DARPA Awards $3.1M for ML Researchers to Counter Rising Threat of Attacks on AI Systems

From detecting illegal stock market activity to increasing safety in self-driving vehicles to improving facial ID recognition, machine learning systems promise to revolutionize a range of security applications--and now a team of University of Maryland computing experts is working to ensure adversaries can't penetrate them. A new $3.1 million grant from the Defense Advanced Research Projects Agency (DARPA) will support efforts to develop safeguards against deception attacks on machine learning algorithms, which let systems learn from data and make decisions with a minimum of human programming. Attacks against these systems are an emerging security threat as artificial intelligence (AI) is further applied to industrial settings, medicine, information analysis and more. "We want to understand the vulnerabilities of these systems, craft defenses that would make it difficult to attack them, and improve the overall security of these systems," said Tom Goldstein, an associate professor of computer science, who is principal investigator of the four-year project. "As far as I'm aware, no one has actually looked at the security of machine learning for those applications," said Goldstein.