arXiv Computer Vision

Tomatoes, Potatoes, and Onions: Questioning the Need for Faces in Face Presentation Attack Detection

arXiv AI

Jul 3

CPG-PAD: Concept-Informed Prompts Guided Presentation Attack Detection

arXiv:2607. 01303v1 Announce Type: cross Abstract: Presentation Attack Detection (PAD) serves as a crucial safeguard for face recognition systems against presentation attacks such as printed photos, replayed videos, and 3D masks.

By Haoyuan Zhang, Xiangyu Zhu, Li Gao, Ajian Liu, Siran Peng, Zhen Lei

llms multimodal benchmarks

arXiv Machine Learning

Jul 30

Foundation Models for Face Presentation Attack Detection: A Unified Linear-Probing Benchmark

arXiv:2607. 26993v1 Announce Type: new Abstract: Face presentation attack detection (PAD) remains challenging under cross-dataset evaluation, where domain shift degrades models trained on a single dataset.

By Peter Lorenz, Anjith George, S\'ebastien Marcel

llms multimodal benchmarks

arXiv Machine Learning

Aug 11

LoRA-based Adaptation Alone Is Not Enough: Understanding the Limits of Foundation Models for Face Presentation Attack Detection

arXiv:2608. 09633v1 Announce Type: cross Abstract: Face presentation attack detection (PAD) aims to reliably detect a wide range of presentation attacks.

By Peter Lorenz, Anjith George, Marcel S\'ebastien

llms fine-tuning benchmarks

arXiv Machine Learning

Jun 11

Adv-TGD: Adversarial Text-Guided Diffusion for Face Recognition Impersonation Attacks

arXiv:2606. 11615v1 Announce Type: cross Abstract: The widespread adoption of face recognition (FR) technologies raises serious privacy concerns, as facial data can be exploited without consent.

By Omid Ahmadieh, Nima Karimian

llms rag diffusion robotics fine-tuning multimodal benchmarks safety

arXiv Computer Vision

Sep 1

Foundation and Multimodal Large Language Models for Face Presentation and Morph Attack Detection

arXiv:2608.29802v1 Announce Type: new Abstract: Face recognition systems are increasingly deployed in security-critical applications, yet they remain vulnerable to presentation and morph attacks. Pre...

By Hatef Otroshi Shahreza, Asif Hussain Khan, Peter Lorenz, Alain Komaty, S\'ebastien Marcel

llms fine-tuning multimodal benchmarks

arXiv AI

Aug 3

DiffAttack: Evasion Attacks Against Face Recognition via Latent Diffusion Models

arXiv:2607. 28936v1 Announce Type: cross Abstract: Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space.

By Omid Ahmadieh, Nima Karimian

rag diffusion benchmarks safety

arXiv Computer Vision

Aug 25

Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing

arXiv:2608.17351v2 Announce Type: replace Abstract: Open-world face anti-spoofing must address both covariate and semantic shifts: source and target domains differ in imaging conditions, while target...

By Fangling Jiang, Qi Li, Bing Liu, Weining Wang, Quilin Huang, Zhenan Sun, Ming-Hsuan Yang

llms benchmarks

arXiv Machine Learning

Sep 22

StyleAT: Defending Face Recognition Against Semantic Attacks

arXiv:2609.23596v1 Announce Type: cross Abstract: With face-recognition models now embedded in everyday authentication and surveillance, recent works have pinpointed a critical weakness: these models...

By Ben Shapira, Roi Cohen, Shang-Tse Chen, Mahmood Sharif

diffusion benchmarks safety

arXiv Machine Learning

Aug 5

SRAP: SVD-Refined Adversarial Perturbations for Imperceptible Face-Swap Defense

arXiv:2608. 03395v1 Announce Type: cross Abstract: Deepfake technologies pose increasing threats to facial privacy and identity security, motivating proactive defenses that protect facial images before misuse.

By Sungwon Cho, Kwanghyun Ko, Myungjoo Kang

safety

arXiv AI

Sep 3

Swin Meets EfficientNet: Lightweight Architectures for GAN-Based Face Forensics

The paper presents lightweight architectures for detecting GAN-generated synthetic faces, comparing a compact Swin Transformer, pre‑trained Swin‑Tiny and Swin‑Small models, and a hybrid EfficientNet‑B0 + Swin Transformer. Using the 140K Real and Fake Faces dataset, the hybrid model achieved 99% accuracy and 99.44% recall on 5,000 test images, outperforming both pure Swin variants and a CNN‑only baseline. The study demonstrates that combining hierarchical CNN features with shifted‑window self‑attention yields an efficient, computationally lightweight detection method.

By Sejuti Basu, Ashima Sood, Vijay Kumar, Sahil Sharma

llms diffusion computer-vision

arXiv AI

Jul 17

Benchmarking Face Recognition without Real Faces

arXiv:2607. 14932v1 Announce Type: cross Abstract: Synthetic face datasets have become effective enough to train face recognition models with accuracy rivaling that of models trained on real photographs.

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

llms benchmarks safety

Hugging Face Trending Papers

Aug 17

Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching

Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical security vulnerabilities. Existing methods typically rely on indirect guidance or highly stochastic guidance, making it difficult to stably optimize generation trajectories toward target facial images.

diffusion benchmarks

Related stories