Perspecta Inc. announced its applied research arm, Perspecta Labs, has received an award from the Intelligence Advanced Research Projects Activity to provide research on the Trojans in Artificial Intelligence, or TrojAI, program.
Advancements in AI and machine learning have added complexity to the threat landscape, the company notes. By hacking the training phase of ML, adversaries can disrupt AI systems during development, causing them to make incorrect classifications and take dangerous actions.
The TrojAI program aims to detect adversarial trojans placed into AI systems to prevent such attacks. Perspecta Labs will lead a team of researchers to study Trojan contamination and develop and provide a multi-faceted detection mechanism to significantly reduce Trojan security risks.
Perspecta Labs looks forward to supporting IARPA on research to protect critical AI systems against malicious interference, said Petros Mouchtaris, president and general manager of Perspecta Labs.
“We look forward to applying our leading expertise in adversarial ML combined with our vast experience in cybersecurity to develop new solutions that can automatically identify compromised AI systems in support of this critical work,” he added.