Tag Archive: Cybersecurity

In his testimony before the House Science Subcommittee on Investigations and Oversight and the Subcommittee on Research and Technology, Senior Fellow Andrew Lohn discussed various vulnerabilities within the AI supply chain and the methods hackers use to subvert AI systems.

According to Senior Fellow Andrew Lohn in his testimony before the Senate Armed Services Subcommittee on Cybersecurity, the U.S. is the leading global innovator in AI.

In his testimony before the Senate Armed Services Subcommittee on Cybersecurity, Senior Fellow Andrew Lohn advises that the DOD has the opportunity to "step ahead of industry in the adversarial context" in terms of AI innovation within cyberspace operations.

CSET Senior Fellow Andrew Lohn testified before the U.S. Senate Armed Services Subcommittee on Cybersecurity hearing on artificial intelligence applications to operations in cyberspace. Lohn discussed AI's capabilities and vulnerabilities in cyber defenses and offenses.

CSET report "Securing AI" highlights the numbers of ways hackers can compromise AI by targeting its data.

The goal of this guide is to acquaint researchers and analysts with tools, resources, and best practices to ensure security when collecting or accessing open-source information.

The new grant will contribute to the CyberAI Project's research at the intersection of artificial intelligence and cybersecurity.

Senior Fellow Andrew Lohn discusses why AI and machine learning's vulnerabilities present limitations when applied in real-life defense applications in an interview with Forbes.

Securing AI

Andrew Lohn Wyatt Hoffman
| March 2022

Like traditional software, vulnerabilities in machine learning software can lead to sabotage or information leakages. Also like traditional software, sharing information about vulnerabilities helps defenders protect their systems and helps attackers exploit them. This brief examines some of the key differences between vulnerabilities in traditional and machine learning systems and how those differences can affect the vulnerability disclosure and remediation processes.

Nvidia hack could help China according to CSET's policy.ai newsletter.