Research map / Adversarial robustness and security / Attacks on text and graphs
Robust Physical-World Attacks on Deep Learning Visual Classification
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 |
|---|---|---|---|
| Apply an object-constrained poster perturbation to a Stop sign | LISA-CNN · Stop sign, stationary lab and drive-by field test | targeted attack success rate: 100% | Helped |
| Apply graffiti-like stickers to a Stop sign | LISA-CNN · Stop sign, stationary lab | targeted attack success rate: 66.67% | Helped |
| Apply camouflage-art stickers to a Stop sign | LISA-CNN · Stop sign, stationary lab | targeted attack success rate: 100% | Helped |
| Apply camouflage-art stickers to a Stop sign | LISA-CNN · Stop sign, drive-by field test | targeted attack success rate: 84.8% | Helped |
| Apply a subtle perturbation to the arrow region | LISA-CNN · Right Turn sign, stationary lab | targeted attack success rate: 73.33% | Helped |
| Apply camouflage-art stickers to a Stop sign | GTSRB-CNN · Stop sign, stationary lab | targeted attack success rate: 80% | Helped |
| Apply camouflage-art stickers to a Stop sign | GTSRB-CNN · Stop sign, drive-by field test | targeted attack success rate: 87.5% | Helped |
| Apply a sticker to a microwave | Inception-v3 · Microwave | targeted attack success rate: 90% | Helped |
| Apply a sticker to a coffee mug | Inception-v3 · Coffee mug | targeted attack success rate: 71.4% | Helped |
Closest papers by meaning
- Connecting the Digital and Physical World: Improving the Robustness of Adversarial Attacks (AAAI 2019 · similarity 0.91)
- Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature (AAAI 2025 · similarity 0.90)
- Adversarial camera stickers: A physical camera-based attack on deep learning systems (ICML 2019 · similarity 0.89)
- Shadows Can Be Dangerous: Stealthy and Effective Physical-World Adversarial Attack by Natural Phenomenon (CVPR 2022 · similarity 0.89)
- Beyond Digital Domain: Fooling Deep Learning Based Recognition System in Physical World (AAAI 2020 · similarity 0.89)
- Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data (ICLR 2025 · similarity 0.86)
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.