{"list":"other","total":52,"rows":[{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672},{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567},{"id":"2309.10253","title":"GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts","created":"2023-09-19","cited_by_count":560},{"id":"2305.13860","title":"Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study","created":"2023-05-23","cited_by_count":498},{"id":"2507.01006","title":"GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning","created":"2025-07-01","cited_by_count":466},{"id":"2310.06387","title":"Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations","created":"2023-10-10","cited_by_count":431},{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367},{"id":"2310.06474","title":"Multilingual Jailbreak Challenges in Large Language Models","created":"2023-10-10","cited_by_count":240},{"id":"2310.11986","title":"Sociotechnical Safety Evaluation of Generative AI Systems","created":"2023-10-18","cited_by_count":157},{"id":"2510.14276","title":"Qwen3Guard Technical Report","created":"2025-10-16","cited_by_count":155},{"id":"2408.15221","title":"LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet","created":"2024-08-27","cited_by_count":151},{"id":"2504.13203","title":"X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents","created":"2025-04-15","cited_by_count":125},{"id":"2402.16914","title":"DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers","created":"2024-02-25","cited_by_count":101},{"id":"2402.09154","title":"Attacking Large Language Models with Projected Gradient Descent","created":"2024-02-14","cited_by_count":94},{"id":"2410.10700","title":"LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts","created":"2024-10-14","cited_by_count":86},{"id":"2410.02832","title":"FlipAttack: Jailbreak LLMs via Flipping","created":"2024-10-02","cited_by_count":80},{"id":"2405.05610","title":"Chain of Attack: a Semantic-Driven Contextual Multi-Turn attacker for LLM","created":"2024-05-09","cited_by_count":77},{"id":"2502.11054","title":"Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models","created":"2025-02-16","cited_by_count":64},{"id":"2508.05668","title":"A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges","created":"2025-08-03","cited_by_count":62},{"id":"2403.12171","title":"EasyJailbreak: A Unified Framework for Jailbreaking Large Language Models","created":"2024-03-18","cited_by_count":60},{"id":"2403.08424","title":"Distract Large Language Models for Automatic Jailbreak Attack","created":"2024-03-13","cited_by_count":45},{"id":"2407.16667","title":"RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent","created":"2024-07-23","cited_by_count":44},{"id":"2503.15754","title":"AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration","created":"2025-03-20","cited_by_count":43},{"id":"2503.05021","title":"Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety","created":"2025-03-06","cited_by_count":39},{"id":"2410.02828","title":"PyRIT: A Framework for Security Risk Identification and Red Teaming in Generative AI System","created":"2024-10-01","cited_by_count":31},{"id":"2408.04811","title":"h4rm3l: A language for Composable Jailbreak Attack Synthesis","created":"2024-08-09","cited_by_count":24},{"id":"2509.19870","title":"FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models","created":"2025-09-24","cited_by_count":21},{"id":"2507.18576","title":"SafeWork-R1: Coevolving Safety and Intelligence under the AI-45$^{\\circ}$ Law","created":"2025-07-24","cited_by_count":14},{"id":"2503.16508","title":"Conversational AI as a Coding Assistant: Understanding Programmers' Interactions with and Expectations from Large Language Models for Coding","created":"2025-03-14","cited_by_count":11},{"id":"2512.06589","title":"OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation","created":"2025-12-06","cited_by_count":11},{"id":"2504.21038","title":"Prefill-level Jailbreak: A Black-Box Risk Analysis of Large Language Models","created":"2025-04-28","cited_by_count":10},{"id":"1911.03677","title":"A Reinforced Generation of Adversarial Examples for Neural Machine Translation","created":"2019-11-09","cited_by_count":9},{"id":"2509.26100","title":"AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models","created":"2025-09-30","cited_by_count":9},{"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},{"id":"2501.00055","title":"LLM-Virus: Evolutionary Jailbreak Attack on Large Language Models","created":"2024-12-28","cited_by_count":7},{"id":"2512.05485","title":"TeleAI-Safety: A comprehensive LLM jailbreaking benchmark towards attacks, defenses, and evaluations","created":"2025-12-05","cited_by_count":7},{"id":"2506.15751","title":"Sysformer: Safeguarding Frozen Large Language Models with Adaptive System Prompts","created":"2025-06-18","cited_by_count":5},{"id":"2508.03864","title":"Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety","created":"2025-08-05","cited_by_count":4},{"id":"2510.05025","title":"Imperceptible Jailbreaking against Large Language Models","created":"2025-10-06","cited_by_count":4},{"id":"2406.11285","title":"Self and Cross-Model Distillation for LLMs: Effective Methods for Refusal Pattern Alignment","created":"2024-06-17","cited_by_count":3},{"id":"2510.05379","title":"AutoDAN-Reasoning: Enhancing Strategies Exploration based Jailbreak Attacks with Test-Time Scaling","created":"2025-10-06","cited_by_count":3},{"id":"2409.17458","title":"RED QUEEN: Safeguarding Large Language Models against Concealed Multi-Turn Jailbreaking","created":"2024-09-26","cited_by_count":2}],"next_cursor":null}