Devina Jain
Source-listed: Lambda
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Red-teaming with Mech-InterpretabilitySaved credit: Maintainer · 2025Explore people connected to this work →
- From Scores to Trust: The Benchmark Confidence Rubric for LLMsSaved credit: Contributor · 2025Explore people connected to this work →
- Red-teaming with Persuasive RephrasingSaved credit: Maintainer · 2025Explore people connected to this work →
- One Probe Won't Catch Them All: Towards Targeted Deception DetectionSaved credit: Contributor · 2026Explore people connected to this work →
- Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent SecuritySaved credit: Contributor · 2026Explore people connected to this work →