Lightweight tools for ‘steering’ LLMs down the right pathResearchKim Martineau15 Oct 2025AIAI TransparencyGenerative AITrustworthy AITrustworthy Generation
Protection against data-oriented attacks through selective data integrityTechnical noteHans Liljestrand, Hani Jamjoom, Matthew Hicks, N. Asokan, Danfeng (Daphne) Yao, and Salman Ahmed27 Oct 2023SecuritySecurity Analysis
Protect yourself from bad neighbors in the cloudTechnical noteMichael V. Le, Salman Ahmed, Dan Williams, and Hani Jamjoom07 Jul 2023Data and AI SecuritySecurity