Evasion, Poisoning, Extraction, and Inference: Tools to Defend and Evaluate

Posted on in Presentations

Adversaries of AI applications continuously advance their tools for evasion, poisoning, extraction, and inference against the underlying machine learning models to achieve their malicious goals. This technical talk will introduce the actual open source tools to reproduce these attacks and the tools needed to defend and evaluate applications before deploying and exposing them to adversaries.

Beat Buesser


Research Staff Member, IBM Research

Abigail Goldsteen


Research Staff Member, IBM

Share With Your Community