← Search

Yupei Liu

2 accepted papers

2025

TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning

AAAI 2025technical

An image encoder pre-trained by self-supervised learning can be used as a general-purpose feature extractor to build downstream classifiers for various downstream tasks. However, many studies showed that an attacker can embed a trojan into an encoder such that multiple downstream classifiers built b…

2022

Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks

AAAI 2022technical

Data poisoning attacks and backdoor attacks aim to corrupt a machine learning classifier via modifying, adding, and/or removing some carefully selected training examples, such that the corrupted classifier makes incorrect predictions as the attacker desires. The key idea of state-of-the-art certifie…