{"total":14,"rows":[{"id":"2406.02622","title":"Safeguarding Large Language Models: A Survey","created":"2024-06-03","cited_by_count":78,"area":"safety"},{"id":"2408.06223","title":"On Effects of Steering Latent Representation for Large Language Model Unlearning","created":"2024-08-12","cited_by_count":32,"area":"safety"},{"id":"2404.12922","title":"Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images","created":"2024-04-19","cited_by_count":18,"area":"safety"},{"id":"2308.04635","title":"Where's the Liability in Harmful AI Speech?","created":"2023-08-09","cited_by_count":12,"area":"safety"},{"id":"2111.09076","title":"To Trust or Not To Trust Prediction Scores for Membership Inference Attacks","created":"2021-11-17","cited_by_count":10,"area":"safety"},{"id":"2208.07522","title":"Reliable Decision from Multiple Subtasks through Threshold Optimization: Content Moderation in the Wild","created":"2022-08-16","cited_by_count":7,"area":"safety"},{"id":"2501.17151","title":"Scanning Trojaned Models Using Out-of-Distribution Samples","created":"2025-01-28","cited_by_count":3,"area":"safety"},{"id":"2310.08015","title":"Why Train More? Effective and Efficient Membership Inference via Memorization","created":"2023-10-12","cited_by_count":2,"area":"safety"},{"id":"2602.18782","title":"MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs","created":"2026-02-21","cited_by_count":2,"area":"safety"},{"id":"2605.01129","title":"Revisiting Privacy Leakage in Machine Unlearning: Membership Inference Beyond the Forgotten Set","created":"2026-05-01","cited_by_count":2,"area":"safety"},{"id":"2502.13191","title":"On the Privacy Risks of Spiking Neural Networks: A Membership Inference Analysis","created":"2025-02-18","cited_by_count":1,"area":"safety"},{"id":"2508.04166","title":"STEMTOX: From Collaborative Tags to Fine-Grained Toxic Meme Detection via Entropy-Guided Multi-Task Learning","created":"2025-08-06","cited_by_count":0,"area":"safety"},{"id":"2602.06331","title":"Don't Break the Boundary: Continual Unlearning for OOD Detection Based on Free Energy Repulsion","created":"2026-02-06","cited_by_count":0,"area":"safety"},{"id":"2606.03499","title":"Characterizing Detectability in 3DGS Poisoning: A Stage-wise Benchmark","created":"2026-06-02","cited_by_count":0,"area":"safety"}],"next_cursor":null}