Research map / Adversarial robustness and security / Certified and empirical robustness
Towards Imperceptible and Robust Adversarial Example Attacks Against Neural Networks
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 |
|---|---|---|---|
| Use the proposed attack instead of JSMA | Targeted adversarial attacks against the 8-layer DNN · CIFAR10, Gaussian noise std=0.05 | success attack rate: 98.25% -> 98.5% | Helped |
| Use the proposed attack instead of JSMA | Targeted adversarial attacks against the 8-layer DNN · CIFAR10, Gaussian noise std=0.1 | success attack rate: 88.5% -> 94.0% | Helped |
| Use the proposed attack instead of JSMA | Targeted adversarial attacks against the 8-layer DNN · CIFAR10, Gaussian noise std=0.15 | success attack rate: 68.8% -> 77.8% | Helped |
| Use the proposed attack instead of JSMA | Targeted adversarial attacks against the 8-layer DNN · CIFAR10, Gaussian noise std=0.2 | success attack rate: 55.12% -> 68.5% | Helped |
| Use the proposed attack instead of JSMA | Targeted adversarial attacks against the 8-layer DNN · CIFAR10, Gaussian noise std=0.25 | success attack rate: 33.2% -> 62% | Helped |
| Use the proposed attack instead of FGSM | Targeted adversarial attacks against the 8-layer DNN · CIFAR10, JPEG compression | success attack rate: 52.3% -> 76% | Helped |
| Use the proposed attack instead of JSMA | Targeted adversarial attacks against the 8-layer DNN · MNIST | human perceptual distance: 80.34 -> 44.78 | Helped |
| Use the proposed attack instead of JSMA | Targeted adversarial attacks against the 8-layer DNN · CIFAR10 | human perceptual distance: 92.25 -> 51.98 | Helped |
Closest papers by meaning
- One Man's Trash Is Another Man's Treasure: Resisting Adversarial Examples by Adversarial Examples (CVPR 2020 · similarity 0.90)
- Imperceptible Adversarial Attack via Invertible Neural Networks (AAAI 2023 · similarity 0.89)
- Are adversarial examples inevitable? (ICLR 2019 · similarity 0.89)
- Adversarial Machine Learning at Scale (ICLR 2017 · similarity 0.89)
- Adversarial Example Games (NeurIPS 2020 · similarity 0.89)
- A Direct Approach to Robust Deep Learning Using Adversarial Networks (ICLR 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.