arXiv subjects

Christopher Choquette-Choo

Publications and source records attributed to Christopher Choquette-Choo.

2 recordsLinked to original sources

arXiv2024

Auditing Private Prediction

Differential privacy (DP) offers a theoretical upper bound on the potential privacy leakage of analgorithm, while empirical auditing establishes a practical lower bound. Auditing techniques exist forDP training algorithms. However machine learning can also be made private at inference. We propose thefirst framework for auditing private prediction where we instantiate adversaries with varying poisoningand query capabilities. This enables us to study the privacy leakage of four private prediction algorithms:PATE [Papernot et al., 2016], CaPC [Choquette-Choo et al., 2020], PromptPATE [Duan et al., 2023],and Private-kNN [Zhu et al., 2020]. To conduct our audit, we introduce novel techniques to empiricallyevaluate privacy leakage in terms of Renyi DP. Our experiments show that (i) the privacy analysis ofprivate prediction can be improved, (ii) algorithms which are easier to poison lead to much higher privacyleakage, and (iii) the privacy leakage is significantly lower for adversaries without query control than thosewith full control.

cs.CR↗

arXiv2023

Students Parrot Their Teachers: Membership Inference on Model Distillation

Model distillation is frequently proposed as a technique to reduce the privacy leakage of machine learning. These empirical privacy defenses rely on the intuition that distilled ``student'' models protect the privacy of training data, as they only interact with this data indirectly through a ``teacher'' model. In this work, we design membership inference attacks to systematically study the privacy provided by knowledge distillation to both the teacher and student training sets. Our new attacks show that distillation alone provides only limited privacy across a number of domains. We explain the success of our attacks on distillation by showing that membership inference attacks on a private dataset can succeed even if the target model is *never* queried on any actual training points, but only on inputs whose predictions are highly influenced by training data. Finally, we show that our attacks are strongest when student and teacher sets are similar, or when the attacker can poison the teacher set.

cs.CR↗