Kavli Affiliate: Anqi Zhang| Summary:While large language models (LLMs) are extensively used, there are raising concerns regarding privacy, security, and copyright due to their opaque training data, which brings the problem of detecting pre-training data on the table. Current solutions to this problem leverage techniques explored in machine learning privacy such as Membership Inference Attacks […]
Continue.. Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens