FB pixel

IARPA expands research on protecting AI systems from tampering

 

The U.S. government’s Intelligence Advanced Research Projects Activity (IARPA) is planning a pair of programs to prevent training data from being maliciously tampered with to turn artificial intelligence systems against their users, Federal News Network reports.

“We appreciate the fact that AI is going to be in a lot more things in our life, and we’re going to be relying on it a lot more, so we would want to be able to take advantage of, or at least mitigate, those vulnerabilities that we know exist,” IARPA Director Stacey Dixon told an audience at the Intelligence and National Security Alliance (INSA) conference in Arlington, Virginia.

One project, Trojans in Artificial Intelligence (TrojAI), seeks to create a warning system for machine-learning algorithm training data compromised by an adversary. That project was originally announced in December, and industry has provided feedback on it. Details of the second project will be revealed in a draft announcement later this year, but Dixon said that it will focus on protecting the identity of people whose images have been used to train facial biometric algorithms.

“How do you ensure that no one can take the algorithm that you created and go back and recreate the faces that were in the database?” Dixon asks. “These are certain areas that we hadn’t seen too much research, and so we will be starting programs.”

IARPA is also working towards cybersecurity attack forecasting based on publicly available information and what Dixon called “non-traditional sensors.” She also notes that while the U.S. government used to be the biggest funder for a lot of research projects, this is no longer the case, making it necessary for government agencies to partner with academic and private sector stakeholders.

In that vein, IARPA is backing a team of academic researchers on protecting biometric systems from previously unseen attack types.

The threat of “deepfakes” and other malicious uses of AI is also drawing increasing attention from concerned researchers.

Article Topics

 |   |   |   |   |   | 

Latest Biometrics News

 

Operationalizing biometrics for digital economy is a process

From biometric binding through regulations for payments from digital wallets, the Biometric Update’s top stories of the week reflect a…

 

Deepfakes a ‘now problem’ as EU AI Act passes compliance deadline: Reality Defender

First it was Joe Biden, Kamala Harris and Taylor Swift. Now it’s Scarlett Johannson, Emmanuel Macron and Italy’s Defense Minister…

 

OneID raises £16 million

UK digital verification service OneID has secured new funding amid a rise of interest in digital identity among the country’s…

 

Digital ID verification can make property transactions more efficient, less prone to fraud

In the UK, Russia, South Korea, India and Pakistan, biometrics are making their way into real estate transactions, as digital…

 

IDV experts ponder death and resurrection of document verification

Is document verification dead? The question hangs over a debate hosted by Peak IDV CEO, Steve Craig. Five industry experts…

 

Jamaica operationalizing national digital ID with data exchange platform

Jamaica will make its digital identity available to all of its citizens, Custos of Kingston Steadman Fuller said on Thursday…

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Most Viewed This Week

Featured Company

Biometrics Insight, Opinion

Digital ID In-Depth

Biometrics White Papers

Biometrics Events