• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Sahar Abdelnabi Announces Postdoc and PhD Hiring in AI Privacy

    She seeks a postdoc or PhD student to study privacy and contextual integrity in AI agents, co-advised with Niloofar Mireshghallah.

    SA
    1 Source, ,

    TLDR

    Sahar Abdelnabi posted on X that she is hiring a postdoc or PhD student for work on privacy and contextual integrity in AI agents. The role is co-advised with Niloofar Mireshghallah and is set to begin as soon as possible. Abdelnabi, a principal investigator at the ELLIS Institute Tübingen and MPI-IS, described the opening as the first of additional projects she plans to announce.

    Combined views

    37.9K

    1 Source, first seen 26d ago

    Combined views

    37.9K

    1 Source, first seen 26d ago

    291 likes
    26d ago
    first seen 26d ago
    291 likes
    4 comments
    197 saves
    35 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    4 comments
    197 saves
    35 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    1 Source

    @sahar_abdelnabi📢 Hiring announcement!! As promised in my earlier post about more projects to come, I am very excited to share an open position, co-advised with Niloofar Mireshghallah (@niloofar_mire)! We are looking for a Postdoc or a PhD student to work with us on privacy and contextual integrity in AI agents, to start as soon as possible! Today's agents tend to see instructions, messages, memories, and tool outputs as one flattened stream of text. They are not very good at distinguishing information that is useful from information that is appropriate to use here, for this person now with their current preferences and relationships, and for this purpose. The project spans single-agent and multi-agent settings. In a single turn, an agent may face ambiguous instructions, incomplete authority, conflicting goals, stale assumptions, or context that has been deliberately manipulated. Over weeks or months, the same agent may accumulate memories, observe changing teams and dependencies, and act on earlier inferences that were never explicitly authorized. In a network, agents representing different users must coordinate, but their interaction may either protect private boundaries or dissolve them. We want to make these questions concrete enough to train and evaluate systems where privacy and utility have to be studied together. The position is fully-funded and based in Tübingen (formal primary host) with potential research visits at CMU (details to be determined and discussed with the applicant). We have generous funding and compute, so come work with us! More details about the project and how to apply: https://docs.google.com/forms/d/e/1FAIpQLSd_LmrBlnovzNTcl4Jgors5x1f-jhTcnmy8lUq6DquleCy_JA/viewform?usp=dialog

    1 Source

    @sahar_abdelnabi📢 Hiring announcement!! As promised in my earlier post about more projects to come, I am very excited to share an open position, co-advised with Niloofar Mireshghallah (@niloofar_mire)! We are looking for a Postdoc or a PhD student to work with us on privacy and contextual integrity in AI agents, to start as soon as possible! Today's agents tend to see instructions, messages, memories, and tool outputs as one flattened stream of text. They are not very good at distinguishing information that is useful from information that is appropriate to use here, for this person now with their current preferences and relationships, and for this purpose. The project spans single-agent and multi-agent settings. In a single turn, an agent may face ambiguous instructions, incomplete authority, conflicting goals, stale assumptions, or context that has been deliberately manipulated. Over weeks or months, the same agent may accumulate memories, observe changing teams and dependencies, and act on earlier inferences that were never explicitly authorized. In a network, agents representing different users must coordinate, but their interaction may either protect private boundaries or dissolve them. We want to make these questions concrete enough to train and evaluate systems where privacy and utility have to be studied together. The position is fully-funded and based in Tübingen (formal primary host) with potential research visits at CMU (details to be determined and discussed with the applicant). We have generous funding and compute, so come work with us! More details about the project and how to apply: https://docs.google.com/forms/d/e/1FAIpQLSd_LmrBlnovzNTcl4Jgors5x1f-jhTcnmy8lUq6DquleCy_JA/viewform?usp=dialog