{"total":22,"rows":[{"id":"2402.06255","title":"Fight Back Against Jailbreaking via Prompt Adversarial Tuning","created":"2024-02-09","cited_by_count":67,"area":"safety"},{"id":"2307.13808","title":"Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy","created":"2023-07-25","cited_by_count":50,"area":"safety"},{"id":"2412.08608","title":"AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models","created":"2024-12-11","cited_by_count":38,"area":"safety"},{"id":"2410.22284","title":"Embedding-based classifiers can detect prompt injection attacks","created":"2024-10-29","cited_by_count":27,"area":"safety"},{"id":"2409.08087","title":"Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks","created":"2024-09-12","cited_by_count":26,"area":"safety"},{"id":"2502.18851","title":"Marking Code Without Breaking It: Code Watermarking for Detecting LLM-Generated Code","created":"2025-02-26","cited_by_count":10,"area":"safety"},{"id":"2503.21730","title":"Effective Skill Unlearning through Intervention and Abstention","created":"2025-03-27","cited_by_count":9,"area":"safety"},{"id":"2402.07518","title":"Efficient and Universal Watermarking for LLM-Generated Code Detection","created":"2024-02-12","cited_by_count":6,"area":"safety"},{"id":"2511.07863","title":"WaterMod: Modular Token-Rank Partitioning for Probability-Balanced LLM Watermarking","created":"2025-11-11","cited_by_count":6,"area":"safety"},{"id":"2407.08956","title":"Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss","created":"2024-07-12","cited_by_count":5,"area":"safety"},{"id":"2501.17501","title":"How Much Do Code Language Models Remember? An Investigation on Data Extraction Attacks before and after Fine-tuning","created":"2025-01-29","cited_by_count":3,"area":"safety"},{"id":"2509.03117","title":"PromptCOS: Towards Content-only System Prompt Copyright Auditing for LLMs","created":"2025-09-03","cited_by_count":3,"area":"safety"},{"id":"2604.09544","title":"Large Language Models Generate Harmful Responses Using a Distinct Mechanism, Shared Across Harm Types","created":"2026-04-10","cited_by_count":3,"area":"safety"},{"id":"2408.01354","title":"MCGMark: An Encodable and Robust Online Watermark for Tracing LLM-Generated Malicious Code","created":"2024-08-02","cited_by_count":1,"area":"safety"},{"id":"2502.18810","title":"Holistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removal","created":"2025-02-26","cited_by_count":1,"area":"safety"},{"id":"2502.02068","title":"Robust and Secure Code Watermarking for Large Language Models via ML/Crypto Codesign","created":"2025-02-04","cited_by_count":0,"area":"safety"},{"id":"2511.07480","title":"KG-DF: A Black-box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs","created":"2025-11-09","cited_by_count":0,"area":"safety"},{"id":"2605.01047","title":"LLM Ghostbusters: Surgical Package Hallucination Suppression via Adaptive Unlearning","created":"2026-05-01","cited_by_count":0,"area":"safety"},{"id":"2607.20852","title":"Code Monitor Red Teaming for Public-Test-Passing Code","created":"2026-07-23","cited_by_count":0,"area":"safety"},{"id":"2608.14855","title":"What to Forget in Unlearning? Forget Set Curation for Language Models","created":"2026-08-14","cited_by_count":0,"area":"safety"},{"id":"2609.20129","title":"Local Sparsity Enables Unsupervised LLM Safety Detection","created":"2026-09-17","cited_by_count":0,"area":"safety"},{"id":"2609.35913","title":"UNBIND: UNlearning By INference-time Directional Steering for Code LLMs","created":"2026-09-28","cited_by_count":0,"area":"safety"}],"next_cursor":null}