3 papers
cs.CV2024
Composite Concept Extraction through Backdooring
Banibrata Ghosh, Haripriya Harikumar, Khoa D Doan +2
Learning composite concepts, such as \textquotedbl red car\textquotedbl , from individual examples -- like a white car representing the concept of \textquotedbl car\textquotedbl{}…
cs.LG2024
Revisiting the Dataset Bias Problem from a Statistical Perspective
Kien Do, Dung Nguyen, Hung Le +6
In this paper, we study the "dataset bias" problem from a statistical standpoint, and identify the main cause of the problem as the strong correlation between a class attribute u a…
cs.CV2022
Defense Against Multi-target Trojan Attacks
Haripriya Harikumar, Santu Rana, Kien Do +4
Adversarial attacks on deep learning-based models pose a significant threat to the current AI infrastructure. Among them, Trojan attacks are the hardest to defend against. In this…