{"id":215610,"date":"2026-05-18T10:15:00","date_gmt":"2026-05-18T14:15:00","guid":{"rendered":"https:\/\/testing.news-you-need.com\/index.php\/2026\/05\/18\/professor-earns-nsf-career-award-to-defend-ai-models-from-attackers\/"},"modified":"2026-05-18T10:45:11","modified_gmt":"2026-05-18T14:45:11","slug":"professor-earns-nsf-career-award-to-defend-ai-models-from-attackers","status":"publish","type":"post","link":"https:\/\/testing.news-you-need.com\/index.php\/2026\/05\/18\/professor-earns-nsf-career-award-to-defend-ai-models-from-attackers\/","title":{"rendered":"Professor earns NSF CAREER Award to defend AI models from attackers"},"content":{"rendered":"<p><a href=\"https:\/\/www.rit.edu\/news\/professor-earns-nsf-career-award-defend-ai-models-attackers\">Professor earns NSF CAREER Award to defend AI models from attackers<\/a><\/p>\n<p><a href=\"https:\/\/www.rit.edu\/news\/professor-earns-nsf-career-award-defend-ai-models-attackers\">https:\/\/www.rit.edu\/news\/professor-earns-nsf-career-award-defend-ai-models-attackers<\/a><\/p>\n<p>Publish Date: <a href=\"publish_date]\">2026-05-18 10:15:00<\/a><\/p>\n<p>Source Domain: <a href=\"www.rit.edu\">www.rit.edu<\/a><\/p>\n<ul>\n<li>\n<p><strong>Artificial Intelligence Threats<\/strong>: AI is increasingly used in critical systems, making machine learning models potential targets for attackers trying to embed vulnerabilities or exploits.<\/p>\n<\/li>\n<li>\n<p><strong>Zhao\u2019s Research Mission<\/strong>: Assistant Professor Weijie Zhao aims to ensure machine learning models do not have hidden vulnerabilities, emphasizing the need for security in the growing use of AI.<\/p>\n<\/li>\n<li>\n<p><strong>Challenge of Interpretability<\/strong>: The inherent complexity and &#8220;black box&#8221; nature of machine learning make it difficult to understand how decisions are made, raising concerns about false information and manipulated outputs.<\/p>\n<\/li>\n<li>\n<p><strong>Career Award and Project Focus<\/strong>: Zhao received a National Science Foundation CAREER award to develop methods for securing machine learning; his five-year project is titled \u201cDefending Machine Learning Models from Adversarial Threats via Unified Interpretability and Attribution.\u201d <\/p>\n<\/li>\n<li>\n<p><strong>Transparency and Safety Goals<\/strong>: The project aims to enhance safety, resilience, and accountability in machine learning systems by making them more understandable and trustworthy.<\/p>\n<\/li>\n<li>\n<p><strong>Techniques and Strategies<\/strong>: Zhao\u2019s research involves identifying harmful outputs from adversarial inputs, designing strategies to correct these issues without full retraining, auditing training data, and creating tools for remediating vulnerabilities.<\/p>\n<\/li>\n<li>\n<p><strong>Future Implications<\/strong>: Zhao hopes the defense framework developed at RIT will be used to build resilient, transparent, and trustworthy machine learning tools, emphasizing the importance of security in AI development.<\/p>\n<\/li>\n<li>\n<p><strong>NSF CAREER Award Recognition<\/strong>: Zhao&#8217;s award highlights the importance of integrating educational activities with impactful research, reflecting the broader goals of the NSF CAREER program in supporting junior faculty.<\/p>\n<\/li>\n<\/ul>\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Professor earns NSF CAREER Award to defend AI models from attackers https:\/\/www.rit.edu\/news\/professor-earns-nsf-career-award-defend-ai-models-attackers Publish Date: 2026-05-18&#8230;<\/p>\n","protected":false},"author":1,"featured_media":215611,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/www.rit.edu\/sites\/rit.edu\/files\/styles\/full\/https\/cdn.rit.edu\/images\/news\/2026-05\/Weijie-Zhao.jpg?itok=M-IWQHzT","fifu_image_alt":"","footnotes":""},"categories":[14],"tags":[20],"class_list":["post-215610","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","tag-artificial-intelligence"],"_links":{"self":[{"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/215610"}],"collection":[{"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/comments?post=215610"}],"version-history":[{"count":1,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/215610\/revisions"}],"predecessor-version":[{"id":215612,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/215610\/revisions\/215612"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/215611"}],"wp:attachment":[{"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=215610"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=215610"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=215610"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}