Showing 1–11 of 11 results
/ Date/ Name
Sep 13, 2023DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward PassSep 16, 2019VeriML: Enabling Integrity Assurances and Fair Payments for Machine Learning as a ServiceJul 1, 2025Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM ReasoningJun 2, 2021Differential Privacy for Text Analytics via Natural Text SanitizationMay 7, 2026When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized AgentsMay 18, 2025SecEmb: Sparsity-Aware Secure Federated Learning of On-Device Recommender System with Large EmbeddingMay 7, 2025OBLIVIATE: Robust and Practical Machine Unlearning for Large Language ModelsJan 7, 2026From Domains to Instances: Dual-Granularity Data Synthesis for LLM UnlearningJan 29, 2026FIT to Forget: Robust Continual Unlearning for Large Language ModelsFeb 23, 2024Machine Unlearning of Pre-trained Large Language ModelsMay 22, 2025Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs