95 citations · 855 across the 81 of their papers we have counts for
18 papers · 1 filter
Sample Complexity of Adversarially Robust Linear Classification on Separated Data
Robi Bhattacharjee, Somesh Jha, Kamalika Chaudhuri
We consider the sample complexity of learning with adversarial robustness. Most prior theoretical results for this problem have considered a setting where different classes in 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…
A General Framework For Detecting Anomalous Inputs to DNN Classifiers
Jayaram Raghuram, Varun Chandrasekaran, Somesh Jha +1
Detecting anomalous inputs, such as adversarial and out-of-distribution (OOD) inputs, is critical for classifiers (including deep neural networks or DNNs) deployed in real-world ap…
Interval Universal Approximation for Neural Networks
Zi Wang, Aws Albarghouthi, Gautam Prakriya +1
To verify safety and robustness of neural networks, researchers have successfully applied abstract interpretation, primarily using the interval abstract domain. In this paper, we s…
Robust and Accurate Authorship Attribution via Program Normalization
Yizhen Wang, Mohannad Alhanahnah, Ke Wang +2
Source code attribution approaches have achieved remarkable accuracy thanks to the rapid advances in deep learning. However, recent studies shed light on their vulnerability to adv…
ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining
Jiefeng Chen, Yixuan Li, Xi Wu +2
Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in an open-world setting. However, existing OOD detection solutions can be brittle…
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…
Representation Bayesian Risk Decompositions and Multi-Source Domain Adaptation
Xi Wu, Yang Guo, Jiefeng Chen +3
We consider representation learning (hypothesis class ) where training and test distributions can be different. Recent studies provide hi…
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…
Analyzing Accuracy Loss in Randomized Smoothing Defenses
Yue Gao, Harrison Rosenberg, Kassem Fawaz +2
Recent advances in machine learning (ML) algorithms, especially deep neural networks (DNNs), have demonstrated remarkable success (sometimes exceeding human-level performance) on s…
A Separation Result Between Data-oblivious and Data-aware Poisoning Attacks
Samuel Deng, Sanjam Garg, Somesh Jha +3
Poisoning attacks have emerged as a significant security threat to machine learning algorithms. It has been demonstrated that adversaries who make small changes to the training set…
Robust Out-of-distribution Detection for Neural Networks
Jiefeng Chen, Yixuan Li, Xi Wu +2
Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in the real world. Existing approaches for detecting OOD examples work well when ev…
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.…
CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods
Wei Zhang, Thomas Kobber Panum, Somesh Jha +2
We study the problem of learning Granger causality between event types from asynchronous, interdependent, multi-type event sequences. Existing work suffers from either limited mode…
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…
Semantic Robustness of Models of Source Code
Goutham Ramakrishnan, Jordan Henkel, Zi Wang +3
Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where…