arXiv Computer Vision
Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
5d ago
Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models
arXiv:2610.15343v1 Announce Type: cross Abstract: World models and video understanding models are increasingly deployed in dynamic visual environments, yet their robustness to physical adversarial th...
arXiv Machine Learning
Sep 10
ComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflages
ComplicitSplat is a novel black‑box attack that leverages 3D Gaussian Splatting (3DGS) shading to create viewpoint‑specific camouflage, embedding adversarial content into scene objects that is only visible from certain angles. The method does not require access to model architecture or weights and can successfully fool a range of popular object detectors—including single‑stage, multi‑stage, and transformer‑based models—on both real‑world physical objects and synthetic scenes. This demonstrates that downstream models using 3DGS are vulnerable to adversarial manipulation.
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
Jul 17
GeoDetect: Geometric Adversarial Detection for VLPs
arXiv:2607. 14737v1 Announce Type: cross Abstract: Vision-language pre-trained models (VLPs) are widely used in real-world applications.
arXiv AI
Aug 20
Breaking the weakest link to evade vision language models
The paper investigates how Vision Language Models (VLMs) can be fooled by small, human‑imperceptible changes to images. It introduces a gradient‑based attack that targets only the vision encoder, reducing computational cost while still effectively disrupting both untargeted and targeted multimodal alignment. Experiments on open‑source VLMs such as Qwen2.5‑VL, Granite‑Vision, FastVLM, and Phi‑3.5‑Vision demonstrate that these perturbations can significantly alter the models’ textual outputs.
arXiv Machine Learning
Jun 11
Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks
arXiv:2605. 31219v2 Announce Type: replace-cross Abstract: While decision-based black-box adversarial attacks present a severe security threat, current methodologies suffer from fundamental limitations.