no code implementations • 26 Jul 2022 • Hui Xia, Xiugui Yang, Xiangyun Qian, Rui Zhang
To solve the above problems, we propose the idea of feature repair for the first time and introduce the blind watermark technique to repair the poisoned features lost during the generation of poisoned data.
no code implementations • 22 Jun 2022 • Hui Xia, Rui Zhang, Zi Kang, Shuliang Jiang
Most black-box adversarial attack schemes for object detectors mainly face two shortcomings: requiring access to the target model and generating inefficient adversarial examples (failing to make objects disappear in large numbers).
no code implementations • 22 Jun 2022 • Hui Xia, Rui Zhang, Shuliang Jiang, Zi Kang
We construct the adversarial examples without relying on any internal information to the target model and design the imperceptible-high attack success rate constraint to guide the Gabor filter to select appropriate angles and scales to smooth the linear texture from the input images to generate adversarial examples.