Skip to the main content

Ram Shankar Siva Kumar is a Data Cowboy working on the intersection of machine learning and security. At Microsoft, he founded the AI Red Team, bringing together an interdisciplinary group of researchers and engineers to proactively attack AI systems and find failures.

His recent book on attacking AI systems, NOT WITH A BUG has been called “Essential Reading” by Microsoft’s Chief Technology Officer and received wide praise from industry leaders at DeepMind, OpenAI as well as policy makers and academia. He is donating his proceeds of the book royalty to Black In AI.

His work on AI and Security has appeared in industry conferences like RSA, BlackHat, Defcon, BlueHat, DerbyCon, MIRCon, Infiltrate, academic workshops at NeurIPS, ICLR, ICML, IEEE S&P, ACM - CCS. His work has been covered by Bloomberg, VentureBeat, Wired, and Geekwire. He founded the Adversarial ML Threat Matrix, an ATT&CK style framework enumerating threats to machine learning. His work on adversarial machine learning appeared notably in the National Security Commission on Artificial Intelligence (NSCAI) Final report presented to the United States Congress and the President.

He is currently Tech Policy Fellow at UC Berkeley and an affiliate at the Berkman Klein Center for Internet and Society at Harvard University, where he is broadly investigating two questions: How do we assess the safety of ML systems? What are the policy and legal ramifications of AI, in the context of security? He is also Technical Advisory Board Member at the University of Washington.


Community

BKC Medium Collection

Legal Risks of Adversarial Machine Learning Research

Studying or testing the security of any operational system potentially runs afoul of the Computer Fraud and Abuse Act

Jul 15, 2020
Harvard Business Review

The Case for AI Insurance

BKC’s Ram Shankar Siva Kumar joins Frank Nagle to explore Adversarial Machine Learning's impact on businesses.  “Most major companies, including Google, Amazon,…

Apr 29, 2020
Medium

Politics of Adversarial Machine Learning

Adversarial machine-learning attacks and defenses have political dimensions

Apr 23, 2020
Bloomberg

Microsoft Wants More Security Researchers to Hack Into Its Cloud

As Microsoft works on cloud security, it’s looking to attract `White Hat’ hackers with rewards and legal guarantees.

Jun 7, 2019
Bloomberg

Artificial Intelligence vs. the Hackers

Machine-learning algorithms watch hackers’ behavior and adapt to their evolving tactics.

A profile of "Data Cowboy" Ram Shankar Siva Kumar, who trains security algorithms

Jan 3, 2019
Medium

Law and Adversarial Machine Learning

A survey of existing legal remedies for attacks that have been demonstrated on machine learning systems, and suggests some potential areas of exploration for machine learning…

Dec 20, 2018
arXiv

Law and Adversarial Machine Learning

When machine learning systems fail because of adversarial manipulation, how should society expect the law to respond?

Oct 26, 2018

Events

Oct 2, 2023 @ 3:30 PM

Not With A Bug, But With A Sticker

the story, science, and societal effects of attacking AI systems

Ram Shankar Siva Kumar shows how major AI systems remain vulnerable to exploits...