3 papers
cs.CV2026
Discovering Natural Transformation Vulnerabilities in Black-Box Vision Models
Dongsu Song, DaeYun GO, Jay Hoon Jung
Natural adversarial examples (NAEs) reveal that vision models can fail under realistic semantic changes beyond norm-bounded perturbations. However, generating NAEs in a black-box s…
cs.CV2026
SegPAR: Class-Centric Decision-Based Sparse Attack for Semantic Segmentation
Dongsu Song, DaeYun GO, Boseung Seo +1
Despite the practical relevance of sparse decision-based black-box threats, they have received limited attention in semantic segmentation. To bridge this gap, we adapt the most rep…
cs.CV2025
Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
Dongsu Song, Daehwa Ko, Jay Hoon Jung
It is well known that query-based attacks tend to have relatively higher success rates in adversarial black-box attacks. While research on black-box attacks is actively being condu…