Towards a Framework to Quantitatively Assess AI Safety

Adversarial machine learning techniques and defense mechanisms.

Summary

AI safety: Towards a Framework to Quantitatively Assess AI Safety. Framework and evaluation methods discussed throughout.

Hyrum Anderson · Zoltan Balaz

Reviews results and top evasion strategies from the AI Village machine learning security and evasion competition.

machine-learningadversarial-mlcontest+1

Journal Club Live

Discusses practical methodologies for discovering exploitable bugs, implementation flaws, and attack surfaces in ML systems.

adversarial-mlvulnerability-researchmachine-learning+1

Erick Galinkin

A primer breaking down core vocabulary, concepts, and foundational theory in machine learning security.

machine-learningvocabularyadversarial-ml+1