5 papers
Boundary-targeted Membership Inference Attacks on Safety Classifiers
Anthony Hughes, Alexander Goldberg, Prince Jha +3
Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with large language models. Despit…
Smooth Partial Lotteries for Stable Randomized Selection
Alexander Goldberg, Giulia Fanti, Nihar B. Shah
Competitive selection processes, from scientific funding to admissions and hiring, use evaluations to score candidates, and eventually choose a subset of them based on those scores…
A Principled Approach to Randomized Selection under Uncertainty: Applications to Peer Review and Grant Funding
Alexander Goldberg, Giulia Fanti, Nihar B. Shah
Many decision-making processes involve evaluating and then selecting items; examples include scientific peer review, job hiring, school admissions, and investment decisions. The ev…
Benchmarking Fraud Detectors on Private Graph Data
Alexander Goldberg, Giulia Fanti, Nihar Shah +1
We introduce the novel problem of benchmarking fraud detectors on private graph-structured data. Currently, many types of fraud are managed in part by automated detection algorithm…
Do AI assistants help students write formal specifications? A study with ChatGPT and the B-Method
Alfredo Capozucca, Daniil Yampolskyi, Alexander Goldberg +1
This paper investigates the role of AI assistants, specifically OpenAI's ChatGPT, in teaching formal methods (FM) to undergraduate students, using the B-method as a formal specific…