arXiv AI
Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Oct 8
Detecting Adversarial Images through Response Profiles of Vision-Language Models
arXiv:2610.10436v1 Announce Type: new Abstract: Adversarial perturbations can alter the predictions of frozen vision-language models (VLMs) while leaving their confidence and image--text similarity p...
Hugging Face Trending Papers
Jun 2
Investigating Adversarial Robustness of Multi-modal Large Language Models
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.
arXiv Machine Learning
Sep 1
ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcity
arXiv:2608.29510v1 Announce Type: cross Abstract: Aerial object detection is increasingly deployed in real-world applications, but models remain vulnerable to physical, universal adversarial patches...
arXiv AI
Oct 7
Transferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving
arXiv:2610.08331v1 Announce Type: cross Abstract: The rapid integration of Vision Language Models (VLMs) into sensitive systems introduces critical safety vulnerabilities that remain unexplored in ex...
arXiv Computer Vision
Aug 24
Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer
arXiv:2608.20748v1 Announce Type: new Abstract: The Visual Geometry Grounded Transformer (VGGT) enables unified feed-forward 3D reconstruction from multi-view images. However, deploying such a high-p...
Hugging Face Trending Papers
Jul 21
Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model
While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.