{"list":"other","total":75,"rows":[{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104},{"id":"1608.04644","title":"Towards Evaluating the Robustness of Neural Networks","created":"2016-08-16","cited_by_count":2998},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2003.01690","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","created":"2020-03-03","cited_by_count":1451},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2312.06674","title":"Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations","created":"2023-12-07","cited_by_count":1207},{"id":"2404.07972","title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","created":"2024-04-11","cited_by_count":1195},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"2310.13548","title":"Towards Understanding Sycophancy in Language Models","created":"2023-10-20","cited_by_count":1040},{"id":"2407.16741","title":"OpenHands: An Open Platform for AI Software Developers as Generalist Agents","created":"2024-07-23","cited_by_count":1002},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"2212.09251","title":"Discovering Language Model Behaviors with Model-Written Evaluations","created":"2022-12-19","cited_by_count":836},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672},{"id":"1708.03999","title":"ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models","created":"2017-08-14","cited_by_count":666},{"id":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"2401.01614","title":"GPT-4V(ision) is a Generalist Web Agent, if Grounded","created":"2024-01-03","cited_by_count":563},{"id":"2406.05946","title":"Safety Alignment Should Be Made More Than Just a Few Tokens Deep","created":"2024-06-10","cited_by_count":472},{"id":"2505.06120","title":"LLMs Get Lost In Multi-Turn Conversation","created":"2025-05-09","cited_by_count":429},{"id":"2407.18901","title":"AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents","created":"2024-07-26","cited_by_count":401},{"id":"2404.01833","title":"Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack","created":"2024-04-02","cited_by_count":390},{"id":"2503.11926","title":"Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation","created":"2025-03-14","cited_by_count":384},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"2412.16339","title":"Deliberative Alignment: Reasoning Enables Safer Language Models","created":"2024-12-20","cited_by_count":308},{"id":"2407.21772","title":"ShieldGemma: Generative AI Content Moderation Based on Gemma","created":"2024-07-31","cited_by_count":243},{"id":"2406.14598","title":"SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal","created":"2024-06-20","cited_by_count":240},{"id":"2409.08264","title":"Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale","created":"2024-09-12","cited_by_count":223},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"2302.04638","title":"Better Diffusion Models Further Improve Adversarial Training","created":"2023-02-09","cited_by_count":208},{"id":"2307.08715","title":"MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbots","created":"2023-07-16","cited_by_count":183},{"id":"2501.18837","title":"Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming","created":"2025-01-31","cited_by_count":181},{"id":"2404.05719","title":"Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs","created":"2024-04-08","cited_by_count":176},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173},{"id":"2403.04783","title":"AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks","created":"2024-03-02","cited_by_count":145},{"id":"2404.05993","title":"AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts","created":"2024-04-09","cited_by_count":136},{"id":"2404.03648","title":"AutoWebGLM: A Large Language Model-based Web Navigating Agent","created":"2024-04-04","cited_by_count":130},{"id":"2411.02391","title":"Attacking Vision-Language Computer Agents via Pop-ups","created":"2024-11-04","cited_by_count":116},{"id":"2409.03215","title":"xLAM: A Family of Large Action Models to Empower AI Agent Systems","created":"2024-09-05","cited_by_count":111},{"id":"2502.12893","title":"H-CoT: Hijacking the Chain-of-Thought Safety Reasoning Mechanism to Jailbreak Large Reasoning Models, Including OpenAI o1/o3, DeepSeek-R1, and Gemini 2.0 Flash Thinking","created":"2025-02-18","cited_by_count":99},{"id":"2409.18169","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","created":"2024-09-26","cited_by_count":90},{"id":"2410.16464","title":"Beyond Browsing: API-Based Web Agents","created":"2024-10-21","cited_by_count":78},{"id":"2406.11200","title":"AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoning","created":"2024-06-17","cited_by_count":72},{"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},{"id":"2407.05965","title":"T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models","created":"2024-07-08","cited_by_count":66},{"id":"2410.13886","title":"Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents","created":"2024-10-11","cited_by_count":65},{"id":"2504.03767","title":"MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits","created":"2025-04-02","cited_by_count":63},{"id":"2504.11281","title":"The Obvious Invisible Threat: LLM-Powered GUI Agents' Vulnerability to Fine-Print Injections","created":"2025-04-15","cited_by_count":59},{"id":"2502.08586","title":"Commercial LLM Agents Are Already Vulnerable to Simple Yet Dangerous Attacks","created":"2025-02-12","cited_by_count":49},{"id":"2502.15806","title":"A Mousetrap: Fooling Large Reasoning Models for Jailbreak with Chain of Iterative Chaos","created":"2025-02-19","cited_by_count":43},{"id":"1612.06299","title":"Simple Black-Box Adversarial Perturbations for Deep Networks","created":"2016-12-19","cited_by_count":42},{"id":"2404.09349","title":"Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies","created":"2024-04-14","cited_by_count":38},{"id":"2311.00117","title":"BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B","created":"2023-10-31","cited_by_count":36},{"id":"2505.11154","title":"MPMA: Preference Manipulation Attack Against Model Context Protocol","created":"2025-05-16","cited_by_count":34},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32},{"id":"2309.11359","title":"Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learning","created":"2023-09-20","cited_by_count":31},{"id":"2504.01094","title":"Multilingual and Multi-Accent Jailbreaking of Audio LLMs","created":"2025-04-01","cited_by_count":31},{"id":"2410.16950","title":"Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In","created":"2024-10-22","cited_by_count":22},{"id":"2505.06843","title":"Benign Samples Matter! Fine-tuning On Outlier Benign Samples Severely Breaks Safety","created":"2025-05-11","cited_by_count":22},{"id":"2503.06550","title":"BingoGuard: LLM Content Moderation Tools with Risk Levels","created":"2025-03-09","cited_by_count":21},{"id":"2505.06679","title":"T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks","created":"2025-05-10","cited_by_count":21},{"id":"2501.14940","title":"CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models","created":"2025-01-24","cited_by_count":20},{"id":"2505.14103","title":"AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models","created":"2025-05-20","cited_by_count":18},{"id":"2404.11027","title":"Empowering Large Language Models on Robotic Manipulation with Affordance Prompting","created":"2024-04-17","cited_by_count":17},{"id":"2411.07494","title":"Rapid Response: Mitigating LLM Jailbreaks with a Few Examples","created":"2024-11-12","cited_by_count":16},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15},{"id":"2503.03911","title":"Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis","created":"2025-03-05","cited_by_count":9},{"id":"2504.10277","title":"RealHarm: A Collection of Real-World Language Model Application Failures","created":"2025-04-14","cited_by_count":8},{"id":"2505.16241","title":"Three Minds, One Legend: Jailbreak Large Reasoning Model with Adaptive Stacked Ciphers","created":"2025-05-22","cited_by_count":8},{"id":"2405.17670","title":"Deployment of Large Language Models to Control Mobile Robots at the Edge","created":"2024-05-27","cited_by_count":2},{"id":"2504.21769","title":"LLM-based Interactive Imitation Learning for Robotic Manipulation","created":"2025-04-30","cited_by_count":2}],"next_cursor":null}