Research map / Adversarial robustness and security / Certified and empirical robustness
Sparse and Imperceptible Adversarial Attack via a Homotopy Algorithm
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 Homotopy-Attack instead of GreedyFool | targeted CIFAR-10 attacks · CIFAR-10 targeted attack, average case | ℓ0: 289 -> 165 | Helped |
| use Homotopy-Attack instead of GreedyFool | targeted ImageNet attacks · ImageNet targeted attack, average case | ℓ0: 10837 -> 2706 | Helped |
| use Homotopy-Attack instead of GreedyFool | nontargeted CIFAR-10 attacks · CIFAR-10 nontargeted attack | ℓ0: 116 -> 72 | Helped |
| use Homotopy-Attack instead of GreedyFool | nontargeted ImageNet attacks · ImageNet nontargeted attack | ℓ0: 1128 -> 387 | Helped |
| add additional ℓ0 change control and post-attack perturbation to Pure-Homotopy (ablation) | Homotopy-Attack · CIFAR-10 targeted ablation | ℓ0: 223 -> 168 | Helped |
| add additional ℓ0 change control and post-attack perturbation to Pure-Homotopy (ablation) | Homotopy-Attack · ImageNet targeted ablation | ℓ0: 16343 -> 2889 | Helped |
| replace nmAPG with binary weight search by the full homotopy attack (ablation) | CIFAR-10 targeted attacks · CIFAR-10 targeted ablation | ℓ0: 283 -> 168 | Helped |
| replace nmAPG with binary weight search by the full homotopy attack (ablation) | ImageNet targeted attacks · ImageNet targeted ablation | ℓ0: 13582 -> 2889 | Helped |
Closest papers by meaning
- Transferable Structural Sparse Adversarial Attack Via Exact Group Sparsity Training (CVPR 2024 · similarity 0.89)
- $\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples (ICLR 2025 · similarity 0.89)
- Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations (ICML 2024 · similarity 0.88)
- GSE: Group-wise Sparse and Explainable Adversarial Attacks (ICLR 2025 · similarity 0.88)
- AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks (NeurIPS 2024 · similarity 0.87)
- BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK (ICLR 2024 · similarity 0.87)
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.