More Like this

1. SAMPL: Scalable Auditability of Monitoring Processes using Public Ledgers

   https://doi.org/10.1145/3319535.3354219  

   Panwar, Gaurav ; Vishwanathan, Roopa ; Misra, Satyajayant ; Bos, Austin ( January 2019 , Session 9E: Web Censorship and Auditing)

   Organized surveillance, especially by governments poses a major challenge to individual privacy, due to the resources governments have at their disposal, and the possibility of overreach. Given the impact of invasive monitoring, in most democratic countries, government surveillance is, in theory, monitored and subject to public oversight to guard against violations. In practice, there is a difficult fine balance between safeguarding individual’s privacy rights and not diluting the efficacy of national security investigations, as exemplified by reports on government surveillance programs that have caused public controversy, and have been challenged by civil and privacy rights organizations. Surveillance is generally conducted through a mechanism where federal agencies obtain a warrant from a federal or state judge (e.g., the US FISA court, Supreme Court in Canada) to subpoena a company or service-provider (e.g., Google, Microsoft) for their customers’ data. The courts provide annual statistics on the requests (accepted, rejected), while the companies provide annual transparency reports for public auditing. However, in practice, the statistical information provided by the courts and companies is at a very high level, generic, is released after-the-fact, and is inadequate for auditing the operations. Often this is attributed to the lack of scalable mechanisms for reporting and transparentmore »auditing. In this paper, we present SAMPL, a novel auditing framework which leverages cryptographic mechanisms, such as zero knowledge proofs, Pedersen commitments, Merkle trees, and public ledgers to create a scalable mechanism for auditing electronic surveillance processes involving multiple actors. SAMPL is the first framework that can identify the actors (e.g., agencies and companies) that violate the purview of the court orders. We experimentally demonstrate the scalability for SAMPL for handling concurrent monitoring processes without undermining their secrecy and auditability.« less
2. Scalable Differential Privacy with Certified Robustness in Adversarial Learning

   Phan, Hai ; Thai, My T. ; Hu, Han ; Jin, Ruoming ; Sun, Tong ; Dou, Dejing ( July 2020 , Proceedings of the 37th International Conference on Machine Learning)

   In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to adversarial examples. By leveraging the sequential composition theory in DP, we randomize both input and latent spaces to strengthen our certified robustness bounds. To address the trade-off among model utility, privacy loss, and robustness, we design an original adversarial objective function, based on the post-processing property in DP, to tighten the sensitivity of our model. A new stochastic batch training is proposed to apply our mechanism on large DNNs and datasets, by bypassing the vanilla iterative batch-by-batch training in DP DNNs. An end-to-end theoretical analysis and evaluations show that our mechanism notably improves the robustness and scalability of DP DNNs.
3. Scalable Differential Privacy with Certified Robustness in Adversarial Learning

   Phan, NhatHai ; Thai, My T. ; Hu, Han ; Jin, Ruoming ; Sun, Tong ; Dou, Dejing ( July 2022 , Proceedings of the 37th International Conference on Machine Learning)

   In this paper, we aim to develop a scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to adversarial examples. By leveraging the sequential composition theory in DP, we randomize both input and latent spaces to strengthen our certified robustness bounds. To address the trade-off among model utility, privacy loss, and robustness, we design an original adversarial objective function, based on the post-processing property in DP, to tighten the sensitivity of our model. A new stochastic batch training is proposed to apply our mechanism on large DNNs and datasets, by bypassing the vanilla iterative batch-by-batch training in DP DNNs. An end-to-end theoretical analysis and evaluations show that our mechanism notably improves the robustness and scalability of DP DNNs.
4. DPavatar: A Real-time Location Protection Framework for Incumbent Users in Cognitive Radio Networks

   https://doi.org/10.1109/TMC.2019.2897099  

   Liu, Jianqing ; Zhang, Chi ; Lorenzo, Beatriz ; Fang, Yuguang ( February 2019 , IEEE Transactions on Mobile Computing)

   Dynamic spectrum sharing between licensed incumbent users (IUs) and unlicensed wireless industries has been well recognized as an efficient approach to solving spectrum scarcity as well as creating spectrum markets. Recently, both U.S. and European governments called a ruling on opening up spectrum that was initially licensed to sensitive military/federal systems. However, this introduces serious concerns on operational privacy (e.g., location, time and frequency of use) of IUs for national security concerns. Although several works have proposed obfuscation methods to address this problem, these techniques only rely on syntactic privacy models, lacking rigorous privacy guarantee. In this paper, we propose a comprehensive framework to provide real-time differential location privacy for sensitive IUs. We design a utility-optimal differentially private mechanism to reduce the loss in spectrum efficiency while protecting IUs from harmful interference. Furthermore, we strategically combine differential privacy with another privacy notion, expected inference error, to provide double shield protection for IU’s location privacy. Extensive simulations are conducted to validate our design and demonstrate significant improvements in utility and location privacy compared with other existing mechanisms.
5. Privacy-Aware Rejection Sampling

   Awan, Jordan ; Rao, Vinayak ( February 2023 , Journal of machine learning research)

   Weller, Adrian (Ed.)

   While differential privacy (DP) offers strong theoretical privacy guarantees, implementations of DP mechanisms may be vulnerable to side-channel attacks, such as timing attacks. When sampling methods such as MCMC or rejection sampling are used to implement a privacy mechanism, the runtime can leak private information. We characterize the additional privacy cost due to the runtime of a rejection sampler in terms of both (, δ)-DP as well as f -DP. We also show that unless the acceptance probability is constant across databases, the runtime of a rejection sampler does not satisfy -DP for any . We show that there is a similar breakdown in privacy with adaptive rejection samplers. We propose three modifications to the rejection sampling algorithm, with varying assumptions, to protect against timing attacks by making the runtime independent of the data. The modification with the weakest assumptions is an approximate sampler, introducing a small increase in the privacy cost, whereas the other modifications give perfect samplers. We also use our techniques to develop an adaptive rejection sampler for log-H ̈older densities, which also has data-independent runtime. We give several examples of DP mechanisms that fit the assumptions of our methods and can thus be implemented using ourmore »samplers.« less