CHANTILLY, Va., Sept. 24, 2020 /PRNewswire/ -- Perspecta Inc.
(NYSE: PRSP), announced today that its innovative applied research
arm, Perspecta Labs, received an award from the Intelligence
Advanced Research Projects Activity (IARPA) to provide research on
the Trojans in Artificial Intelligence (TrojAI) program.
Advancements in artificial intelligence (AI) and machine
learning (ML) have added complexity to the threat landscape. 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 goal of the TrojAI
program is 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.
"At Perspecta Labs, we welcome the opportunity to support IARPA
on research to defend critical AI systems against malicious
interference," said Petros Mouchtaris, president and general
manager, 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."
To accomplish this task, the Perspecta Labs team will develop
automatic tools to detect Trojans hidden within AI systems. Several
techniques will be developed to provide multi-pronged detection,
including: detecting Trojans by stimulating neurons in a neural
network model and leveraging gradient magnitudes to identify
Trojans among candidate triggers; confirming the presence of
Trojans via differences in the distribution of vector
representations of sample inputs generated from the AI; and
detecting Trojans based on the clustering properties of adversarial
directions.
About Perspecta Inc.
At Perspecta (NYSE: PRSP), we question, we seek and we solve.
Perspecta brings a diverse set of capabilities to our U.S.
government customers in defense, intelligence, civilian, health
care and state and local markets. Our 280+ issued, licensed and
pending patents are more than just pieces of paper, they tell the
story of our innovation. With offerings in mission services,
digital transformation and enterprise operations, our team of
nearly 14,000 engineers, analysts, investigators and architects
work tirelessly to not only execute the mission, but build and
support the backbone that enables it. Perspecta was formed to take
on big challenges. We are an engine for growth and success and we
enable our customers to build a better nation. For more
information about Perspecta, visit perspecta.com.
This press release may contain forward-looking statements.
These forward-looking statements are made on the basis of the
current beliefs, expectations and assumptions of the management of
Perspecta and are subject to significant risks and uncertainty.
Readers are cautioned not to place undue reliance on any such
forward-looking statements. All such forward-looking statements
speak only as of the date they are made, and Perspecta undertakes
no obligation to update or revise these statements, whether as a
result of new information, future events or otherwise. Although
Perspecta believes that the expectations reflected in these
forward-looking statements are reasonable, these statements involve
a variety of risks and uncertainties that may cause actual results
to differ materially from what may be expressed or implied in these
forward-looking statements.
View original content to download
multimedia:http://www.prnewswire.com/news-releases/perspecta-labs-to-conduct-critical-research-for-machine-learning-and-artificial-intelligence-security-301137952.html
SOURCE Perspecta Inc.