Search

SPY Lab SPY Lab
SPY Lab SPY Lab
  • Blog
  • Publications
  • Teaching
  • Hiring
  • Contact
    ETH Zurich
    Privacy side channels in machine learning systems
    We explore the privacy of machine learning systems, and show how many standard components of the ML pipeline create side-channel vulnerabilities that leak private user data.
    Sep 12, 2023
    Evaluating superhuman models with consistency checks
    We propose an evaluation methodology for AI systems operating in domains without ground truth. The key idea is to test whether the AI’s outputs violate consistency constraints of the problem domain. We show that this allows finding clear failures in state-of-the-art models, including GPT-4 on tasks where it is hard to evaluate, and superhuman chess engines.
    Aug 16, 2023
    Adversarial examples in the age of ChatGPT
    We reflect on the discrepancies between the attack goals and techniques developed in the adversarial examples literature, and the current landscape of attacks on chatbot applications.
    Jun 30, 2023

    © 2023 ETH Zürich | Department of Computer Science | SPY Lab