Research map / Adversarial robustness and security / Black-box and transfer attacks
Boosting Black-Box Attack With Partially Transferred Conditional Adversarial Distribution
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 |
|---|---|---|---|
| Use transferred c-Glow mapping parameters and adapt Gaussian parameters with target queries | CIFAR-10 untargeted attacks · ResNet, DenseNet, VGG, and PyramidNet targets | mean queries: 135.1 -> 81.6; 111.7 -> 43.3; 125.5 -> 56.4; 82.3 -> 30.1 | Helped |
| Use transferred c-Glow mapping parameters and adapt Gaussian parameters with target queries | CIFAR-10 targeted attacks to class 0 · ResNet, DenseNet, VGG, and PyramidNet targets | mean queries: 894.1 -> 696.4; 826.9 -> 787.1; 1343.2 -> 861.1; 865.8 -> 651.2 | Helped |
| Use transferred c-Glow mapping parameters and adapt Gaussian parameters with target queries | CIFAR-10 untargeted attacks · ResNet, DenseNet, VGG, and PyramidNet targets | ASR: 100.0; 100.0; 99.9; 100.0 | Helped |
| Use transferred c-Glow mapping parameters and adapt Gaussian parameters with target queries | CIFAR-10 targeted attacks to class 0 · ResNet, DenseNet, VGG, and PyramidNet targets | ASR: 99.9; 100.0; 98.8; 98.9 | Mixed |
Closest papers by meaning
- Attacking deep networks with surrogate-based adversarial black-box methods is easy (ICLR 2022 · similarity 0.93)
- Enhancing Adversarial Transferability with Checkpoints of a Single Model's Training (CVPR 2025 · similarity 0.90)
- Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior (ICML 2024 · similarity 0.90)
- LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate (AAAI 2024 · similarity 0.90)
- Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks (ICLR 2024 · similarity 0.89)
- Enhancing Adversarial Transferability with Adversarial Weight Tuning (AAAI 2025 · similarity 0.89)
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.