SEI Blog | Securing AI

SEI Blog | Securing AIhttp://www.sei.cmu.edu/feeds/topic/securing-ai/atom/?utm_source=blog&utm_medium=rss2025-02-24T00:00:00-05:00Updates on changes and additions to the SEI Blog for posts matching Securing AIProtecting AI from the Outside In: The Case for Coordinated Vulnerability Disclosure2025-02-24T00:00:00-05:002025-02-24T00:00:00-05:00Allen Householder, Vijay Sarvepalli, Jeff Havrilla, Matt Churilla, Lena Pons, Shing-hon Lau, Nathan VanHoudnos, Andrew Kompanek, Lauren McIlvennyhttps://www.sei.cmu.edu/blog/protecting-ai-from-the-outside-in-the-case-for-coordinated-vulnerability-disclosure/?utm_source=blog&utm_medium=rss&utm_campaign=my_site_updates

This post highlights lessons learned from applying the coordinated vulnerability disclosure (CVD) process to reported vulnerabilities in AI and ML systems.

3 Recommendations for Machine Unlearning Evaluation Challenges2024-08-26T00:00:00-04:002024-08-26T00:00:00-04:00Keltin Grimes, Collin Abidi, Cole Frank, Shannon Gallagherhttps://www.sei.cmu.edu/blog/3-recommendations-for-machine-unlearning-evaluation-challenges/?utm_source=blog&utm_medium=rss&utm_campaign=my_site_updates

Machine unlearning (MU) aims to develop methods to remove data points efficiently and effectively from a model without the need for extensive retraining. This post details our work to address MU challenges and offers 3 recommendations for evaluation methods.