Skip to the content.

Overview

Date May 5, 2023 (9 am - 18:00 pm US Eastern Daylight Time)
Link https://iclr.cc/virtual/2023/workshop/12825 (ICLR registration required)
Location Virtually
Schedule Click here

Backdoor attacks aim to cause consistent misclassification of any input by adding a specific pattern called a trigger. Unlike adversarial attacks requiring generating perturbations on the fly to induce misclassification for one single input, backdoor attacks have prompt effects by simply applying a pre-chosen trigger. Recent studies have shown the feasibility of launching backdoor attacks in various domains, such as computer vision (CV), natural language processing (NLP), federated learning (FL), etc. As backdoor attacks are mostly carried out through data poisoning (i.e., adding malicious inputs to training data), it raises major concerns for many publicly available pre-trained models. Companies relying on user data to construct their machine learning models are also susceptible to backdoor attacks.

This workshop, Backdoor Attacks aNd DefenSes in Machine Learning (BANDS), aims to bring together researchers from government, academia, and industry that share a common interest in exploring and building more secure machine learning models against backdoor attacks.

Featured Speakers

Speakers are in alphabetical order by last name.

Pin-Yu Chen Wenbo Guo Amir Houmansadr
Pin-Yu Chen
IBM Research AI
Wenbo Guo
UC Berkeley
Amir Houmansadr
University of Massachusetts
Ruoxi Jia Bo Li Michael Mahoney
Ruoxi Jia
Virginia Tech
Bo Li
UIUC
Michael Mahoney
UC Berkeley and ICSI
Vitaly Shmatikov Yang Zhang Ben Y. Zhao
Vitaly Shmatikov
Cornell Tech
Yang Zhang
CISPA
Ben Y. Zhao
UChicago

Panelists

Panelists are in alphabetical order by last name.

Pin-Yu Chen Ruoxi Jia Bo Li
Pin-Yu Chen
IBM Research AI
Ruoxi Jia
Virginia Tech
Bo Li
UIUC
Vitaly Shmatikov Ben Y. Zhao  
Vitaly Shmatikov
Cornell Tech
Ben Y. Zhao
UChicago
 

Best Paper Award

Organizers

Guanhong Tao Kaiyuan Zhang Shawn Shan Emily Wenger
Guanhong Tao
Purdue University
Kaiyuan Zhang
Purdue University
Shawn Shan
University of Chicago
Emily Wenger
University of Chicago
Rui Zhu Eugene Bagdasaryan Naren Sarayu Manoj Taylor Kulp-McDowall
Rui Zhu
Indiana University
Eugene Bagdasaryan
Cornell Tech
Naren Sarayu Manoj
TTIC
Taylor Kulp-McDowall
IARPA
Yousra Aafer Shiqing Ma Xiangyu Zhang  
Yousra Aafer
University of Waterloo
Shiqing Ma
Rutgers University
Xiangyu Zhang
Purdue University