IFS-1.6
HOW SECURE ARE THE ADVERSARIAL EXAMPLES THEMSELVES?
Hui Zeng, Southwest university of science and technology, China; Kang Deng, Anjie Peng, Southwest University of Science and Technology, China; Biwei Chen, Houghton College, United States of America
Session:
Multimedia Forensics I
Track:
Information Forensics and Security
Location:
Gather Area G
Presentation Time:
Sun, 8 May, 23:00 - 23:45 China Time (UTC +8)
Sun, 8 May, 15:00 - 15:45 UTC
Sun, 8 May, 15:00 - 15:45 UTC
Session Chair:
Christian Riess, Friedrich-Alexander University
Session IFS-1
IFS-1.1: Real-World Adversarial Examples via Makeup
Chang-Sheng Lin, National Chung Hsing University, Taiwan; Chia-Yi Hsu, Chia-Mu Yu, National Yang Ming Chiao Tung University, Taiwan; Pin-Yu Chen, IBM Research, Taiwan
IFS-1.2: In Pursuit of Preserving the Fidelity of Adversarial Images
Joseph Clements, Yingjie Lao, Clemson University, United States of America
IFS-1.3: OBJECT-ORIENTED BACKDOOR ATTACK AGAINST IMAGE CAPTIONING
Meiling Li, Nan Zhong, Xinpeng Zhang, Zhenxing Qian, Sheng Li, Fudan University, China
IFS-1.4: TOWARDS ROBUST SPEECH-TO-TEXT ADVERSARIAL ATTACK
Mohammad Esmaeilpour, Patrick Cardinal, Alessandro Lameiras Koerich, École de Technologie Supérieure, Canada
IFS-1.5: Sparse Adversarial Attack for video via Gradient-Based Keyframe Selection
Yixiao Xu, Xiaolei Liu, Mingyong Yin, Teng Hu, Kangyi Ding, China Academy of Engineering Physics, China
IFS-1.6: HOW SECURE ARE THE ADVERSARIAL EXAMPLES THEMSELVES?
Hui Zeng, Southwest university of science and technology, China; Kang Deng, Anjie Peng, Southwest University of Science and Technology, China; Biwei Chen, Houghton College, United States of America