Measure-Observe-Remeasure: An Interactive Paradigm for Differentially-Private Exploratory Analysis

Abstract

Differential privacy (DP) has the potential to enable privacy-preserving analysis on sensitive data, but requires analysts to judiciously spend a limited ``privacy loss budget'' $\epsilon$ across queries. Analysts conducting exploratory analyses do not, however, know all queries in advance and seldom have DP expertise. Thus, they are limited in their ability to specify $\epsilon$ allotments across queries prior to an analysis. To support analysts in spending $\epsilon$ efficiently, we propose a new interactive analysis paradigm, Measure-Observe-Remeasure, where analysts ``measure'' the database with a limited amount of $\epsilon$, observe estimates and their errors, and remeasure with more $\epsilon$ as needed. We instantiate the paradigm in an interactive visualization interface which allows analysts to spend increasing amounts of $\epsilon$ under a total budget. To observe how analysts interact with the Measure-Observe-Remeasure paradigm via the interface, we conduct a user study that compares the utility of $\epsilon$ allocations and findings from sensitive data participants make to the allocations and findings expected of a rational agent who faces the same decision task. We find that participants are able to use the workflow relatively successfully, including using budget allocation strategies that maximize over half of the available utility stemming from $\epsilon$ allocation. Their loss in performance relative to a rational agent appears to be driven more by their inability to access information and report it than to allocate $\epsilon$.

Published in IEEE Symposium on Security and Privacy (SP) 2024

References in corpus (10)

• LLaMA: Open and Efficient Foundation Language Models
• ChatGPT and Software Testing Education: Promises & Perils
• Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
• Prompt Injection attack against LLM-integrated Applications
• Anatomy of an AI-powered malicious social botnet
• Beyond the Safeguards: Exploring the Security Risks of ChatGPT
• Evaluating topic coherence measures
• "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
• Targeted Phishing Campaigns using Large Scale Language Models
• Evaluating ChatGPT's Performance for Multilingual and Emoji-based Hate Speech Detection

Cited by in corpus (5)

• Can Features for Phishing URL Detection Be Trusted Across Diverse Datasets? A Case Study with Explainable AI
• Lateral Phishing With Large Language Models: A Large Organization Comparative Study
• The Impact of Emerging Phishing Threats: Assessing Quishing and LLM-generated Phishing Emails against Organizations
• Phishing Detection in the Gen-AI Era: Quantized LLMs vs Classical Models
• Anti-Phishing Training (Still) Does Not Work: A Large-Scale Reproduction of Phishing Training Inefficacy Grounded in the NIST Phish Scale