Wei Sun
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper proposes PCDM, a diffusion-based framework that enables highly stealthy and effective data poisoning attacks against Federated Learning systems, significantly degrading global performance while evading detection.
The paper demonstrates that the AI-like style introduced by post-training alignment can be measured, localized, and causally removed using a novel ablation technique called PASTA.
Papers
Measuring, Localizing, and Ablating Alignment Signatures in LLMs
Aniket Anand, Janvijay Singh, Zhewei Sun, Dilek Hakkani-Tür +1 more
The paper demonstrates that the AI-like style introduced by post-training alignment can be measured, localized, and causally removed using a novel ablation technique called PASTA.