November 3, 2021via Amazon Science
Foiling AI hackers with counterfactual reasoning
Why it matters
As AI systems become more prevalent in critical applications, developing robust defenses against adversarial attacks becomes essential for enterprise deployment and safety. This research addresses a key barrier to widespread AI adoption.
Key signals
- Amazon Research Award recipient
- Focus on autonomous systems robustness
- Counterfactual reasoning as defense mechanism
The hook
AI hackers are getting smarter. Counterfactual reasoning might be the defense autonomous systems need.
Amazon Research Award recipient Yezhou Yang is studying how to make autonomous systems more robust.
Relevance score:75/100