4 papers
Certification of Machine Learning Models via Directional Sharpness
Gefei Tan, Adria Gascon, Sarah Meiklejohn +1
In machine learning, model certification has been identified as an important method for gaining assurance about a model's trustworthiness and quality. A model's quality is largely…
HelpBench: Assessing the Ability of LLMs to Provide Privacy, Safety, and Security Advice
Sarah Meiklejohn, Sunny Consolvo, Patrick Gage Kelley +5
This paper introduces HelpBench, a benchmark for assessing whether LLMs are capable of providing accurate help in response to questions about digital privacy, safety, and security.…
Machine Learning Models Have a Supply Chain Problem
Sarah Meiklejohn, Hayden Blauzvern, Mihai Maruseac +3
Powerful machine learning (ML) models are now readily available online, which creates exciting possibilities for users who lack the deep technical expertise or substantial computin…
Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography
Ilia Shumailov, Daniel Ramage, Sarah Meiklejohn +4
We often interact with untrusted parties. Prioritization of privacy can limit the effectiveness of these interactions, as achieving certain goals necessitates sharing private data.…