2 papers
cs.AI2026
Toward Reusability of AI Models Using Dynamic Updates of AI Documentation
Peter Bajcsy, Walid Keyrouz
This work addresses the challenge of disseminating reusable artificial intelligence (AI) models accompanied by AI documentation (a.k.a., AI model cards). The work is motivated by t…
cs.LG2024
Interactive Simulations of Backdoors in Neural Networks
Peter Bajcsy, Maxime Bros
This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence (AI) models. The motivation comes from our lack of understanding…