PII-Compass: Guiding LLM training data extraction prompts towards the target PII via groundingAugust 31, 2024This post is the note of the paper “PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding”. See docs for more info.Continue reading
Teach LLMs to Phish Stealing Private Information from Language Models - NoteAugust 29, 2024This post is the note of the paper “Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs”. See docs for more info.Continue reading