Trustworthy AI for National Security - Kathleen Fisher - PSW #805

<p>AI/ML is providing significant benefits in a wide range of application domains but also provides adversaries with a new attack surface. Learn about DARPA's efforts to help evaluate AI/ML and work towards a trust model that will allow us to use these valuable tools safely.</p> <p>Segment Resources:</p> <ul> <li>Identifying and Mitigating the Security Risks of Generative AI paper (co-authored by Kathleen): <a rel="noopener" target="_blank" href= "https://arxiv.org/abs/2308.14840">https://arxiv.org/abs/2308.14840</a></li> <li>DARPA’s AI Forward, which will include AI Exploration opportunities and resource material: <a rel="noopener" target= "_blank" href= "https://www.darpa.mil/work-with-us/ai-forward">https://www.darpa.mil/work-with-us/ai-forward</a></li> <li>I2O webpage, important to include because this hosts links to many of the programs Dr. Fisher will discuss: <a rel="noopener" target="_blank" href= "https://www.darpa.mil/i2o">https://www.darpa.mil/i2o</a></li> </ul> <p>Show Notes: <a rel="noopener" target="_blank" href= "https://securityweekly.com/psw-805">https://securityweekly.com/psw-805</a></p>