Research map / Adversarial robustness and security / Black-box and transfer attacks
Efficient Decision-Based Black-Box Adversarial Attacks on Face Recognition
Yinpeng Dong, Hang Su, Baoyuan Wu, Zhifeng Li, Wei Liu, Tong Zhang, Jun Zhu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use evolutionary search with covariance adaptation and reduced-dimensional coordinate search instead of Optimization | decision-based face recognition attacks · LFW face verification, CosFace, 5,000 queries | MSE: 2.9e-3 -> 9.1e-5 | Improved |
| add covariance matrix adaptation (ablation) | Evolutionary attack · LFW face verification, SphereFace, 10,000 queries, dodging | MSE: 2.6e-4 -> 2.4e-4 | Improved |
| add stochastic coordinate selection (ablation) | Evolutionary attack with CMA · LFW face verification, SphereFace, 10,000 queries, dodging | MSE: 2.4e-4 -> 1.7e-4 | Improved |
| select coordinates proportional to covariance diagonal rather than uniformly (ablation) | Evolutionary attack with CMA and SCS · LFW face verification, SphereFace, 10,000 queries, dodging | MSE: 2.0e-4 -> 1.7e-4 | Improved |
| reduce the search-space dimension (ablation) | Evolutionary attack · LFW face verification, dodging and impersonation | MSE | Mixed |
Closest papers by meaning
- Unravelling Robustness of Deep Learning Based Face Recognition Against Adversarial Attacks (AAAI 2018 · similarity 0.89)
- Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models (ICLR 2018 · similarity 0.88)
- Black-box Adversarial Attacks with Limited Queries and Information (ICML 2018 · similarity 0.88)
- Heuristic Black-Box Adversarial Attacks on Video Recognition Models (AAAI 2020 · similarity 0.88)
- Practical No-box Adversarial Attacks against DNNs (NeurIPS 2020 · similarity 0.88)
- FaceSec: A Fine-Grained Robustness Evaluation Framework for Face Recognition Systems (CVPR 2021 · similarity 0.87)
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.
