BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//IEEE Region 6 - ECPv6.16.5//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.ieeer6.org
X-WR-CALDESC:Events for IEEE Region 6
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20250309T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20251102T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20260308T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20261101T090000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20270314T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20271107T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20260526T164500
DTEND;TZID=America/Los_Angeles:20260526T190000
DTSTAMP:20260525T202755Z
CREATED:20260430T212646Z
LAST-MODIFIED:20260525T202755Z
UID:10000490-1779813900-1779822000@www.ieeer6.org
SUMMARY:2026 GET-AI SERIES: 2 . Trust in AI Systems: Detecting\, Defending\, and Securing Intelligent Agents
DESCRIPTION:We are excited to continue the Orange County Computer Society (OCCS) Global Emerging Technologies and Artificial Intelligence (GET-AI) Series—a monthly platform focused on transformative innovations in computer science and technology. Hosted by the IEEE Orange County Computer Society Chapter\, this series brings together professionals\, students\, and tech enthusiasts to explore the cutting edge of what’s possible.\nFollowing a highly engaging April session on Generative AI\, where we explored LLMs\, RAG\, Agents\, MCP\, and hands-on AI application development\, we are excited to bring you our May Tech Talk on “Security in AI.”\n—————————————————————\n🔒 May Focus: Securing Generative AI\nAs AI systems evolve—from traditional models to LLM-powered agents interacting with enterprise systems and real-world tools—they introduce powerful capabilities along with new security challenges\, including:\n– Data leakage and prompt injection\n– Model misuse and unauthorized access\n– Risks in agent-driven automation\n– Governance and compliance concerns\nThis session combines technical insights and practical demonstrations to explore how to build secure\, trustworthy AI systems at scale.\n—————————————————————\nSession 1: Intelligent Attack Detection & Provenance (45 mins)\nModern enterprises generate massive\, fragmented logs\, making it difficult to derive meaningful security insights.\nThis session explores how AI enhances detection and forensic analysis:\n– Graph-Based Intrusion Detection\nUse unsupervised graph learning to uncover multi-step attacks in network activity\n– LLM-Powered Security Intelligence\nConvert low-level alerts into high-level\, actionable insights for faster response\n👉 Takeaway: Move from fragmented alerts to intelligent\, end-to-end attack understanding\n—————————————————————\nSession 2: Securing AI Agents — MCP Threats & Defense (45 mins)\nAs AI agents integrate with tools\, APIs\, and external systems\, they introduce new attack surfaces.\nThis session includes a live demo of how agents can be compromised—and secured:\n– Understanding MCP Architectures\nHow agents invoke tools and why trust boundaries blur\n– Live Demo: Tool Poisoning & Agent Manipulation\nSee how adversarial inputs can:\n– Manipulate agent behavior\n– Trigger unintended actions\n– Lead to data exfiltration\n– Layered Security Framework\nPractical defenses:\n– Tool authentication\n– Response sanitization\n– Schema validation\n– Context isolation\n– Real-Time Evaluation\nPrevent attacks without impacting performance\n👉 Takeaway: Practical strategies to secure AI agents in enterprise environments\n—————————————————————\nAbout the Organizer\nPradyumna Kodgi\nPrincipal Product Manager | Oracle Health & AI\nIEEE Senior Member | Vice Chair\, IEEE EMBS – Orange County\nMember\, IEEE AI Agentic Systems & AI Policy Committees\n📍 California\, USA\n📧 pkodgi@ieee.org\n🔗 linkedin.com/in/pkodgi\nCo-sponsored by: Pradyumna Kodgi\nSpeaker(s): Zhou\, Sreekanth\nAgenda:\nSecuring AI: From Innovation to Resilience\nAI is rapidly transforming how we build intelligent systems—but as capabilities grow\, so do security risks. From LLM-powered agents to tool-integrated architectures\, the question is no longer just what AI can do—but how do we secure it?\nIn this interactive session\, we cut through the noise and break down AI security in practical\, real-world terms—so you can understand not just the risks\, but how to defend against them.\n—————————————————————\n🔍 What You’ll Explore\n– How modern AI systems (LLMs\, agents\, MCP) introduce new attack surfaces\n– The shift from traditional security to AI-driven threat models\n– Key security concepts—explained clearly and practically\n– Real-world attack scenarios and emerging threat patterns\n—————————————————————\n💡 What Makes This Session Different\nThis isn’t just theory—you’ll see AI systems under attack and defense in action.\nThrough a live\, end-to-end demonstration\, we’ll show how AI agents can be manipulated—and how layered security approaches can prevent these attacks in real time.\n—————————————————————\n🛠️ Practical Takeaways\nYou’ll walk away with actionable strategies and frameworks you can apply immediately\, including:\n– Securing AI agents interacting with external tools\n– Validating and sanitizing untrusted inputs\n– Designing trust boundaries in AI-driven architectures\n—————————————————————\n🎯 Who Should Attend\n– Security professionals and architects working with AI systems\n– Engineers and developers building AI/LLM-based applications\n– Product managers and leaders driving AI adoption\n– Anyone interested in understanding AI risks and defenses\n—————————————————————\n✨ What You’ll Walk Away With\n– A clear understanding of emerging AI security risks\n– Practical knowledge of how to secure AI agents and systems\n– Real-world insights into attack prevention and defense strategies\n—————————————————————\nAs AI systems become more autonomous and integrated into enterprise workflows\, security becomes foundational—not optional. This session will equip you with the mindset and tools to build AI systems you can trust.\nVirtual: https://events.vtools.ieee.org/m/557806
URL:https://www.ieeer6.org/event/2026-get-ai-series-2-trust-in-ai-systems-detecting-defending-and-securing-intelligent-agents/
LOCATION:Virtual: https://events.vtools.ieee.org/m/557806
CATEGORIES:Local Events
ATTACH;FMTTYPE=image/jpeg:https://www.ieeer6.org/wp-content/uploads/ieee-region-6-event-01.jpg
END:VEVENT
END:VCALENDAR