My Blog

1. Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice  Arxiv Preprint

#machine_unlearning #generativeAI #structural_removal #output_suppression #AI_Policy

2. Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial Attack  LREC-COLING 2024

#llm_generated_text_detection #adversarial_attack #adversarial_learning