Futa Waseda
Futa Waseda
Home
Projects
Publications
Contact
CV
EN
日本語
Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection
Lukas Strack
,
Futa Waseda
,
Huy H. Nguyen
,
Yinqiang Zheng
,
Isao Echizen
October 2024
Paper
Slides
DOI
GitHub
Cite
TL;DR
Infrared human detection gains a patch defense
: POD addresses physically realizable adversarial patches.
Patch-aware training detects people and attacks
: Augments training images with random patches and learns to locate them.
Defense generalizes to unseen patches
: Improves robustness across patch shapes and sizes while also improving clean precision.
Type
Conference paper
Publication
ICIP 2024
Presentation Slides
PDF
←
1 / 11
→
Recent
Futa Waseda
Project Assistant Professor
Related
【WACV 2023】Closer Look at the Transferability of Adversarial Examples: How They Fool Different Models Differently
【SMC 2026】Semantic Color Naturalness Breaker: Preventing Illegitimate Colorization via Content-Aware Color Priors
【APSIPA ASC 2025】Uncolorable Examples: Preventing Unauthorized AI Colorization via Perception-Aware Chroma-Restrictive Perturbation
【WACV 2026】Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships
【ACM MM 2025】Quality Text, Robust Vision: The Role of Language in Enhancing Visual Robustness of Vision-Language Models
Cite
×