next_cursor":null}