Decision Making in Adversarial Automation
Bobby Kuzma, Michael Odell
DEF CON 33 (backfill) · Day 1 · Main Stage
In the intricate dance between attackers and defenders, the speed and accuracy of decision-making often dictate the outcome. This talk, "Decision Making in Adversarial Automation," delivered by Bobby Kuzma and Michael Odell at DEF CON, delves into the theoretical underpinnings and practical applications of automating adversarial decision processes. The speakers explore how concepts from artificial intelligence, game theory, and graph theory can be leveraged to create more sophisticated and adaptive automated attack tools, moving beyond simple deterministic playbooks to embrace probabilistic and context-aware strategies.
AI review
Kuzma and Odell are clearly doing real work here — the DSL-plus-Kuzu architecture is a legitimate engineering contribution and the POMDP framing is the right abstraction for adversarial automation. But the talk sits awkwardly between a conceptual primer and a working system demo, and the 'toy example with 14 tools' proof-of-concept doesn't yet close the gap between the theoretical ambition and something a practitioner can weaponize tomorrow.