Research map / Learning theory and algorithms / Matrix and tensor methods
Improved Algorithms for White-Box Adversarial Streams
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 SIS-based sketches to detect inputs that violate the k-sparsity promise | White-box k-sparse recovery · k-sparse recovery | space: $\tilde{\mathcal{O}}(k)$ bits | Helped |
| Replace the previous L0 space bound with the sparse-recovery-based algorithm | White-box L0 estimation · L0-norm estimation | space: $\tilde{\mathcal{O}}(n^{1-\varepsilon+c\varepsilon})$ -> $\tilde{\mathcal{O}}(n^{1-\varepsilon})$ | Helped |
| Use SIS-based sketches to detect rank above k and recover low-rank matrices | White-box low-rank matrix recovery · low-rank matrix recovery | space: $\tilde{\mathcal{O}}(nk)$ bits | Helped |
| Use low-rank recovery to solve rank decision | White-box rank decision · rank decision | space: $\tilde{\mathcal{O}}(nk^2)$ -> $\tilde{\mathcal{O}}(nk)$ | Helped |
| Use deterministic Tutte-matrix entries and low-rank recovery | White-box maximum matching · maximum matching | space: $\tilde{\mathcal{O}}(nk)$ | Helped |
| Apply SIS-based detection alongside a fast recovery scheme | White-box robust PCA · robust PCA | space: $\tilde{\mathcal{O}}(nk+r)$ bits | Helped |
| Apply SIS-based detection alongside a fast tensor recovery scheme | White-box low-rank tensor recovery · low-rank tensor recovery | space: $\tilde{\mathcal{O}}(k(n_1 + \cdots n_d))$ bits | Helped |
Closest papers by meaning
- Fast White-Box Adversarial Streaming Without a Random Oracle (ICML 2024 · similarity 0.94)
- Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters (NeurIPS 2024 · similarity 0.88)
- The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm Estimation (NeurIPS 2025 · similarity 0.84)
- $\sigma$-zero: Gradient-based Optimization of $\ell_0$-norm Adversarial Examples (ICLR 2025 · similarity 0.84)
- Towards Efficient Training and Evaluation of Robust Models against $l_0$ Bounded Adversarial Perturbations (ICML 2024 · similarity 0.84)
- BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK (ICLR 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.