Research map / Adversarial robustness and security / Certified and empirical robustness
Thwarting Adversarial Examples: An $L_0$-Robust Sparse Fourier Transform
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 L0-robust DCT correction before classification | Fashion-MNIST CNN under JSMA with 30 corrupted pixels · Fashion-MNIST, JSMA (30 pixels) | accuracy: 24.8% -> 83.1% | Helped |
| Apply L0-robust DCT correction before classification | Fashion-MNIST CNN under CW attack · Fashion-MNIST, CW | accuracy: 0% -> 85.7% | Helped |
| Apply Patchwise IHT to detect and remove the contiguous patch | ResNet-50 · ImageNet, adversarial patch | Top-5 accuracy: 63.9% -> 80.4% | Helped |
| Apply Patchwise IHT to detect and remove the contiguous patch | ResNet-50 · ImageNet, adversarial patch | Top-1 accuracy: 12.0% -> 59.7% | Helped |
| Train on top-k 2D-DCT-projected images rather than original images | MNIST classifier · MNIST | accuracy: <1% | Hurt |
| Train on top-k 2D-DCT-projected images rather than original images | Fashion-MNIST classifier · Fashion-MNIST | accuracy: <2.5% | Hurt |
Closest papers by meaning
- Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation (AAAI 2020 · similarity 0.89)
- $\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples (ICLR 2025 · similarity 0.88)
- Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations (ICML 2024 · similarity 0.87)
- BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK (ICLR 2024 · similarity 0.87)
- The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm Estimation (NeurIPS 2025 · similarity 0.86)
- DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms (NeurIPS 2024 · similarity 0.85)
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.