AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

CAG: A Real-Time Low-Cost Enhanced-Robustness High-Transferability Content-Aware Adversarial Attack Generator

Huy Phan, Yi Xie, Siyu Liao, Jie Chen, Bo Yuan

AAAI 2020 · Adversarial robustness and security › Black-box and transfer attacks · approach: Transfer attacks on face recognition · 18 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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 changedWhereMeasuredEffect
Replace iterative optimization with a U-Net generatorCAG on CIFAR-10 · CIFAR-10Generation time: 12m56s -> 1.44sImproved
Add perturbation dropout, increasing p from 0.0 to 0.3 (ablation)CAG · CIFAR-10 black-boxASR: 83.78% -> 89.24%Improved
Add perturbation dropout, increasing p from 0.0 to 0.1 (ablation)CAG · CIFAR-10 black-boxASR: 83.78% -> 85.92%Improved
Add perturbation dropout, increasing p from 0.1 to 0.2 (ablation)CAG · CIFAR-10 black-boxASR: 85.92% -> 87.85%Improved
Add perturbation dropout, increasing p from 0.2 to 0.3 (ablation)CAG · CIFAR-10 black-boxASR: 87.85% -> 89.24%Improved
Train one generator with label embeddings rather than separate generators for each target classCAG · ImageNet 1000 targeted classesStorage: 30 MB × 1000 -> 222 MBImproved
Use a content-aware generator with CAM supervision instead of GAP U-NetCAG · ImageNet 5 targeted classes, black-boxASR: 85.66% -> 94.62%Improved
Use a content-aware generator with CAM supervision instead of GAP U-NetCAG · ImageNet 5 targeted classes, white-boxASR: 98.09% -> 97.71%Mixed
Constrain perturbations using CAM informationCAG · ImageNet, Pixel DeflectionClassification accuracy after defense: 27.63%Improved
Use ensemble classifiers for ImageNet CAG trainingCAG · ImageNetOverfittingImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy