Deep Backdoors in Deep Reinforcement Learning Agents
Unknown
Black Hat USA 2024 · Day 1 · Briefing
This talk delves into the emerging and critical threat of backdoors in **Deep Reinforcement Learning (DRL) agents**, a domain rapidly expanding beyond games into real-world, high-stakes applications. Speakers Vaz and Jamie illuminate how these intelligent agents, powered predominantly by neural networks, can be compromised to harbor malicious functionality. Unlike traditional software backdoors, DRL backdoors operate by recognizing specific "triggers" within their operational environment, prompting a drastic and potentially catastrophic deviation from their intended, safe behavior. The talk not only dissects the mechanics of such attacks but also introduces a novel defensive mechanism, **Neural Watchdog**, designed to mitigate these sophisticated threats.