More Like this

1. Near-Optimal Differentially Private Reinforcement Learning

   Qiao, Dan; Wang, Yu-Xiang (April 2023, Proceedings of Machine Learning Research)

   Ruiz, Francisco and (Ed.)

   Motivated by personalized healthcare and other applications involving sensitive data, we study online exploration in reinforcement learning with differential privacy (DP) constraints. Existing work on this problem established that no-regret learning is possible under joint differential privacy (JDP) and local differential privacy (LDP) but did not provide an algorithm with optimal regret. We close this gap for the JDP case by designing an $$\epsilon$$-JDP algorithm with a regret of $$\widetilde{O}(\sqrt{SAH^2T}+S^2AH^3/\epsilon)$$ which matches the information-theoretic lower bound of non-private learning for all choices of $$\epsilon> S^{1.5}A^{0.5} H^2/\sqrt{T}$$. In the above, $$S$$, $$A$$ denote the number of states and actions, $$H$$ denotes the planning horizon, and $$T$$ is the number of steps. To the best of our knowledge, this is the first private RL algorithm that achieves privacy for free asymptotically as $$T\rightarrow \infty$$. Our techniques — which could be of independent interest — include privately releasing Bernstein-type exploration bonuses and an improved method for releasing visitation statistics. The same techniques also imply a slightly improved regret bound for the LDP case. 

   more » « less
2. Near-Optimal Differentially Private Reinforcement Learning

   Qiao, Dan; Wang, Yu-Xiang (April 2023, Proceedings of Machine Learning Research)

   Motivated by personalized healthcare and other applications involving sensitive data, we study online exploration in reinforcement learning with differential privacy (DP) constraints. Existing work on this problem established that no-regret learning is possible under joint differential privacy (JDP) and local differential privacy (LDP) but did not provide an algorithm with optimal regret. We close this gap for the JDP case by designing an ϵ-JDP algorithm with a regret of O˜(sqrt(SAH^2T) +S^2AH^3/ϵ) which matches the information-theoretic lower bound of non-private learning for all choices of ϵ>S^1.5A^0.5H^2/sqrt(T). In the above, S, A denote the number of states and actions, H denotes the planning horizon, and T is the number of steps. To the best of our knowledge, this is the first private RL algorithm that achieves \emph{privacy for free} asymptotically as T→∞. Our techniques -- which could be of independent interest -- include privately releasing Bernstein-type exploration bonuses and an improved method for releasing visitation statistics. The same techniques also imply a slightly improved regret bound for the LDP case. 

   more » « less
3. Exploring Use of Explanative Illustrations to Communicate Differential Privacy Models

   https://doi.org/10.1177/21695067231195006  

   Xiong, Aiping; Wu, Chuhao; Wang, Tianhao; Proctor, Robert W.; Blocki, Jeremiah; Li, Ninghui; Jha, Somesh (September 2023, Proceedings of the Human Factors and Ergonomics Society Annual Meeting)

   Proper communication is key to the adoption and implementation of differential privacy (DP). In this work, we designed explanative illustrations of three DP models (Central DP, Local DP, Shuffler DP) to help laypeople conceptualize how random noise is added to protect individuals’ privacy and preserve group utility. Following a pilot survey and an interview, we conducted an online experiment ( N = 300) exploring participants’ comprehension, privacy and utility perception, and data-sharing decisions across the three DP models. We obtained empirical evidence showing participants’ acceptance of the Shuffler DP model for data privacy protection. We discuss the implications of our findings. 

   more » « less
4. Improving Utility and Security of the Shuffler based Differential Privacy

   https://doi.org/10.14778/3424573.3424576  

   Wang, Tianhao; Ding, Bolin; Xu, Min; Huang, Zhicong; Hong, Cheng; Zhou, Jingren; Li, Ninghui; Jha, Somesh (August 2020, Proceedings of the VLDB Endowment)

   When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent it to the central aggregator. LDP imposes large amount of noise as each user executes the randomization independently. To address this issue, recent work introduced an intermediate server with the assumption that this intermediate server does not collude with the aggregator. Under this assumption, less noise can be added to achieve the same privacy guarantee as LDP, thus improving utility for the data collection task. This paper investigates this multiple-party setting of LDP. We analyze the system model and identify potential adversaries. We then make two improvements: a new algorithm that achieves a better privacy-utility tradeoff; and a novel protocol that provides better protection against various attacks. Finally, we perform experiments to compare different methods and demonstrate the benefits of using our proposed method. 

   more » « less
5. Discrete distribution estimation under user-level local differential privacy

   Acharya, Jayadev; Liu, Yuhan; Sun, Ziteng (April 2023, Proceedings of Machine Learning Research)

   Ruiz, Francisco; Dy, Jennifer; van de Meent, Jan-Willem (Ed.)

   We study discrete distribution estimation under user-level local differential privacy (LDP). In user-level $$\varepsilon$$-LDP, each user has $$m\ge1$$ samples and the privacy of all $$m$$ samples must be preserved simultaneously. We resolve the following dilemma: While on the one hand having more samples per user should provide more information about the underlying distribution, on the other hand, guaranteeing the privacy of all $$m$$ samples should make the estimation task more difficult. We obtain tight bounds for this problem under almost all parameter regimes. Perhaps surprisingly, we show that in suitable parameter regimes, having $$m$$ samples per user is equivalent to having $$m$$ times more users, each with only one sample. Our results demonstrate interesting phase transitions for $$m$$ and the privacy parameter $$\varepsilon$$ in the estimation risk. Finally, connecting with recent results on shuffled DP, we show that combined with random shuffling, our algorithm leads to optimal error guarantees (up to logarithmic factors) under the central model of user-level DP in certain parameter regimes. We provide several simulations to verify our theoretical findings. 

   more » « less