Research map / Adversarial robustness and security / Attacks on text and graphs
Detecting Adversarial Examples Through Image Transformation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| randomized rotation-based detector vs Gong/Grosse detectors | adversarial example detection · MNIST white-box CW | detection success: 0 -> 0.85 | Helped |
| adding random rotation angles to detector (ablation) | transformation-based detector · MNIST/CIFAR10 oblivious CW | detection accuracy | Hurt |
| adding randomness (attacker cannot know angles) (ablation) | transformation-based detector · MNIST white-box CW | detection accuracy | Helped |
| adding detector to classifier | CW white-box attack · MNIST conf 20 | distortion required: 3.29 -> 7.64 | Helped |
| training detector on all confidence levels vs single level (ablation) | detector · MNIST/CIFAR10 | detection accuracy | Helped |
| transfer CW-trained detector to FGS/IFGS attacks | detector · MNIST | detection success: 0.967-0.999 | Helped |
Closest papers by meaning
- Countering Adversarial Images using Input Transformations (ICLR 2018 · similarity 0.90)
- Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions (AAAI 2021 · similarity 0.90)
- One Man's Trash Is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examples (CVPR 2020 · similarity 0.90)
- Learning to Attack: Adversarial Transformation Networks (AAAI 2018 · similarity 0.89)
- Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks (CVPR 2019 · similarity 0.89)
- Improving Transferability of Adversarial Examples With Input Diversity (CVPR 2019 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.