Research map / Adversarial robustness and security / Black-box and transfer attacks
Improving the Transferability of Adversarial Samples With Adversarial Transformations
Check 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 |
|---|---|---|---|
| Add an adversarial transformation network and train samples to resist its distortions (ablation) | BIM-based transfer attacks · ImageNet validation, Inc-v3 source to other models | success rate (%) | Helped |
| Add adversarial transformations | Inc-v3-source attacks against defended models · ImageNet defenses, average | success rate (%): 72.1 -> 78.4 | Helped |
| Use a smaller Conv (4, 3) transformation network instead of Conv (16, 3) (ablation) | ATTA · ImageNet validation, source Inc-v3 → Res-v2 | success rate (%): 44.8 -> 39.7 | Hurt |
| Use a larger Conv (32, 3) transformation network instead of Conv (16, 3) (ablation) | ATTA · ImageNet validation, source Inc-v3 → Res-v2 | success rate (%): 44.8 -> 34.8 | Hurt |
| Use a deeper Conv (32, 32, 3) transformation network instead of Conv (16, 3) (ablation) | ATTA · ImageNet validation, source Inc-v3 → Res-v2 | success rate (%): 44.8 -> 33.8 | Hurt |
| Combine adversarial transformations with SI-NI-TI-DIM | SI-NI-TI-DIM transfer attack · ImageNet validation, Inc-v4 source to Inc-v3 | success rate (%): 72.1 -> 75.2 | Helped |
Closest papers by meaning
- Rethinking Adversarial Transferability from a Data Distribution Perspective (ICLR 2022 · similarity 0.92)
- Enhancing Adversarial Transferability with Adversarial Weight Tuning (AAAI 2025 · similarity 0.90)
- Learning to Transform Dynamically for Better Adversarial Transferability (CVPR 2024 · similarity 0.90)
- Enhancing Adversarial Transferability with Checkpoints of a Single Model's Training (CVPR 2025 · similarity 0.89)
- Boosting Adversarial Transferability through Augmentation in Hypothesis Space (CVPR 2025 · similarity 0.89)
- Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability (NeurIPS 2025 · 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.