AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

FaceSec: A Fine-Grained Robustness Evaluation Framework for Face Recognition Systems

Liang Tong, Zhengzhang Chen, Jingchao Ni, Wei Cheng, Dongjin Song, Haifeng Chen, Yevgeniy Vorobeychik

CVPR 2021 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training with feature consistency · 20 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
Expose the target architecture rather than the training set to the attackerFaceNet closed-set system, sticker dodging · Closed-set VGGFace2 subsetattack success rate: 0.01 -> 0.92Improved
Use grid-level face-mask rather than pixel-level sticker perturbationsClosed-set systems, zero-knowledge dodging · Closed-set VGGFace2 subsetattack success rateMixed
Attack open-set rather than closed-set recognitionFace recognition systems under zero-knowledge dodging · LFW and closed-set VGGFace2 subsetattack success rateImproved
Use a universal face-mask perturbation rather than other universal perturbation typesClosed-set systems, N=20 · Closed-set VGGFace2 subsetattack success rate: 0.91 for FaceNet; 0.08 for ArcFace18 eyeglass-frame attackImproved
Increase the number of inputs sharing one universal perturbationClosed-set PGD, eyeglass-frame, and sticker attacks · Closed-set VGGFace2 subsetattack success rate: 0.94 -> 0.15 for VGGFace PGD; 0.98 -> 0.09 for VGGFace stickerHurt
Add momentum to the single-surrogate PGD transfer attack (ablation)FaceNet closed-set system · Closed-set VGGFace2 subset, training-set knowledgeattack success rate: 0.42 -> 0.52Improved
Replace a single surrogate with an ensemble surrogate for PGD transfer (ablation)FaceNet closed-set system · Closed-set VGGFace2 subset, training-set knowledgeattack success rate: 0.42 -> 0.73Improved
Add momentum to an ensemble-surrogate PGD transfer attack (ablation)FaceNet closed-set system · Closed-set VGGFace2 subset, training-set knowledgeattack success rate: 0.73 -> 0.83Improved
Use ensemble and momentum transfer techniques for sticker attacks (ablation)Closed-set face recognition systems · Closed-set VGGFace2 subset, training-set knowledgeattack success rate: 0.00 -> 0.01 on FaceNetNo clear effect
Apply DOA adversarial training against face-mask perturbationsFour of five closed-set systems · Closed-set systems, dodgingattack success rateNo clear effect
Apply DOA adversarial training to FaceNet against face-mask attacksFaceNet closed-set system · Closed-set systems, dodgingattack success rate: 1.0 -> 0.24Improved
Generalize robustness from one perturbation type to anotherDOA-retrained face recognition systems · Closed-set systems, physically realizable attacksattack success rateMixed

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