{"id":189182,"date":"2026-02-20T11:29:00","date_gmt":"2026-02-20T16:29:00","guid":{"rendered":"https:\/\/testing.news-you-need.com\/index.php\/2026\/02\/20\/computer-science-professor-studies-the-intersection-of-cybersecurity-and-ai\/"},"modified":"2026-02-20T11:45:08","modified_gmt":"2026-02-20T16:45:08","slug":"computer-science-professor-studies-the-intersection-of-cybersecurity-and-ai","status":"publish","type":"post","link":"https:\/\/testing.news-you-need.com\/index.php\/2026\/02\/20\/computer-science-professor-studies-the-intersection-of-cybersecurity-and-ai\/","title":{"rendered":"Computer science professor studies the intersection of cybersecurity and AI\u00a0"},"content":{"rendered":"

Computer science professor studies the intersection of cybersecurity and AI\u00a0<\/a><\/p>\n

https:\/\/news.uga.edu\/computer-science-professor-studies-the-intersection-of-cybersecurity-and-ai\/<\/a><\/p>\n

Publish Date: 2026-02-20 11:29:00<\/a><\/p>\n

Source Domain: news.uga.edu<\/a><\/p>\n

Author: <\/a><\/p>\n

Using an unordered list, summarize the following article with between 4 and 8 key points.
\nPhishing attacks. Jailbreaking and social engineering attacks. Malicious advertisements. These have all become part of the day in\u00a0the life\u00a0for most everyone who depends on a web connection for their work and livelihood. University of Georgia\u00a0cybersecurity expert Roberto\u00a0Perdisci\u00a0welcomes a greater awareness of the threats that have long been at the center of his professional life.\u00a0<\/p>\n

\u201cI initially came to the U.S.\u00a0as a research scholar to deepen my doctoral\u00a0work in Italy, which was at the intersection of machine learning and cybersecurity,\u201d said\u00a0Perdisci, Patty and D.R. Grimes Distinguished Professor of Computer Science and\u00a0director of the UGA Institute of Cybersecurity and Privacy. \u201cAnd back then, it was already a big thing.\u201d\u00a0<\/p>\n

Attracted to the U.S.\u00a0to work with Wenke Lee, Regents\u2019\u00a0Professor\u00a0and John P. Imlay Jr. Chair in Software in the Georgia Tech College of Computing,\u00a0Perdisci\u00a0completed a post-doctoral\u00a0fellowship with Lee after finishing his Ph.D. and joined the UGA faculty in 2010.\u00a0<\/p>\n

The quick transition is indicative of what continues to be a high demand field. \u201cWith all the development of AI agents, the intersection with\u00a0cybersecurity has become even more prevalent,\u201d he said.\u00a0<\/p>\n

Perdisci\u2019s\u00a0research primarily focuses on using machine learning and AI as tools to improve cybersecurity, rather than the safety and security of AI systems themselves. Understanding the distinction is instructive to understanding the many uses\u00a0\u2014\u00a0and potential misuses\u00a0\u2014\u00a0of large language models.\u00a0<\/p>\n

Security and safety of AI models themselves refer to attacks on AI systems, whether self-driving cars that\u00a0encounter\u00a0defaced road signs or nefarious attempts to trick an LLM\u00a0such as\u00a0Open AI\u2019s ChatGPT or Google\u2019s\u00a0Gemini with illicit or illegal prompts. \u201cThat\u2019s known as jailbreaking, because the AI system is working within safeguards,\u00a0and you\u2019re trying to break those safeguards to misuse the model,\u201d\u00a0Perdisci\u00a0said.\u00a0\u00a0<\/p>\n

\u201cBut we can also use AI systems to help improve the cybersecurity of a web browser,\u201d he said, for\u00a0instances\u00a0including\u00a0when\u00a0people\u00a0encounter\u00a0malicious web pages while using a browser to navigate across the internet.\u00a0<\/p>\n

