Research map / Adversarial robustness and security / Attacks on text and graphs
Unadversarial Examples: Designing Objects for Robust Vision
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 |
|---|---|---|---|
| Add a class-specific unadversarial patch 20 times smaller than the image | Pre-trained ImageNet classifier · ImageNet validation | accuracy: 26.3% | Helped |
| Add a class-specific unadversarial patch 5% the size of the image | Pre-trained ImageNet classifier · ImageNet-C | accuracy across corruptions: 31.7% points | Helped |
| Use a random training image instead of the best-loss training image as the patch | Best-training-image patch baseline · ImageNet and CIFAR-10 | performance | Hurt |
| Replace optimized patches with predefined fixed random Gaussian-noise patches and train the classifier on boosted data | ImageNet and CIFAR-10 classifiers · ImageNet-C and CIFAR-10-C | performance across corruptions | Hurt |
| Vary patch-training learning rate among 0.1, 0.01, and 0.001 (ablation) | Unadversarial patches · ImageNet and CIFAR-10 | performance | No clear effect |
Closest papers by meaning
- Progress and Limitations of Deep Networks to Recognize Objects in Unusual Poses (AAAI 2023 · similarity 0.88)
- Synthesizing Robust Adversarial Examples (ICML 2018 · similarity 0.88)
- Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization (CVPR 2023 · similarity 0.86)
- A Combination of Noise and Bilateral Filters Achieve Supralinear and Scalable Adversarial Robustness in CNNs (CVPR 2026 · similarity 0.85)
- Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models (NeurIPS 2023 · similarity 0.85)
- Harnessing Edge Information for Improved Robustness in Vision Transformers (AAAI 2024 · similarity 0.84)
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.