Skip to main content
Search

Quentin Le Roux

1 related articles

Subscribe to updates
  1. arXiv

    Three practical defenses for face-recognition pipelines: catch poisoned identities during training, reject trigger-bearing inputs at inference

    For face-recognition pipelines whose training data may come from compromised third parties while the model is trained in-house, a set of three backdoor defenses is proposed and tested on realistic workloads: a training-time check flags poisoned identities from anomalously fast-rising intra-identity accuracy, and two inference-time checks compare a second detector's boxes and landmarks or cut-and-paste inputs onto held-out faces. On RetinaFace detectors and five feature extractors, detector pairing reached about 7.1% average false negative rate on FGA and about 0.6% on LSA, Cut-and-Mix stayed below 1% false negative rate on well-learned backdoors, and the training-time defense failed on clean-label backdoors.

You’re all caught up