News from the team
Research, awards, events, and company news from the Sentinel team.
Awards 3
Award Distinguished Paper at NDSS 2026: Fuzzilicon finds hidden flaws inside real x86 CPUs
Our paper on fuzzing real x86 CPUs through their microcode won a Distinguished Paper Award at NDSS 2026. Here's what it found.
Read more →Award Best paper at COPA 2024: conformal prediction under data contamination
Our award-winning paper on conformal prediction under contaminated calibration data. Here's what it found.
Read more →Award Best paper at NeurIPS 2017: a goodness-of-fit test that scales linearly
Our NeurIPS 2017 best paper on a goodness-of-fit test that scales linearly with sample size. Here's what it found.
Read more →Workshops 1
Workshop STALA 2027: we're co-organizing a workshop on security testing for LLMs and agents at NDSS 2027
A workshop at NDSS 2027 in Seoul on one question: how do we know whether an LLM or agent is secure enough? Paper submissions are due 11 December 2026.
Read more →Papers 7
Paper NeST: making LLMs safer by tuning a few neurons, accepted at IEEE S&P 2027
Our paper on making LLMs safer by tuning only a small set of safety-relevant neurons was accepted at IEEE S&P 2027. Here's what NeST does.
Read more →Paper A general theory of data corruption, published in JMLR
Our paper building a general theory of data corruption in supervised learning was published in the Journal of Machine Learning Research. Here's what it found.
Read more →Paper GateBreaker: our attack on Mixture-of-Experts LLM safety, accepted at USENIX Security 2026
Our paper on attacking safety alignment in Mixture-of-Experts LLMs was accepted at USENIX Security 2026. Here's what GateBreaker found.
Read more →Paper NeuroStrike: our attack on LLM safety alignment is heading to NDSS 2026
Our paper on neuron-level attacks against aligned LLMs was accepted at NDSS Symposium 2026. Here's what it found.
Read more →Paper Testing generative models that don't give you a probability, published at NeurIPS 2022
Our NeurIPS 2022 paper on testing generative models that only give you samples, not probabilities. Here's what it found.
Read more →Book Our book on learning without clean labels, published by MIT Press
Our book on learning from incomplete and imperfect labels was published by MIT Press. Here's what it covers.
Read more →Paper Testing whether a model fits data on curved spaces, published at ICML 2021
Our ICML 2021 paper on goodness-of-fit testing for models on curved geometric spaces. Here's what it found.
Read more →