The Secure, Reliable, and Intelligent Systems (SRI) Lab is a research group in the Department of Computer Science at ETH Zurich. Our current research focus is on the areas of reliable, secure, robust and fair machine learning, large language models, probabilistic and quantum programming, and machine learning for code. Our work led to six ETH spin-offs: InvariantLabs (secure AI agents), NetFabric (AI for systems), LogicStar (AI code agents), LatticeFlow (robust ML), DeepCode (AI for code; acquired by Snyk), and ChainSecurity (security verification; acquired by PwC). See our Publications and our Blog to learn more about our latest work, and follow our group on Twitter.

Latest Blog Posts

Latest News

Latest News & Blog Posts

Probing Google DeepMind's SynthID-Text Watermark: We apply the techniques from our recent work to investigate how SynthID-Text, the first large-scale deployment of an LLM watermarking scheme, fares in several adversarial scenarios. We discuss a range of findings, provide novel insights into the properties of this scheme, and outline interesting future research directions.

Niels Mündler and Mark Vero, doctoral students at the lab, were interviewed for the latest NZZ article about DeepSeek and the LLM market. See the original article (in German, paywalled).

The Role of Red Teaming in PETs: In February, our team won the Red Teaming category of the U.S. PETs Prize Challenge, securing a prize of 60,000 USD. In this blog post, we will provide a brief overview of the significance of Red Teaming in the field of Privacy Enhancing Technologies (PETs) research in the context of the competition.

Our ETH spin-off LogicStar raises USD 3M in pre-seed funding to build tools for autonomous maintenance of software applications. Learn more in the latest TechCrunch article.

LAMP: Extracting Text from Gradients with Language Model Priors: In this work we present an attack on federated learning's privacy specific to the text domain. We show that federated learning in the text domain can expose a lot of user data.

Jingxuan He, former doctoral student at SRI Lab, has won the 2024 ETH Medal for his outstanding doctoral thesis “Machine Learning for Code: Security and Reliability”. See the announcement from the D-INFK department.

Reliability Guarantees on Private Data: We present Phoenix (CCS '22), the first system for privacy-preserving neural network inference with robustness and fairness guarantees.

Together with our spin-off LatticeFlow and INSAIT, we launched COMPL-AI, an open-source compliance-centered evaluation framework for Generative AI models. The release was covered by TechCrunch, Reuters, and EuroNews.

See all Blog Posts
See all News & Media