{"total":21,"rows":[{"id":"2306.04528","title":"PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts","created":"2023-06-07","cited_by_count":226,"area":"safety"},{"id":"2305.08883","title":"Watermarking Text Generated by Black-Box Language Models","created":"2023-05-14","cited_by_count":76,"area":"safety"},{"id":"2112.05224","title":"Spinning Language Models: Risks of Propaganda-As-A-Service and Countermeasures","created":"2021-12-09","cited_by_count":73,"area":"safety"},{"id":"2212.09573","title":"Privacy Adhering Machine Un-learning in NLP","created":"2022-12-19","cited_by_count":36,"area":"safety"},{"id":"2305.19607","title":"Adversarial Clean Label Backdoor Attacks and Defenses on Text Classification Systems","created":"2023-05-31","cited_by_count":11,"area":"safety"},{"id":"2308.07847","title":"Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models","created":"2023-08-15","cited_by_count":7,"area":"safety"},{"id":"2405.08400","title":"Stylometric Watermarks for Large Language Models","created":"2024-05-14","cited_by_count":4,"area":"safety"},{"id":"2503.09330","title":"Group-robust Machine Unlearning","created":"2025-03-12","cited_by_count":3,"area":"safety"},{"id":"2511.07842","title":"Safety-Preserving PTQ via Contrastive Alignment Loss","created":"2025-11-11","cited_by_count":3,"area":"safety"},{"id":"2210.11082","title":"Apple of Sodom: Hidden Backdoors in Superior Sentence Embeddings via Contrastive Learning","created":"2022-10-20","cited_by_count":2,"area":"safety"},{"id":"2505.22852","title":"Operationalizing CaMeL: Strengthening LLM Defenses for Enterprise Deployment","created":"2025-05-28","cited_by_count":1,"area":"safety"},{"id":"2601.15595","title":"Data-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning","created":"2026-01-22","cited_by_count":1,"area":"safety"},{"id":"2605.15172","title":"MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs","created":"2026-05-14","cited_by_count":1,"area":"safety"},{"id":"2605.18993","title":"Distilling Linearized Behavior into Non-Linear Fine-Tuning for Effective Task Arithmetic","created":"2026-05-18","cited_by_count":1,"area":"safety"},{"id":"2601.19487","title":"LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment","created":"2026-01-27","cited_by_count":0,"area":"safety"},{"id":"2603.07452","title":"Backdoor4Good: Benchmarking Beneficial Uses of Backdoors in LLMs","created":"2026-03-08","cited_by_count":0,"area":"safety"},{"id":"2605.18879","title":"ZeroUnlearn: Few-Shot Knowledge Unlearning in Large Language Models","created":"2026-05-16","cited_by_count":0,"area":"safety"},{"id":"2607.09804","title":"Trivial Prompt Reframing Bypasses Safety Guardrails in Google\\'s MedGemma-4B","created":"2026-07-09","cited_by_count":0,"area":"safety"},{"id":"2607.22657","title":"Between Suppression and Collapse: Evaluating Narrative Unlearning with LENS","created":"2026-06-27","cited_by_count":0,"area":"safety"},{"id":"2610.06503","title":"Harmful Content Generation in Text-to-Image Models: Capabilities and Moderation Limitations","created":"2026-10-05","cited_by_count":0,"area":"safety"},{"id":"2610.19385","title":"RA$^2$: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning","created":"2026-10-14","cited_by_count":0,"area":"safety"}],"next_cursor":null}