[2021-03-19] Prof. Shan-Hung (Brandon) Wu, National Tsing Hua University (NTHU), "On the Trustworthiness of Deep Neural Networks"

Poster:Post date:2021-03-08
Title: On the Trustworthiness of Deep Neural Networks
Date: 2021-03-19 2:20pm-3:30pm
Location: R103, CSIE
Speaker: Prof. Shan-Hung (Brandon) Wu, National Tsing Hua University (NTHU)
Hosted by: Prof. Chu-Song Chen
Deep neural networks (DNNs) have achieved impressive performance in many domains such as computer vision, natural language processing, speech, and robotics, etc. However, DNNs are shown to be susceptible to some types of attacks, including adversarial attacks and backdoor attacks, which can seriously impact people's lives in security- and safety-sensitive applications such as self-driving cars. In this talk, I present my recent works on the trustworthiness of DNNs. I first discuss how to defend against evolving adversarial attacks that may not be known at training time. Next, I introduce a simple defense against physical adversarial attacks for DNN-based object detectors. Finally, I share a discovery about the trade-off between the adversarial robustness and backdoor robustness of DNNs. The findings suggest that future research on defense should take both adversarial and backdoor attacks into account when designing algorithms or robustness measures to avoid pitfalls and a false sense of security.

Shan-Hung (Brandon) Wu is an Associate Professor at the Department of Computer Science, National Tsing Hua University (NTHU). His research interests include Machine Learning, Big Data Management, and App Intelligence. He received a Ph.D. degree in Electrical Engineering from the National Taiwan University (Sep 2005 - Feb 2009). Before joining NTHU in 2010, he was a senior research scientist at Telcordia Technologies (formerly Bellcore) Inc. during 2004 and 2010. Dr. Wu has published many papers in top-tier conference venues, including NeurIPS/NIPS, ICML, KDD, SIGMOD, VLDB, ICDE, INFOCOM, WWW, etc. He received the Google Faculty Award in 2020. 
Last modification time:2021-03-08 AM 9:16

cron web_use_log