Ziyao Wang

A General Framework for Defending Against Backdoor Attacks via Influence Graph

2021 · arXiv (Cornell University)

In this work, we propose a new and general framework to defend against backdoor attacks, inspired by the fact that attack triggers usually follow a \textsc{specific} type of attacking pattern, and therefore, poisoned training examples …

Moderator: Moderating Text-to-Image Diffusion Models through Fine-grained Context-based Policies

2024

We present Moderator, a policy-based model management system that allows administrators to specify fine-grained content moderation policies and modify the weights of a text-to-image (TTI) model to make it significantly more challenging for users to …