Danni Yuan — accepted AI-conference papers

2025

Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks

Danni Yuan, Mingda Zhang, Shaokui Wei, Li Liu, Baoyuan Wu

ICLR 2025poster

This work studies the task of poisoned sample detection for defending against data poisoning based backdoor attacks. Its core challenge is finding a generalizable and discriminative metric to distinguish between clean and various types of poisoned samples (e.g., various triggers, various poisoning r…

Cited by 4 Source ↗PDF ↗Scholar ↗

2022

BackdoorBench: A Comprehensive Benchmark of Backdoor Learning

Baoyuan Wu, Hongrui Chen, Mingda Zhang, Zihao Zhu, Shaokui Wei, Danni Yuan +1

NeurIPS 2022accept

Backdoor learning is an emerging and vital topic for studying deep neural networks' vulnerability (DNNs). Many pioneering backdoor attack and defense methods are being proposed, successively or concurrently, in the status of a rapid arms race. However, we find that the evaluations of new methods are…

Cited by 154 Source ↗PDF ↗code ↗Scholar ↗