AI Paper Atlas

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

Triangle Attack: A Query-Efficient Decision-Based Adversarial Attack

Xiaosen Wang, Zeliang Zhang, Kangheng Tong, Dihong Gong, Kun He, Zhifeng Li, Wei Liu

ECCV 2022 · Adversarial robustness and security › Black-box and transfer attacks · approach: Query-efficient black-box attacks · 67 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
optimize in the low-frequency space with a mask instead of the input space (ablation)Triangle Attack · ImageNet ResNet-18, RMSE 0.01attack success rate (%): 3.0 -> 51.5Improved
sample the line in frequency space rather than input space (perturbation still in input space) (ablation)Triangle Attack · ImageNet ResNet-18, RMSE 0.01attack success rate (%): 3.0 -> 22.5Improved
optimize the perturbation in frequency space rather than input space (ablation)Triangle Attack · ImageNet ResNet-18, RMSE 0.01attack success rate (%): 22.5 -> 25.5Improved
restrict to the low-frequency subspace (top 10%) rather than the full frequency space (ablation)Triangle Attack · ImageNet ResNet-18, RMSE 0.01attack success rate (%): 25.5 -> 51.5Improved
increase the low-frequency ratio (ablation)Triangle Attack · ImageNet ResNet-18, 1000 queriesattack success rate (%)Hurt
restrict each adversarial example to the decision boundary with binary search (increase N_bs) (ablation)Triangle Attack · ImageNet ResNet-18, RMSE 0.01attack success rate (%)Hurt
set gamma to 0.01 rather than 0.05 or 0.005 (ablation)Triangle Attack · ImageNet ResNet-18, RMSE 0.01attack success rate (%)Improved
increase lambda with gamma = 0.01 (ablation)Triangle Attack · ImageNet ResNet-18, RMSE 0.01attack success rate (%)Mixed
increase the dimension d of the directional line from 1 to 10 (ablation)Triangle Attack · ImageNet ResNet-18, 1000 queriesattack success rate (%)Hurt
increase the angle bound tau (ablation)Triangle Attack · ImageNet ResNet-18, 1000 queriesattack success rate (%)Hurt
Triangle Attack versus runner-up attack on ResNet-101Triangle Attack · ImageNet ResNet-101, RMSE 0.1/0.05/0.01attack success rate (%): 1.0%, 7.5% and 13.0%Improved
Triangle Attack versus Surfree on 1000 images of VGG-16Triangle Attack · ImageNet VGG-16 (1000 images), RMSE 0.01attack success rate (%): 36.5 -> 39.7Improved

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