3 papers
cs.CV2022
FRIB: Low-poisoning Rate Invisible Backdoor Attack based on Feature Repair
Hui Xia, Xiugui Yang, Xiangyun Qian +1
During the generation of invisible backdoor attack poisoned data, the feature space transformation operation tends to cause the loss of some poisoned features and weakens the mappi…
cs.CV2022
AdvSmo: Black-box Adversarial Attack by Smoothing Linear Structure of Texture
Hui Xia, Rui Zhang, Shuliang Jiang +1
Black-box attacks usually face two problems: poor transferability and the inability to evade the adversarial defense. To overcome these shortcomings, we create an original approach…
cs.CV2022
SSMI: How to Make Objects of Interest Disappear without Accessing Object Detectors?
Hui Xia, Rui Zhang, Zi Kang +1
Most black-box adversarial attack schemes for object detectors mainly face two shortcomings: requiring access to the target model and generating inefficient adversarial examples (f…