| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
RoBIC: A benchmark suite for assessing classifiers robustness
Abstract : Many defenses have emerged with the development of adversarial attacks. Models must be objectively evaluated accordingly. This paper systematically tackles this concern by proposing a new parameter-free benchmark we coin RoBIC. RoBIC fairly evaluates the robustness of image classifiers using a new half-distortion measure. It gauges the robustness of the network against white and black box attacks, independently of its accuracy. RoBIC is faster than the other available benchmarks. We present the significant differences in the robustness of 16 recent models as assessed by RoBIC. We make this benchmark publicly available for use and contribution at https://gitlab.inria.fr/tmaho/ robustness_benchmark.
https://hal.inria.fr/hal-03234791
Contributor : Erwan Le Merrer Connect in order to contact the contributor
Submitted on : Tuesday, May 25, 2021 - 3:02:52 PM
Last modification on : Friday, April 8, 2022 - 4:08:03 PM
Long-term archiving on: : Thursday, August 26, 2021 - 8:03:40 PM
Contributor : Erwan Le Merrer Connect in order to contact the contributor
Submitted on : Tuesday, May 25, 2021 - 3:02:52 PM
Last modification on : Friday, April 8, 2022 - 4:08:03 PM
Long-term archiving on: : Thursday, August 26, 2021 - 8:03:40 PM
File
main.pdf
Files produced by the author(s)