acm-header
Sign In

Communications of the ACM

Latest Research



Technical Perspective: Beautiful Symbolic Abstractions for Safe and Secure Machine Learning
From Communications of the ACM

Technical Perspective: Beautiful Symbolic Abstractions for Safe and Secure Machine Learning

"Proving Data-Poisoning Robustness in Decision Trees," by Samuel Drews et al., addresses the challenge of processing an intractably large set of trained models...

Proving Data-Poisoning Robustness in Decision Trees
From Communications of the ACM

Proving Data-Poisoning Robustness in Decision Trees

We present a sound verification technique based on abstract interpretation and implement it in a tool called Antidote, which abstractly trains decision trees for...
Sign In for Full Access
» Forgot Password? » Create an ACM Web Account