2 papers
cs.CV2026
Concept Labels Are Not Enough: Rethinking Concept Bottleneck Models through Representation Integrity
Gaoxiang Huang, Songning Lai, Yutao Yue
Although deep neural networks achieve strong predictive performance, their internal reasoning often remains difficult to inspect and control. Concept Bottleneck Models (CBMs) addre…
cs.CR2024
Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models
Songning Lai, Yu Huang, Jiayu Yang +3
The increasing complexity of AI models, especially in deep learning, has raised concerns about transparency and accountability, particularly in high-stakes applications like medica…