Finding — and preventing — vulnerabilities in machine learning models
Nobody talking about AI security vulnerabilities. Everyone's rushing to deploy. Few are securing their models.

Why it matters
As enterprises rapidly deploy AI systems, model security and trustworthiness becomes a critical business risk that most companies aren't adequately addressing.
The key facts
3 to knowBo Li appointed as Amazon Visiting Academic
Former Amazon Research Award recipient
Focus on explainable machine learning vulnerabilities
Go to the source
Amazon Scienceamazon.science
Publisher excerpt: Bo Li — a new Amazon Visiting Academic and former Amazon Research Award recipient — is making sure algorithms are not only smarter but more trustworthy.

