Separating Oblivious and Adaptive Differential Privacy under Continual Observation
This work addresses a foundational problem in privacy-preserving streaming algorithms, providing a theoretical separation that clarifies the limitations of adaptive privacy in continual observation settings.
The paper resolves an open question by demonstrating a separation between oblivious and adaptive differential privacy under continual observation, showing that an oblivious algorithm remains accurate for exponentially many time steps, while any adaptive algorithm fails after a constant number of steps.
We resolve an open question of Jain, Raskhodnikova, Sivakumar, and Smith (ICML 2023) by exhibiting a problem separating differential privacy under continual observation in the oblivious and adaptive settings. The continual observation (a.k.a. continual release) model formalizes privacy for streaming algorithms, where data is received over time and output is released at each time step. In the oblivious setting, privacy need only hold for data streams fixed in advance; in the adaptive setting, privacy is required even for streams that can be chosen adaptively based on the streaming algorithm's output. We describe the first explicit separation between the oblivious and adaptive settings. The problem showing this separation is based on the correlated vector queries problem of Bun, Steinke, and Ullman (SODA 2017). Specifically, we present an $(\varepsilon,0)$-DP algorithm for the oblivious setting that remains accurate for exponentially many time steps in the dimension of the input. On the other hand, we show that every $(\varepsilon,δ)$-DP adaptive algorithm fails to be accurate after releasing output for only a constant number of time steps.