62 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Singapore University of Technology and DesignSG2 papers
- Aarhus UniversityDK1 paper
- Columbia UniversityUS1 paper
- Dalle Molle Institute for Artificial Intelligence ResearchCH1 paper
- Florida State UniversityUS1 paper
- Harvard UniversityUS1 paper
- iTrustSG1 paper
- London School of Economics and Political ScienceGB1 paper
- Microsoft Research New York City (United States)1 paper
- National Museum of EthnologyNL1 paper
- National University of SingaporeSG1 paper
- Ruhr University BochumDE1 paper
Showing 2025Show all
2 papers · 1 filter
cs.LG2025★ 1 cited
Space Explanations of Neural Network Classification
Faezeh Labbaf, Tomáš Kolárik, Martin Blicha +3
We present a novel logic-based concept called Space Explanations for classifying neural networks that gives provable guarantees of the behavior of the network in continuous areas o…
cs.CR2025
Accountable Liveness
Andrew Lewis-Pye, Joachim Neu, Tim Roughgarden +1
Safety and liveness are the two classical security properties of consensus protocols. Recent works have strengthened safety with accountability: should any safety violation occur,…