Auditing Traffic-Sign Robustness via DDIM Inversion: Do Diffusion Latents Preserve Shadow Attacks?

Jan 1, 2026·

Ashton B McEntarffer

,

Amir Salarpour

,

Pedram MohajerAnsari

Mert D. Pesé

Mert D. Pesé

· 0 min read

Type

Conference paper

Publication

The 6th Workshop of Adversarial Machine Learning on Computer Vision: Safety of Vision-Language Agents

Last updated on Jan 1, 2026

Mert D. Pesé

Authors

Assistant Professor

My research interests broadly lie in automotive security and privacy.

← Toward Inherently Robust VLMs Against Visual Perception Attacks Jan 13, 2026

Comparative Analysis of Patch Attack on VLM-Based Autonomous Driving Architectures Jan 1, 2026 →