20.01.2025

Teaser image to Sarah Ball's Research Featured on on the LLM Cybersecurity podcast

Sarah Ball's Research Featured on on the LLM Cybersecurity Podcast

Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models

We are happy to share that Sarah Ball, a PhD student at the Munich Center for Machine Learning, has had her research featured on the LLM Cybersecurity podcast by Ariel Fogel and Tyler Bettilyon.

The discussion centered around Sarah's paper, "Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models", highlighting its insights and implications for the field of AI and cybersecurity.

20.01.2025


Subscribe to RSS News feed

Related

Link to  AI as Co-Pilot

01.04.2025

AI as Co-Pilot

AI tools by Stefan Feuerriegel’s team at LMU support public decision-making, aiming for efficiency, transparency, and human control.

Link to Robot Jack Navigates Like a Human – A Project Led by Angela Schoellig

31.03.2025

Robot Jack Navigates Like a Human – A Project Led by Angela Schoellig

Angela Schoellig’s team at TUM developed robot Jack, which navigates safely through crowds using human-inspired motion planning.

Link to New Method Significantly Reduces AI Energy Consumption

18.03.2025

New Method Significantly Reduces AI Energy Consumption

Felix Dietrich and his team at TUM developed a new method that significantly reduces AI energy consumption, making AI more efficient and sustainable.

Link to Björn Schuller was featured on ARTE TV

10.03.2025

Björn Schuller Was Featured on ARTE TV

Björn Schuller was featured in an ARTE TV documentary on AI therapy, presenting his research on emotion recognition.

Link to AI Competition: Where Does Europe Stand?

26.02.2025

AI Competition: Where Does Europe Stand?

Gitta Kutyniok talks to Plattform Lernende Systeme about Europe’s AI competitiveness and the role of mathematics in AI.