AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Simulated Adversarial Testing of Face Recognition Models

Nataniel Ruiz, Adam Kortylewski, Weichao Qiu, Cihang Xie, Sarah Adel Bargal, Alan Yuille, Stan Sclaroff

CVPR 2022 · Adversarial robustness and security › Attacks on text and graphs · approach: Diffusion-based adversarial purification · 8 citations (OpenAlex)

Check 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
Use policy-gradient adversarial testing instead of uniform random samplingCBAM-ResNet50 with ArcFace · Synthetic face verification, 15 shape and 15 texture parametersaccuracy: 99% -> 36%Hurt
Use policy-gradient adversarial testing instead of uniform random samplingCBAM-ResNet50 with ArcFace · Synthetic face verification, 15 shape and 15 texture parametersAvg. Cosine Similarity: 0.518 -> 0.263Hurt
Use policy-gradient adversarial testing rather than random sampling or random optimizationFace recognition models · Synthetic face verification, 30 shape, 30 texture, and 2 pose parametersaccuracy: ArcFace CBAM-ResNet50: 99.9% -> 49%; CosFace CBAM-ResNet50: 99.9% -> 57%; ArcFace SE-CBAM-ResNet50: 99.8% -> 34%; ArcFacHurt
Filter negative-yaw images from trainingCBAM-ResNet50 with ArcFace · Synthetic face verification, yaw [-1.0, -0.5]Area Between Curves: 8.69Hurt
Filter positive-yaw images from trainingCBAM-ResNet50 with ArcFace · Synthetic face verification, yaw [0.5, 1.0]Area Between Curves: 8.46Hurt
Test with adversarial simulator parameters instead of random samplingArcFace CBAM-ResNet50 · Synthetic face verification, 30 shape, 30 texture, and 2 pose parametersadversarial samples found: one adversarial sample over 1,000 iterations -> 51 adversarial samples over 12,587 iterationsImproved

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