{"total":24,"rows":[{"id":"2311.03191","title":"DeepInception: Hypnotize Large Language Model to Be Jailbreaker","created":"2023-11-06","cited_by_count":367,"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":"2404.16873","title":"AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs","created":"2024-04-21","cited_by_count":156,"area":"safety"},{"id":"2309.01446","title":"Open Sesame! Universal Black Box Jailbreaking of Large Language Models","created":"2023-09-04","cited_by_count":134,"area":"safety"},{"id":"2403.13355","title":"BadEdit: Backdooring large language models by model editing","created":"2024-03-20","cited_by_count":96,"area":"safety"},{"id":"2402.09091","title":"Play Guessing Game with LLM: Indirect Jailbreak Attack with Implicit Clues","created":"2024-02-14","cited_by_count":68,"area":"safety"},{"id":"2401.05949","title":"Universal Vulnerabilities in Large Language Models: Backdoor Attacks for In-context Learning","created":"2024-01-11","cited_by_count":53,"area":"safety"},{"id":"2402.09674","title":"PAL: Proxy-Guided Black-Box Attack on Large Language Models","created":"2024-02-15","cited_by_count":50,"area":"safety"},{"id":"2310.09573","title":"Self-Detoxifying Language Models via Toxification Reversal","created":"2023-10-14","cited_by_count":46,"area":"safety"},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2410.22086","title":"Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate","created":"2024-10-29","cited_by_count":31,"area":"safety"},{"id":"2309.13322","title":"From Text to Source: Results in Detecting Large Language Model-Generated Content","created":"2023-09-23","cited_by_count":26,"area":"safety"},{"id":"2408.15488","title":"Legilimens: Practical and Unified Content Moderation for Large Language Model Services","created":"2024-08-28","cited_by_count":13,"area":"safety"},{"id":"2503.04036","title":"Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge","created":"2025-03-06","cited_by_count":12,"area":"safety"},{"id":"2308.13449","title":"The Poison of Alignment","created":"2023-08-25","cited_by_count":10,"area":"safety"},{"id":"2308.02080","title":"Causality Guided Disentanglement for Cross-Platform Hate Speech Detection","created":"2023-08-03","cited_by_count":9,"area":"safety"},{"id":"2601.02751","title":"Window-based Membership Inference Attacks Against Fine-tuned Large Language Models","created":"2026-01-06","cited_by_count":7,"area":"safety"},{"id":"2510.16629","title":"On the Impossibility of Retrain Equivalence in Machine Unlearning","created":"2025-10-18","cited_by_count":6,"area":"safety"},{"id":"2411.12600","title":"Provable unlearning in topic modeling and downstream tasks","created":"2024-11-19","cited_by_count":4,"area":"safety"},{"id":"2412.05232","title":"LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds","created":"2024-12-06","cited_by_count":4,"area":"safety"},{"id":"2503.05721","title":"What Are They Filtering Out? An Experimental Benchmark of Filtering Strategies for Harm Reduction in Pretraining Datasets","created":"2025-02-17","cited_by_count":2,"area":"safety"},{"id":"2604.03199","title":"Learning the Signature of Memorization in Autoregressive Language Models","created":"2026-04-03","cited_by_count":1,"area":"safety"},{"id":"2403.16151","title":"Ultra Low-Cost Two-Stage Multimodal System for Non-Normative Behavior Detection","created":"2024-03-24","cited_by_count":0,"area":"safety"},{"id":"2603.00811","title":"Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning","created":"2026-02-28","cited_by_count":0,"area":"safety"}],"next_cursor":null}