\u201cThis happens because either you visit a site that is not reputable, or you visit one that is reputable but includes an advertisement that is dynamically selected,\u201d he said, noting that the publisher of a particular site\u00a0doesn\u2019t\u00a0necessarily have control over its ads. \u201cAnd sometimes malicious adverts can trigger the browser so that ends up being re-directed to a social engineering attack, like a fake software download or antivirus, a tech support\u00a0scam\u00a0or fake lottery type of\u00a0scam, and so forth. These are all social engineering attacks performed on the web.\u201d\u00a0<\/p>\n

To work against and help foil such attacks,\u00a0Perdisci\u00a0has led an NSF-funded project since 2021 where his team\u00a0demonstrates\u00a0the possibility of integrating an AI model within the browser itself.\u00a0<\/p>\n

\u201cAs you browse the web, the AI model inspects both the visual appearance of the web pages and the textual appearance, not necessarily the HTML of the underlying pages, but how the page reads visually. A technology like Optical Character Recognition interprets the visual image that is\u00a0rendered\u00a0by the browser to\u00a0determine\u00a0whether\u00a0it\u2019s\u00a0a\u00a0scam,\u201d he said.\u00a0<\/p>\n

Because of the scale and speed required by such a tool, the inspection can only be\u00a0accomplished\u00a0through ML and AI systems. And as with AI-enhanced browsers or LLMs\u00a0including\u00a0ChatGPT and Gemini, AI models that interact with the internet on\u00a0a person\u2019s\u00a0behalf use tools that are understood and planned for by attackers.\u00a0<\/p>\n

\u201cOne thing they can do is construct web content in a way that doesn\u2019t\u00a0appear as\u00a0malicious to a human being but could mislead the AI agent,\u201d\u00a0Perdisci\u00a0said. As the use of AI models grows, more and newer vulnerabilities are being introduced through its tools and systems.\u00a0<\/p>\n

\u201cThere are many different types of vulnerabilities that have been introduced because of the use of AI,\u201d he said, \u201cbut this is true for any technology.\u00a0It\u2019s\u00a0just that this is a new one, and as usual for any type of information system,\u00a0that\u2019s\u00a0the pattern: features and functionalities come first, and security later. If the company makes money, the product survives\u00a0and\u00a0maybe they\u00a0will think about adding more security investment.\u201d\u00a0<\/p>\n

Emerging\u00a0threats color this brave new world, but\u00a0Perdisci\u00a0brings that moment and its urgency directly into the classroom for his students to consider, learn\u00a0and build new security strategies.\u00a0\u00a0<\/p>\n

In 2025,\u00a0Perdisci\u00a0was selected as a recipient of an Amazon Research Award, one of four awardees in the AI for Information Security category. The award will support his project,\u00a0ContextADBench: A Comprehensive Benchmark Suite for Contextual Anomaly Detection, which grew out of one of his doctoral student\u2019s 2024 internship at Amazon\u00a0Web\u00a0Services.\u00a0<\/p>\n

Real-world examples of challenges students will face working in industry\u00a0make\u00a0them more attuned to tomorrow\u2019s threats. Awareness of how AI works and can work against\u00a0people\u00a0still requires\u00a0the human\u00a0touch after all.\u00a0<\/p>\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

Computer science professor studies the intersection of cybersecurity and AI\u00a0 https:\/\/news.uga.edu\/computer-science-professor-studies-the-intersection-of-cybersecurity-and-ai\/ Publish Date: 2026-02-20 11:29:00…<\/p>\n","protected":false},"author":1,"featured_media":189183,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/news.uga.edu\/wp-content\/uploads\/2026\/02\/RobertPerdisci.jpg","fifu_image_alt":"","footnotes":""},"categories":[15],"tags":[26,24,17,25],"class_list":["post-189182","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-cybersecurity","tag-ai","tag-cybersecurity","tag-llm","tag-phishing"],"_links":{"self":[{"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/189182"}],"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=189182"}],"version-history":[{"count":1,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/189182\/revisions"}],"predecessor-version":[{"id":189184,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/posts\/189182\/revisions\/189184"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/media\/189183"}],"wp:attachment":[{"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/media?parent=189182"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/categories?post=189182"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/testing.news-you-need.com\/index.php\/wp-json\/wp\/v2\/tags?post=189182"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}