{"total":34,"rows":[{"id":"2310.06987","title":"Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation","created":"2023-10-10","cited_by_count":451,"area":"safety"},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285,"area":"safety"},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258,"area":"safety"},{"id":"2402.08983","title":"SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding","created":"2024-02-14","cited_by_count":247,"area":"safety"},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2308.00113","title":"Three Bricks to Consolidate Watermarks for Large Language Models","created":"2023-07-26","cited_by_count":84,"area":"safety"},{"id":"2403.00867","title":"Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes","created":"2024-03-01","cited_by_count":74,"area":"safety"},{"id":"2402.14904","title":"Watermarking Makes Language Models Radioactive","created":"2024-02-22","cited_by_count":58,"area":"safety"},{"id":"2404.02062","title":"Digital Forgetting in Large Language Models: A Survey of Unlearning Methods","created":"2024-04-02","cited_by_count":40,"area":"safety"},{"id":"2402.05813","title":"Selective Forgetting: Advancing Machine Unlearning Techniques and Evaluation in Language Models","created":"2024-02-08","cited_by_count":39,"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":"2406.12257","title":"CleanGen: Mitigating Backdoor Attacks for Generation Tasks in Large Language Models","created":"2024-06-18","cited_by_count":24,"area":"safety"},{"id":"2310.11237","title":"Watermarking LLMs with Weight Quantization","created":"2023-10-17","cited_by_count":22,"area":"safety"},{"id":"2409.00426","title":"Is Difficulty Calibration All We Need? Towards More Practical Membership Inference Attacks","created":"2024-08-31","cited_by_count":21,"area":"safety"},{"id":"2505.15710","title":"Advancing LLM Safe Alignment with Safety Representation Ranking","created":"2025-05-21","cited_by_count":16,"area":"safety"},{"id":"2307.10476","title":"What can we learn from Data Leakage and Unlearning for Law?","created":"2023-07-19","cited_by_count":15,"area":"safety"},{"id":"2403.13000","title":"Duwak: Dual Watermarks in Large Language Models","created":"2024-03-12","cited_by_count":11,"area":"safety"},{"id":"2410.06809","title":"Root Defence Strategies: Ensuring Safety of LLM at the Decoding Level","created":"2024-10-09","cited_by_count":11,"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":"2503.15128","title":"Increasing the Robustness of the Fine-tuned Multilingual Machine-Generated Text Detectors","created":"2025-03-19","cited_by_count":8,"area":"safety"},{"id":"2510.12981","title":"Reference-Specific Unlearning Metrics Can Hide the Truth: A Reality Check","created":"2025-10-14","cited_by_count":5,"area":"safety"},{"id":"2506.17299","title":"Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem","created":"2025-06-17","cited_by_count":4,"area":"safety"},{"id":"2508.03829","title":"Majority Bit-Aware Watermarking For Large Language Models","created":"2025-08-05","cited_by_count":4,"area":"safety"},{"id":"2504.12108","title":"Entropy-Guided Watermarking for LLMs: A Test-Time Framework for Robust and Traceable Text Generation","created":"2025-04-16","cited_by_count":3,"area":"safety"},{"id":"2511.16278","title":"\"To Survive, I Must Defect\": Jailbreaking LLMs via the Game-Theory Scenarios","created":"2025-11-20","cited_by_count":3,"area":"safety"},{"id":"2604.05242","title":"XMark: Reliable Multi-Bit Watermarking for LLM-Generated Texts","created":"2026-04-06","cited_by_count":3,"area":"safety"},{"id":"2510.13829","title":"A Linguistics-Aware LLM Watermarking via Syntactic Predictability","created":"2025-10-10","cited_by_count":2,"area":"safety"},{"id":"2605.31293","title":"Divergence Decoding: Inference-Time Unlearning via Auxiliary Models","created":"2026-05-29","cited_by_count":2,"area":"safety"},{"id":"2506.01825","title":"Backdoors in Code Summarizers: How Bad Is It?","created":"2025-06-02","cited_by_count":1,"area":"safety"},{"id":"2407.14206","title":"Watermark Smoothing Attacks against Language Models","created":"2024-07-19","cited_by_count":0,"area":"safety"},{"id":"2505.07167","title":"Decoding One Safety Trigger Token for Balancing Safety and Usability in Large Language Models","created":"2025-05-12","cited_by_count":0,"area":"safety"},{"id":"2512.13352","title":"On the Effectiveness of Membership Inference in Targeted Data Extraction from Large Language Models","created":"2025-12-15","cited_by_count":0,"area":"safety"},{"id":"2603.01550","title":"Extracting Training Dialogue Data from Large Language Model based Task Bots","created":"2026-03-02","cited_by_count":0,"area":"safety"},{"id":"2610.04169","title":"Language Model Fingerprinting Requires Rethinking Watermark Teachers","created":"2026-10-03","cited_by_count":0,"area":"safety"}],"next_cursor":null}