Author

Bilal Syed Arfeen

0 works0 citations

Recent research

AI & ComputingOpen access
SHV-Bench: A Containment-Capability Trade-Off Benchmark for Structural Honesty Verification -- Successor Protocol and Task Corpus Design
SHV-Bench specifies a two-sided benchmark for evaluating whether BSSG containment (DOI 10.5281/zenodo.21713180) changes the measurable outcomes of an AI cybersecurity agent. The contained agent must produce fewer unauthorized effects (Side 1) while maintaining noninferiority on w...
Zenodo (CERN European Organization for Nuclear Research)2026-08-220 citationsDOI
AI & ComputingOpen access
SHV-Bench: A Containment-Capability Trade-Off Benchmark for Structural Honesty Verification -- Successor Protocol and Task Corpus Design
SHV-Bench specifies a two-sided benchmark for evaluating whether BSSG containment (DOI 10.5281/zenodo.21713180) changes the measurable outcomes of an AI cybersecurity agent. The contained agent must produce fewer unauthorized effects (Side 1) while maintaining noninferiority on w...
Zenodo (CERN European Organization for Nuclear Research)2026-08-220 citationsDOI