OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models

Large language models LLMs trained over extensive corpora risk memorizing sensitive, copyrighted, or toxic content. To address this, we propose OBLIVIATE, a robust unlearning framework that removes targeted data while preserving model utility. The framework follows a structured process: extractin...

Recovering Real Faces from Face-Generation ML System

New paper: "This Person Probably Exists. Identity Membership Attacks Against GAN Generated Faces. Abstract: Recently, generative adversarial networks GANs have achieved stunning realism, fooling even human observers. Indeed, the popular tongue-in-cheek website http://thispersondoesnotexist.com,...