閉じる

NEWS

Distinguished Paper Award at ICICS 2026: “Artistic Adversarial Examples”

2026.10.30
ICICS 2026 Distinguished Paper Award 表彰スライド

Our paper “Artistic Adversarial Examples: Graffiti-Based Adversarial Attacks on Traffic Sign Recognition,” a joint work between Waseda University (Mori Lab) and Politecnico di Milano, received the Distinguished Paper Award at the 28th International Conference on Information and Communications Security (ICICS 2026), held in Fukui, Japan, on October 27-30, 2026.

In this work, we propose artistic adversarial examples: adversarial patches crafted to look like ordinary street graffiti so that they blend naturally into urban scenes. Combining a graffiti-trained generative model with a two-stage optimization that couples white-box latent optimization and black-box placement refinement, the attack degrades traffic sign recognition while keeping the perturbations visually plausible. Experiments across digital, simulated, and physical settings show that the generated graffiti substantially disrupts traffic sign recognition, achieving up to a 72.8% attack success rate with an average confidence drop of 65.8%.

[Paper]
Zhenghao Michele Zhuge, Go Tsuruoka, Zhihe Zhang, Stefano Longari, Lachlan Moore, Stefano Zanero, Tatsuya Mori, “Artistic Adversarial Examples: Graffiti-Based Adversarial Attacks on Traffic Sign Recognition,” Proceedings of the 28th International Conference on Information and Communications Security (ICICS 2026), LNCS 17214, pp. 198-219, Fukui, Japan, October 2026. (Distinguished Paper Award)

ICICS 2026 website / Paper (Springer)