Think Outside the Prompt: Creative Approaches to Attacking AI
netspi.com | blog | #ai-security | #supply-chain | #machine-learning | #threat-analysis | #typosquatting | #pytorch
Summary
Using the PyTorch-nightly compromise as a case study, this post explores attacking AI via its supply chain: typosquatted dependencies, credential theft from build machines, and model integrity risks.
- Published
- Collected
Skip to content