arXiv AI August 17, 2026 By Yingjie Ma, Zitong Yu, Wei Jia, Ajay Kumar, Linlin Shen

GBU-Palm: A Multimodal Video Dataset and Benchmark for Palm Presentation Attack Detection

arXiv:2608. 14389v1 Announce Type: cross Abstract: Existing palm presentation attack detection (PAD) datasets are often limited by static imagery, restricted acquisition conditions, or insufficient multimodal video data, hindering systematic evaluation across environments, modalities, and attack types.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

22h ago

Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs

arXiv:2604. 12616v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) expand the attack surface of safety-aligned systems by coupling visual perception with text generation.

By Jianhao Chen, Haoyang Chen, Hanjie Zhao, Haozhe Liang, Zheng Wang, Tieyun Qian

llms agents multimodal 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 Machine Learning

Jun 9

CHROMA: Detecting AI-Generated Images through Inter-Channel Color-Space Correlations

arXiv:2606. 08864v1 Announce Type: cross Abstract: The rapid adoption of diffusion and large-scale generative models has made it increasingly challenging to distinguish synthetic imagery from real photographs.

By Juan Pablo Sotelo, Marina Gardella, Pablo Mus\'e

diffusion benchmarks

Hugging Face Trending Papers

Jun 24

VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks

Recent advancements in Image-to-Video (I2V) generation have transformed input images from simple appearance references into interactive control interfaces where visual cues such as arrows, sketches, and emojis orchestrate complex video dynamics with unprecedented controllability. However, these seemingly innocuous static cues can be interpreted by models as executable temporal instructions, unfolding into harmful actions in the generated videos.

rag diffusion multimodal benchmarks safety

arXiv AI

Jul 21

ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments

arXiv:2607. 17077v1 Announce Type: cross Abstract: Adversarial attacks against vision models like object detectors are often evaluated under limited conditions, leaving their performance under-characterized.

By Mansi Phute, Alexander Greenhalgh, Matthew Hull, Haoran Wang, Alec Helbling, ShengYun Peng, Elliott Faa, Willian Lunardi, Martin Andreoni, Wenke Lee, Duen Horng Chau

safety

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

Related stories

Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs

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

CHROMA: Detecting AI-Generated Images through Inter-Channel Color-Space Correlations

VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks

ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments

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