Research map / Adversarial robustness and security / Attacks on text and graphs
Frequency-Driven Imperceptible Adversarial Attack on Semantic Similarity
Check 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 self-paced weighting to SSA (ablation) | SSA · ImageNet-1K | FID: 5.83 -> 4.63 | Helped |
| Add self-paced weighting to SSA (ablation) | SSA · ImageNet-1K | ℓ2: 3.12 -> 2.34 | Helped |
| Add the low-frequency constraint (ablation) | SSA · ImageNet-1K | LF: 1.05 -> 0.06 | Helped |
| Use SSAH instead of C&W ℓ2 | ResNet-50 attack on ImageNet-1K · ImageNet-1K | FID: 12.14 -> 3.90 | Helped |
| Use SSAH instead of C&W ℓ2 | ResNet-50 attack on ImageNet-1K · ImageNet-1K | ASR (%): 99.27 -> 98.01 | Hurt |
| Increase low-frequency constraint weight λ at m = 0.4 from 0.00 to 1.00 (ablation) | SSAH · CIFAR-10 | ASR (%): 82.02% -> 60.98% | Hurt |
| Vary batch size from 32 to 10000 (ablation) | SSAH · CIFAR-10 | ASR (%): 99.94 -> 99.94 | No clear effect |
Closest papers by meaning
- Mutual-Modality Adversarial Attack with Semantic Perturbation (AAAI 2024 · similarity 0.86)
- FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks (AAAI 2024 · similarity 0.86)
- Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature (AAAI 2025 · similarity 0.86)
- Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective (NeurIPS 2024 · similarity 0.86)
- DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain (NeurIPS 2024 · similarity 0.86)
- Wide Two-Layer Networks can Learn from Adversarial Perturbations (NeurIPS 2024 · similarity 0.86)
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.