research
∙
04/05/2023
UNICORN: A Unified Backdoor Trigger Inversion Framework
The backdoor attack, where the adversary uses inputs stamped with trigge...
share
research
∙
11/29/2022
Backdoor Vulnerabilities in Normally Trained Deep Learning Models
We conduct a systematic study of backdoor vulnerabilities in normally tr...
research
∙
10/27/2022
Rethinking the Reverse-engineering of Trojan Triggers
Deep Neural Networks are vulnerable to Trojan (or backdoor) attacks. Rev...
research
∙
05/26/2022
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning
Deep neural networks are vulnerable to Trojan attacks. Existing attacks ...
research
∙
02/13/2022
Neural Network Trojans Analysis and Mitigation from the Input Domain
Deep Neural Networks (DNNs) can learn Trojans (or backdoors) from benign...
research
∙
06/01/2021
Assembly Planning by Recognizing a Graphical Instruction Manual
This paper proposes a robot assembly planning method by automatically re...
research
∙
03/16/2021