MLSP-L7.1
DEFENDING AGAINST CLEAN-IMAGE BACKDOOR ATTACK IN MULTI-LABEL CLASSIFICATION
Cheng-Yi Lee, Cheng-Chang Tsai, Ching-Chia Kao, Chun-Shien Lu, Academia Sinica, Taiwan; Chia-Mu Yu, National Yang Ming Chiao Tung University, Taiwan
Session:
MLSP-L7: Adversarial Machine Learning I Lecture
Track:
Machine Learning for Signal Processing
Location:
Room 201
Presentation Time:
Wed, 17 Apr, 08:20 - 08:40 (UTC +9)
Session Co-Chairs:
Jen-Tzung Chien, National Yang Ming Chiao Tung University and Shengchen Li, Xian Jiaotong Liverpool University
Session MLSP-L7
MLSP-L7.1: DEFENDING AGAINST CLEAN-IMAGE BACKDOOR ATTACK IN MULTI-LABEL CLASSIFICATION
Cheng-Yi Lee, Cheng-Chang Tsai, Ching-Chia Kao, Chun-Shien Lu, Academia Sinica, Taiwan; Chia-Mu Yu, National Yang Ming Chiao Tung University, Taiwan
MLSP-L7.2: ROBUSTNESS AGAINST ADVERSARIAL ATTACKS VIA LEARNING CONFINED ADVERSARIAL POLYTOPES
Shayan Mohajer Hamidi, Linfeng Ye, University of Waterloo, Canada
MLSP-L7.3: SSTA: Salient Spatially Transformed Attack
Renyang Liu, Wei Zhou, Sixing Wu, Yunnan University, China; Jun Zhao, Kwok-Yan Lam, Nanyang Technological University, Singapore
MLSP-L7.4: ENHANCING ADVERSARIAL TRANSFERABILITY IN OBJECT DETECTION WITH BIDIRECTIONAL FEATURE DISTORTION
Xinlong Ding, Jiansheng Chen, Hongwei Yu, University of Science and Technology Beijing, China; Yu Shang, Tsinghua University, China; Huimin Ma, University of Science and Technology Beijing, China
MLSP-L7.5: GCIA: A BLACK-BOX GRAPH INJECTION ATTACK METHOD VIA GRAPH CONTRASTIVE LEARNING
Xiao Liu, Jun-Jie Huang, Wentao Zhao, National University of Defense Technology, China
MLSP-L7.6: TOWARDS A UNIFIED VIEW OF ADVERSARIAL TRAINING: A CONTRASTIVE PERSPECTIVE
Jen-Tzung Chien, Yuan-An Chen, National Yang Ming Chiao Tung University, Taiwan
Contacts