103 citations · 301 across the 19 of their papers we have counts for
20 papers
A Floating-Point Secure Implementation of the Report Noisy Max with Gap Mechanism
Zeyu Ding, John Durrell, Daniel Kifer +5
The Noisy Max mechanism and its variations are fundamental private selection algorithms that are used to select items from a set of candidates (such as the most common diseases in…
ResidualPlanner+: a scalable matrix mechanism for marginals and beyond
Guanlin He, Yingtai Xiao, Levent Toksoz +3
Noisy marginals are a common form of confidentiality protecting data release and are useful for many downstream tasks such as contingency table analysis, construction of Bayesian n…
Answering Private Linear Queries Adaptively using the Common Mechanism
Yingtai Xiao, Guanhong Wang, Danfeng Zhang +1
When analyzing confidential data through a privacy filter, a data scientist often needs to decide which queries will best support their intended analysis. For example, an analyst m…
Reconstruction Attacks on Aggressive Relaxations of Differential Privacy
Prottay Protivash, John Durrell, Zeyu Ding +2
Differential privacy is a widely accepted formal privacy definition that allows aggregate information about a dataset to be released while controlling privacy leakage for individua…
Demystifying Arch-hints for Model Extraction: An Attack in Unified Memory System
Zhendong Wang, Xiaoming Zeng, Xulong Tang +3
The deep neural network (DNN) models are deemed confidential due to their unique value in expensive training efforts, privacy-sensitive training data, and proprietary network chara…
Exact Privacy Analysis of the Gaussian Sparse Histogram Mechanism
Brian Karrer, Daniel Kifer, Arjun Wilkins +1
Sparse histogram methods can be useful for returning differentially private counts of items in large or infinite histograms, large group-by queries, and more generally, releasing a…
Towards a General-Purpose Dynamic Information Flow Policy
Peixuan Li, Danfeng Zhang
Noninterference offers a rigorous end-to-end guarantee for secure propagation of information. However, real-world systems almost always involve security requirements that change du…
DPGen: Automated Program Synthesis for Differential Privacy
Yuxin Wang, Zeyu Ding, Yingtai Xiao +2
Differential privacy has become a de facto standard for releasing data in a privacy-preserving way. Creating a differentially private algorithm is a process that often starts with…
Understanding TEE Containers, Easy to Use? Hard to Trust
Weijie Liu, Hongbo Chen, XiaoFeng Wang +4
As an emerging technique for confidential computing, trusted execution environment (TEE) receives a lot of attention. To better develop, deploy, and run secure applications on a TE…
The Permute-and-Flip Mechanism is Identical to Report-Noisy-Max with Exponential Noise
Zeyu Ding, Daniel Kifer, Sayed M. Saghaian N. E. +4
The permute-and-flip mechanism is a recently proposed differentially private selection algorithm that was shown to outperform the exponential mechanism. In this paper, we show that…
Free Gap Estimates from the Exponential Mechanism, Sparse Vector, Noisy Max and Related Algorithms
Zeyu Ding, Yuxin Wang, Yingtai Xiao +3
Private selection algorithms, such as the Exponential Mechanism, Noisy Max and Sparse Vector, are used to select items (such as queries with large answers) from a set of candidates…
Optimizing Fitness-For-Use of Differentially Private Linear Queries
Yingtai Xiao, Zeyu Ding, Yuxin Wang +2
In practice, differentially private data releases are designed to support a variety of applications. A data release is fit for use if it meets target accuracy requirements for each…
CheckDP: An Automated and Integrated Approach for Proving Differential Privacy or Finding Precise Counterexamples
Yuxin Wang, Zeyu Ding, Daniel Kifer +1
We propose CheckDP, the first automated and integrated approach for proving or disproving claims that a mechanism is differentially private. CheckDP can find counterexamples for me…
Guidelines for Implementing and Auditing Differentially Private Systems
Daniel Kifer, Solomon Messing, Aaron Roth +2
Differential privacy is an information theoretic constraint on algorithms and code. It provides quantification of privacy leakage and formal privacy guarantees that are currently c…
Identifying Cache-Based Side Channels through Secret-Augmented Abstract Interpretation
Shuai Wang, Yuyan Bao, Xiao Liu +3
Cache-based side channels enable a dedicated attacker to reveal program secrets by measuring the cache access patterns. Practical attacks have been shown against real-world crypto…
Free Gap Information from the Differentially Private Sparse Vector and Noisy Max Mechanisms
Zeyu Ding, Yuxin Wang, Danfeng Zhang +1
Noisy Max and Sparse Vector are selection algorithms for differential privacy and serve as building blocks for more complex algorithms. In this paper we show that both algorithms c…
Proving Differential Privacy with Shadow Execution
Yuxin Wang, Zeyu Ding, Guanhong Wang +2
Recent work on formal verification of differential privacy shows a trend toward usability and expressiveness -- generating a correctness proof of sophisticated algorithm while mini…
Detecting Violations of Differential Privacy
Zeyu Ding, Yuxin Wang, Guanhong Wang +2
The widespread acceptance of differential privacy has led to the publication of many sophisticated algorithms for protecting privacy. However, due to the subtle nature of this priv…
Towards a Flow- and Path-Sensitive Information Flow Analysis: Technical Report
Peixuan Li, Danfeng Zhang
This paper investigates a flow- and path-sensitive static information flow analysis. Compared with security type systems with fixed labels, it has been shown that flow-sensitive ty…
LightDP: Towards Automating Differential Privacy Proofs
Danfeng Zhang, Daniel Kifer
The growing popularity and adoption of differential privacy in academic and industrial settings has resulted in the development of increasingly sophisticated algorithms for releasi…