{"total":29,"rows":[{"id":"2506.09956","title":"LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge","created":"2025-06-11","cited_by_count":21,"area":"safety"},{"id":"2509.22067","title":"The Rogue Scalpel: Activation Steering Compromises LLM Safety","created":"2025-09-26","cited_by_count":21,"area":"safety"},{"id":"2508.07173","title":"Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models","created":"2025-08-10","cited_by_count":18,"area":"safety"},{"id":"2601.18076","title":"Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming","created":"2026-01-26","cited_by_count":15,"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":"2505.16934","title":"In-Context Watermarks for Large Language Models","created":"2025-05-22","cited_by_count":10,"area":"safety"},{"id":"2511.04934","title":"Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding","created":"2025-11-07","cited_by_count":9,"area":"safety"},{"id":"2605.06161","title":"Beyond Accuracy: Policy Invariance as a Reliability Test for LLM Safety Judges","created":"2026-05-07","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":"2507.04531","title":"DP-Fusion: Token-Level Differentially Private Inference for Large Language Models","created":"2025-07-06","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":"2509.24675","title":"Understanding the Dilemma of Unlearning for Large Language Models","created":"2025-09-29","cited_by_count":4,"area":"safety"},{"id":"2508.16889","title":"ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn Jailbreaks","created":"2025-08-23","cited_by_count":3,"area":"safety"},{"id":"2509.15260","title":"Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore's Low-Resource Languages","created":"2025-09-18","cited_by_count":2,"area":"safety"},{"id":"2602.03787","title":"Inference-time Unlearning Using Conformal Prediction","created":"2026-02-03","cited_by_count":2,"area":"safety"},{"id":"2504.06577","title":"Bypassing Safety Guardrails in LLMs Using Humor","created":"2025-04-09","cited_by_count":1,"area":"safety"},{"id":"2507.03620","title":"Is It Time To Treat Prompts As Code? A Multi-Use Case Study For Prompt Optimization Using DSPy","created":"2025-07-04","cited_by_count":1,"area":"safety"},{"id":"2511.12217","title":"AlignTree: Efficient Defense Against LLM Jailbreak Attacks","created":"2025-11-15","cited_by_count":1,"area":"safety"},{"id":"2602.05401","title":"BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models","created":"2026-02-05","cited_by_count":1,"area":"safety"},{"id":"2603.19247","title":"When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language Models","created":"2026-02-21","cited_by_count":1,"area":"safety"},{"id":"2605.06652","title":"When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels","created":"2026-05-07","cited_by_count":1,"area":"safety"},{"id":"2606.16751","title":"Automated jailbreak attack targeting multiple defense strategies","created":"2026-06-15","cited_by_count":1,"area":"safety"},{"id":"2601.21682","title":"FIT to Forget: Robust Continual Unlearning for Large Language Models","created":"2026-01-29","cited_by_count":0,"area":"safety"},{"id":"2602.21831","title":"A Multi-Turn Framework for Evaluating AI Misuse in Fraud and Cybercrime Scenarios","created":"2026-02-25","cited_by_count":0,"area":"safety"},{"id":"2604.24700","title":"Green Shielding: A User-Centric Approach Towards Trustworthy AI","created":"2026-04-27","cited_by_count":0,"area":"safety"},{"id":"2605.04116","title":"Membership Inference Attacks for Retrieval Based In-Context Learning for Document Question Answering","created":"2026-05-05","cited_by_count":0,"area":"safety"},{"id":"2605.05116","title":"On the Hardness of Junking LLMs","created":"2026-05-06","cited_by_count":0,"area":"safety"},{"id":"2605.28734","title":"Code as a Weapon: A Consensus-Labeled Prompt Bank for Measuring Coding-Model Compliance with Malicious-Code Requests","created":"2026-05-27","cited_by_count":0,"area":"safety"},{"id":"2606.26936","title":"Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries","created":"2026-06-25","cited_by_count":0,"area":"safety"}],"next_cursor":null}