BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/Chicago BEGIN:DAYLIGHT DTSTART:20260308T030000 TZOFFSETFROM:-0600 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:CDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20261101T010000 TZOFFSETFROM:-0500 TZOFFSETTO:-0600 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:CST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20260424T163504Z UID:D1388570-6B26-49BE-9981-9CF403F615B3 DTSTART;TZID=America/Chicago:20260417T120000 DTEND;TZID=America/Chicago:20260417T130000 DESCRIPTION:Large Language Models (LLMs) are increasingly used by developer s and students to generate code\, offering significant gains in productivi ty and accessibility. However\, LLM-generated code often introduces subtle yet critical security vulnerabilities\, particularly in domains such as c ryptography and secure software development. This webinar presents a pract ical and systematic approach to secure code generation using LLMs\, focusi ng on transforming raw model outputs into verifiably safe implementations. \nThe session introduces a structured workflow\, Prompt → Harden → Ver ify\, that guides participants through crafting security-aware prompts wit h explicit constraints\, enforcing correctness through unit testing\, and applying lightweight automated security checks prior to deployment. Throug h hands-on demonstrations\, attendees will learn how to integrate secure c oding practices directly into the LLM-assisted development pipeline.\nBy t he end of the webinar\, participants will gain a repeatable methodology fo r reducing vulnerabilities in AI-generated code\, along with ready-to-use templates and a security validation checklist. This work aims to bridge th e gap between AI-assisted programming and secure software engineering\, en abling practitioners to harness LLM capabilities while maintaining strong security guarantees.\n\nSpeaker(s): Dr. Mahmoud Abouyoussef\, \n\nVirtual: https://events.vtools.ieee.org/m/553201 LOCATION:Virtual: https://events.vtools.ieee.org/m/553201 ORGANIZER:shuvalaxmi.dass@louisiana.edu SEQUENCE:27 SUMMARY:Building Secure Code with LLMs: A Hands-On Prompt-to-Verification W orkflow URL;VALUE=URI:https://events.vtools.ieee.org/m/553201 X-ALT-DESC:Description: <br /><div>Large Language Models (LLMs) are increas ingly used by developers and students to generate code\, offering signific ant gains in productivity and accessibility. However\, LLM-generated code often introduces subtle yet critical security vulnerabilities\, particular ly in domains such as cryptography and secure software development. This w ebinar presents a practical and systematic approach to secure code generat ion using LLMs\, focusing on transforming raw model outputs into verifiabl y safe implementations.</div>\n<div>The session introduces a structured wo rkflow\, <em>Prompt &rarr\; Harden &rarr\; Verify\, </em>that guides parti cipants through crafting security-aware prompts with explicit constraints\ , enforcing correctness through unit testing\, and applying lightweight au tomated security checks prior to deployment. Through hands-on demonstratio ns\, attendees will learn how to integrate secure coding practices directl y into the LLM-assisted development pipeline.</div>\n<div>By the end of th e webinar\, participants will gain a repeatable methodology for reducing v ulnerabilities in AI-generated code\, along with ready-to-use templates an d a security validation checklist. This work aims to bridge the gap betwee n AI-assisted programming and secure software engineering\, enabling pract itioners to harness LLM capabilities while maintaining strong security gua rantees.</div> END:VEVENT END:VCALENDAR