News

ACTION Distinguished Lecture: Claudionor Coelho Jr., Chief AI Officer of ZScaler, Inc.

The Mythical LLM-Month: Building Trustworthy Copilots and AutoPilots

Claudionor N. Coelho Jr, PhD/MBA
Chief AI Officer, Zscaler Inc

Date: Friday, May 31
Time: 1:00 pm PT
YouTube link: https://youtu.be/S8cop6_wDqQ

Abstract

Local High School Reflection on Hacking Experience

Alex Ortiz, a student at Dos Pueblos High School in Goleta, reflected on the School for Scientific Thought experience by interviewing Stijn Pletinckx and Ilya Grishchencko, two researchers in the UCSB SecLab who collaborate with the ACTION Institute. 

ACTION Distinguished Lecture: Snehal Antani, CEO of Horizon3.ai

Go Hack Yourself: More War Stories from ~50k Pentests

Snehal Antani, CEO
Horizon3.ai

2 May 2024
1:00 pm PT (4:00 pm ET)

https://youtu.be/VXPpjttpVMY

U Washington Research on LLM Jailbreaking in Science Explorer Magazine

Journalist Kathryn Hulick included research from Fengqing Jiang and Radha Poovendran at the University of Washington in her article titled, "Jailbreaks bring out the evil side of chatbots." Specifically, she referenced Jiang's

CERIAS Holds their 25th Annual Cyber Security Symposium at Purdue

The 25th annual (1999-2024) CERIAS Security Symposium brought together researchers, scientists, academics, and industry professionals to hear prestigious keynote addresses, thought provoking panel discussions, and innovative lighting and technology talks.

Spring 2024 AI Magazine features AI Institutes

The Spring 2024 issue of AI Magazine features guest editors Chaohua Ou and Ashok Goel, who hail from Georgia Institute of Technology and the AI-ALOE Institute. This special issue delivers brief reports on the first 18 AI Institutes, launched in 2020 and 2021. Take a look at the amazing work our partner institutes are undertaking.

Creating Intelligent Cyberinfrastructure for Democratizing AI: Overview of the Activities at the NSF-AI Institute ICICLE

Distinguished Lecture at the ECE Seminar Series

Dhabaleswar K. (DK) Panda
Computer Science & Engineering, Ohio State University

April 05, 2024 (Fri.)
Coffee hour beings at 1:00 PM
Lecture begins at 2:00 PM
Location: ESB 1001

Seminar: Toward Provable and Explainable AI Security

Chong Xiang
Thursday, 28 March 2024
11 am - 12 pm PT
Join via Zoom

Abstract

Existing defenses for AI models are being broken by adaptive attacks all the time. One major reason is that most defenses do not provide convincing explanations or formal proof of any model robustness they have intended to achieve.