Home  | News

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 Junior Member Sarah Ball, a PhD student in the group of our PI Frauke Kreuter, 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.

#media #podcast #research #kreuter
Subscribe to RSS News feed

Related

Link to Blind Matching – Aligning Images and Text Without Training or Labels

15.01.2026

Blind Matching – Aligning Images and Text Without Training or Labels

CVPR 2025 research from Daniel Cremers’ group shows how images and text can be aligned without training data, labels, or paired examples.

Link to High-Res Images, Less Wait: A Simple Flow for Image Generation

08.01.2026

High-Res Images, Less Wait: A Simple Flow for Image Generation

ECCV 2024 research led by Björn Ommer’s team enables faster high-resolution image generation by boosting diffusion models with flow matching.

Link to

02.01.2026

MCML Researchers in Highly-Ranked Journals

We are excited to announce that MCML researchers have four papers published in highly-ranked journals in 2026.

Link to Digdeep Podcast: Armin Nassehi, how does social transformation succeed?

25.12.2025

Digdeep Podcast: Armin Nassehi, How Does Social Transformation Succeed?

In the new episode of #digdeep, sociologist Armin Nassehi explains, how social transformation succeeds.

Link to "See, Don’t Assume": Revealing and Reducing Gender Bias in AI

18.12.2025

"See, Don’t Assume": Revealing and Reducing Gender Bias in AI

ICLR 2025 research led by Zeynep Akata’s team reveals and reduces gender bias in popular vision-language AI models.

Back to Top