Darker than Black-Box: Face Reconstruction from Similarity Queries
- URL: http://arxiv.org/abs/2106.14290v1
- Date: Sun, 27 Jun 2021 17:25:46 GMT
- Title: Darker than Black-Box: Face Reconstruction from Similarity Queries
- Authors: Anton Razzhigaev, Klim Kireev, Igor Udovichenko, Aleksandr Petiushko
- Abstract summary: We propose a novel approach that allows reconstructing the face querying only similarity scores of the black-box model.
While our algorithm operates in a more general setup, experiments show that it is query efficient and outperforms the existing methods.
- Score: 65.62256987706128
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Several methods for inversion of face recognition models were recently
presented, attempting to reconstruct a face from deep templates. Although some
of these approaches work in a black-box setup using only face embeddings,
usually, on the end-user side, only similarity scores are provided. Therefore,
these algorithms are inapplicable in such scenarios. We propose a novel
approach that allows reconstructing the face querying only similarity scores of
the black-box model. While our algorithm operates in a more general setup,
experiments show that it is query efficient and outperforms the existing
methods.
Related papers
- Inverting Black-Box Face Recognition Systems via Zero-Order Optimization in Eigenface Space [43.698488201196746]
Reconstructing facial images from black-box recognition models poses a significant privacy threat.<n>This paper introduces DarkerBB, a novel approach that reconstructs color faces by performing zero-order optimization within a PCA-derived eigenface space.<n>Experiments on LFW, AgeDB-30, andFP benchmarks demonstrate that DarkerBB achieves state-of-the-art verification accuracies in the similarity-only setting, with competitive query efficiency.
arXiv Detail & Related papers (2025-06-11T14:15:18Z) - What You See is What You Classify: Black Box Attributions [61.998683569022006]
We train a deep network, the Explainer, to predict attributions for a pre-trained black-box classifier, the Explanandum.
Unlike most existing approaches, ours is capable of directly generating very distinct class-specific masks.
We show that our attributions are superior to established methods both visually and quantitatively.
arXiv Detail & Related papers (2022-05-23T12:30:04Z) - Restricted Black-box Adversarial Attack Against DeepFake Face Swapping [70.82017781235535]
We introduce a practical adversarial attack that does not require any queries to the facial image forgery model.
Our method is built on a substitute model persuing for face reconstruction and then transfers adversarial examples from the substitute model directly to inaccessible black-box DeepFake models.
arXiv Detail & Related papers (2022-04-26T14:36:06Z) - Dynamic Facial Expression Recognition under Partial Occlusion with
Optical Flow Reconstruction [20.28462460359439]
We propose a new solution based on an auto-encoder with skip connections to reconstruct the occluded part of the face in the optical flow domain.
Our experiments show that the proposed method reduce significantly the gap, in terms of recognition accuracy, between occluded and non-occluded situations.
arXiv Detail & Related papers (2020-12-24T12:28:47Z) - Black-Box Face Recovery from Identity Features [61.950765357647605]
We attack the state-of-the-art face recognition system (ArcFace) to test our algorithm.
Our algorithm requires a significantly less number of queries compared to the state-of-the-art solution.
arXiv Detail & Related papers (2020-07-27T15:25:38Z) - The Power of Triply Complementary Priors for Image Compressive Sensing [89.14144796591685]
We propose a joint low-rank deep (LRD) image model, which contains a pair of complementaryly trip priors.
We then propose a novel hybrid plug-and-play framework based on the LRD model for image CS.
To make the optimization tractable, a simple yet effective algorithm is proposed to solve the proposed H-based image CS problem.
arXiv Detail & Related papers (2020-05-16T08:17:44Z) - GeoDA: a geometric framework for black-box adversarial attacks [79.52980486689287]
We propose a framework to generate adversarial examples in one of the most challenging black-box settings.
Our framework is based on the observation that the decision boundary of deep networks usually has a small mean curvature in the vicinity of data samples.
arXiv Detail & Related papers (2020-03-13T20:03:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.