95 citations · 855 across the 81 of their papers we have counts for
31 papers · 1 filter
Differentially Private Paired Table-Image Multimodal Synthesis
Kai Chen, Josephine Lamp, Somesh Jha +1
Differentially private (DP) synthesis has been extensively studied for tabular and image data separately, yet many real-world datasets contain images paired with multivariate tabul…
Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems
Debopam Sanyal, Jui-Tse Hung, Manav Agrawal +6
Model-serving systems have become increasingly popular, especially in real-time web applications. In such systems, users send queries to the server and specify the desired performa…
Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks
Ryan Feng, Ashish Hooda, Neal Mangaokar +3
Recent work has proposed stateful defense models (SDMs) as a compelling strategy to defend against a black-box attacker who only has query access to the model, as is common for onl…
Formal Analysis of the API Proxy Problem
Somesh Jha, Mihai Christodorescu, Anh Pham
Implementing a security mechanism on top of APIs requires clear understanding of the semantics of each API, to ensure that security entitlements are enforced consistently and compl…
Federated Boosted Decision Trees with Differential Privacy
Samuel Maddock, Graham Cormode, Tianhao Wang +2
There is great demand for scalable, secure, and efficient privacy-preserving machine learning models that can be trained over distributed data. While deep learning models typically…
Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms
Saeed Mahloujifar, Alexandre Sablayrolles, Graham Cormode +1
Given a trained model and a data sample, membership-inference (MI) attacks predict whether the sample was in the model's training set. A common countermeasure against MI attacks is…
Using Illustrations to Communicate Differential Privacy Trust Models: An Investigation of Users' Comprehension, Perception, and Data Sharing Decision
Aiping Xiong, Chuhao Wu, Tianhao Wang +4
Proper communication is key to the adoption and implementation of differential privacy (DP). However, a prior study found that laypeople did not understand the data perturbation pr…
EIFFeL: Ensuring Integrity for Federated Learning
Amrita Roy Chowdhury, Chuan Guo, Somesh Jha +1
Federated learning (FL) enables clients to collaborate with a server to train a machine learning model. To ensure privacy, the server performs secure aggregation of updates from th…
NeuraCrypt is not private
Nicholas Carlini, Sanjam Garg, Somesh Jha +3
NeuraCrypt (Yara et al. arXiv 2021) is an algorithm that converts a sensitive dataset to an encoded dataset so that (1) it is still possible to train machine learning models on the…
ShadowNet: A Secure and Efficient On-device Model Inference System for Convolutional Neural Networks
Zhichuang Sun, Ruimin Sun, Changming Liu +3
With the increased usage of AI accelerators on mobile and edge devices, on-device machine learning (ML) is gaining popularity. Thousands of proprietary ML models are being deployed…
Is Private Learning Possible with Instance Encoding?
Nicholas Carlini, Samuel Deng, Sanjam Garg +6
A private machine learning algorithm hides as much as possible about its training data while still preserving accuracy. In this work, we study whether a non-private learning algori…
Strengthening Order Preserving Encryption with Differential Privacy
Amrita Roy Chowdhury, Bolin Ding, Somesh Jha +2
Ciphertexts of an order-preserving encryption (OPE) scheme preserve the order of their corresponding plaintexts. However, OPEs are vulnerable to inference attacks that exploit this…
Continuous Release of Data Streams under both Centralized and Local Differential Privacy
Tianhao Wang, Joann Qiongna Chen, Zhikun Zhang +5
In this paper, we study the problem of publishing a stream of real-valued data satisfying differential privacy (DP). One major challenge is that the maximal possible value can be q…
Towards Effective Differential Privacy Communication for Users' Data Sharing Decision and Comprehension
Aiping Xiong, Tianhao Wang, Ninghui Li +1
Differential privacy protects an individual's privacy by perturbing data on an aggregated level (DP) or individual level (LDP). We report four online human-subject experiments inve…
Face-Off: Adversarial Face Obfuscation
Varun Chandrasekaran, Chuhan Gao, Brian Tang +3
Advances in deep learning have made face recognition technologies pervasive. While useful to social media platforms and users, this technology carries significant privacy threats.…
GRAPHITE: Generating Automatic Physical Examples for Machine-Learning Attacks on Computer Vision Systems
Ryan Feng, Neal Mangaokar, Jiefeng Chen +3
This paper investigates an adversary's ease of attack in generating adversarial examples for real-world scenarios. We address three key requirements for practical attacks for the r…
Improving Utility and Security of the Shuffler-based Differential Privacy
Tianhao Wang, Bolin Ding, Min Xu +5
When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent it to the centr…
Crypt: Crypto-Assisted Differential Privacy on Untrusted Servers
Amrita Roy Chowdhury, Chenghong Wang, Xi He +2
Differential privacy (DP) has steadily become the de-facto standard for achieving privacy in data analysis, which is typically implemented either in the "central" or "local" model.…
Adversarial Binaries for Authorship Identification
Xiaozhu Meng, Barton P. Miller, Somesh Jha
Binary code authorship identification determines authors of a binary program. Existing techniques have used supervised machine learning for this task. In this paper, we look this p…
Towards Understanding Limitations of Pixel Discretization Against Adversarial Attacks
Jiefeng Chen, Xi Wu, Vaibhav Rastogi +2
Wide adoption of artificial neural networks in various domains has led to an increasing interest in defending adversarial attacks against them. Preprocessing defense methods such a…
OAT: Attesting Operation Integrity of Embedded Devices
Zhichuang Sun, Bo Feng, Long Lu +1
Due to the wide adoption of IoT/CPS systems, embedded devices(IoT frontends) become increasingly connected and mission-critical, which in turn has attracted advanced attacks (e.g.,…
Malware Lineage in the Wild
Irfan Ul Haq, Sergio Chica, Juan Caballero +1
Malware lineage studies the evolutionary relationships among malware and has important applications for malware analysis. A persistent limitation of prior malware lineage approache…
Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting
Samuel Yeom, Irene Giacomelli, Matt Fredrikson +1
Machine learning algorithms, when applied to sensitive data, pose a distinct threat to privacy. A growing body of prior work demonstrates that models produced by these algorithms m…
Locally Differentially Private Heavy Hitter Identification
Tianhao Wang, Ninghui Li, Somesh Jha
The notion of Local Differential Privacy (LDP) enables users to answer sensitive questions while preserving their privacy. The basic LDP frequent oracle protocol enables the aggreg…