arXiv Machine Learning July 20, 2026 By Tyler Fitzsimmons, Adam Czajka

Intentional Electromagnetic Interference Attacks on Facial Recognition

Read the original on arXiv Machine Learning →

arXiv:2607. 15512v1 Announce Type: cross Abstract: Attacks on general computer vision algorithms are often relegated to the digital domain, with the optimization performed purely in the digital world and then translated to physical mediums for implementation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Aug 3

Have I Seen You? Embedding Behavior Signals Synthetic Face Dataset Membership

arXiv:2607. 29144v1 Announce Type: cross Abstract: Synthetic face datasets are increasingly used to reduce privacy exposure and data access constraints in biometric recognition.

By Pawe{\l} Borsukiewicz, Daniele Lunghi, Wendk\^uuni C. Ou\'edraogo, Jacques Klein, Tegawend\'e F. Bissyand\'e

rag safety

arXiv Machine Learning

Aug 6

Model Inversion meets Cryptographic Fuzzy Extractors

arXiv:2510. 25687v4 Announce Type: replace-cross Abstract: Model inversion attacks pose an open challenge to privacy-sensitive applications that use machine learning (ML) models.

By Mallika Prabhakar, Louise Xu, Prateek Saxena

rag safety

arXiv Computer Vision

Aug 24

Breaking High Confidence: Practical Face Impersonation under High-Security Thresholds

arXiv:2608.20884v1 Announce Type: new Abstract: Face recognition systems (FRSs) are increasingly deployed in critical real-world services for authentication, such as banking applications and airport...

By Changjin Kim, Seunghun Paik, Dongsoo Kim, Jae Hong Seo

benchmarks

arXiv Machine Learning

Sep 4

Selfie-Capture Dynamics as an Auxiliary Signal Against Deepfakes and Injection Attacks for Mobile Identity Verification

The paper investigates whether passive motion traces recorded during selfie capture can serve as an auxiliary signal for detecting spoofing and verifying users in mobile remote identity verification systems. It introduces the CanSelfie dataset, comprising 375 multi‑sensor sequences from 30 participants, and evaluates seven time‑series classifiers and eight anomaly detectors across various sensor configurations. Results show that accelerometer‑only classifiers achieve very low false rejection rates, while certain models achieve low false acceptance rates and high verification accuracy, indicating that selfie‑capture motion is a promising low‑friction evidence channel.

By Erkka Rantahalvari, Olli Silv\'en, Zinelabidine Boulkenafet, Constantino \'Alvarez Casado

benchmarks

arXiv AI

Jun 11

On the Study of Biometric Spoofing Detection using Deep Learning

arXiv:2606. 11505v1 Announce Type: cross Abstract: Biometric systems are increasingly deployed in security applications; however, they remain vulnerable to spoofing attacks, in which attackers exploit counterfeit biometric data to gain unauthorized access.

By Kumar Kartikey, Nikos Komninos

fine-tuning benchmarks

arXiv Computer Vision

1d ago

A Valid Watermark Is Not a Valid Identity: Spatial-Spectral Adversarial Face Evasion with Watermark Preservation

arXiv:2610.20278v1 Announce Type: new Abstract: Facial image watermarking can support traceability and certification in biometric pipelines, but provenance or manipulation detection alone does not gu...

By Jefferson David Rodriguez Chivata, Davide Ghiani, Simone Maurizio La Cava, Marco Micheletto, Giulia Orr\`u, Gian Luca Marcialis

robotics safety