TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs
As large language models (LLMs) face growing demands for data removal driven by regulatory compliance, copyright concerns, and privacy protection, approximate unlearning has emerged as a practical alternative to expensive full retraining. In practice, pre- and post-unlearning model snapshots are often maintained for au...
Meng-Ying Zhang, De-Rui Wang, Ibrahim Khalil et al.
· 0 citations