Hugging Face Trending Papers August 17, 2026

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

Read the original on Hugging Face Trending Papers →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI

1d ago

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

arXiv:2608. 16791v1 Announce Type: cross Abstract: Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical security vulnerabilities.

By Ye Lu, Shen Wang, Zhaoyang Zhang, Yihan Yan, Li Liu, Runze Liu, Fanghui Sun

diffusion 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

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 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 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 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

Related stories

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

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

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

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

DiffAttack: Evasion Attacks Against Face Recognition via Latent Diffusion Models

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