Search All 2022 Events
 

Results

<<   <   Page 1 of 2   >   >>
Poster
Tue 10:30 Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios
Zhen Xiang · David Miller · George Kesidis
Poster
Wed 2:30 NETWORK INSENSITIVITY TO PARAMETER NOISE VIA PARAMETER ATTACK DURING TRAINING
Julian B├╝chel · Fynn Faber · Dylan R Muir
Poster
Wed 10:30 Towards Understanding the Robustness Against Evasion Attack on Categorical Data
Hongyan Bao · Yufei Han · Yujun Zhou · Yun Shen · Xiangliang Zhang
Poster
Thu 18:30 Transferable Adversarial Attack based on Integrated Gradients
Yi Huang · Adams Kong
Poster
Mon 2:30 Understanding and Improving Graph Injection Attack by Promoting Unnoticeability
Yongqiang Chen · Han Yang · Yonggang Zhang · MA KAILI · Tongliang Liu · Bo Han · James Cheng
Workshop
REVERSING ADVERSARIAL ATTACKS WITH MULTIPLE SELF SUPERVISED TASKS
Matthew Lawhon · Chengzhi Mao · Gustave Ducrest · Junfeng Yang
Poster
Tue 10:30 Provably Robust Adversarial Examples
Dimitar I. Dimitrov · Gagandeep Singh · Timon Gehr · Martin Vechev
Poster
Wed 2:30 Attacking deep networks with surrogate-based adversarial black-box methods is easy
Nicholas A. Lord · Romain Mueller · Luca Bertinetto
Poster
Thu 10:30 Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?
Vikash Sehwag · Saeed Mahloujifar · Tinashe Handina · Sihui Dai · Chong Xiang · Mung Chiang · Prateek Mittal
Poster
Wed 18:30 Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent
Oliver Bryniarski · Nabeel Hingun · Pedro Pachuca · Vincent Wang · Nicholas Carlini
Poster
Tue 10:30 Online Adversarial Attacks
Andjela Mladenovic · Joey Bose · Hugo Berard · William Hamilton · Simon Lacoste-Julien · Pascal Vincent · Gauthier Gidel
Poster
Wed 18:30 Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains
Qilong Zhang · Xiaodan Li · YueFeng Chen · Jingkuan Song · Lianli Gao · Yuan He · Hui Xue'