Somesh Jha

is this you? claim profile

∙ 0 followers
University of Wisconsin-Madison

Professor of Computer Science at University of Wisconsin, Chief Scientist at Tala Systems

Sample Complexity of Adversarially Robust Linear Classification on Separated Data

We consider the sample complexity of learning with adversarial robustnes...
12/19/2020 ∙ by Robi Bhattacharjee, et al. ∙ 6 ∙ share

read it
ShadowNet: A Secure and Efficient System for On-device Model Inference

On-device machine learning (ML) is getting more and more popular as fast...
11/11/2020 ∙ by Zhichuang Sun, et al. ∙ 13 ∙ share

read it
Intertwining Order Preserving Encryption and Differential Privacy

Ciphertexts of an order-preserving encryption (OPE) scheme preserve the ...
09/11/2020 ∙ by Amrita Roy Chowdhury, et al. ∙ 0 ∙ share

read it
Detecting Anomalous Inputs to DNN Classifiers By Joint Statistical Testing at the Layers

Detecting anomalous inputs, such as adversarial and out-of-distribution ...
07/29/2020 ∙ by Jayaram Raghuram, et al. ∙ 16 ∙ share

read it
Abstract Universal Approximation for Neural Networks

With growing concerns about the safety and robustness of neural networks...
07/12/2020 ∙ by Zi Wang, et al. ∙ 9 ∙ share

read it
Robust Learning against Logical Adversaries

Test-time adversarial attacks have posed serious challenges to the robus...
07/01/2020 ∙ by Yizhen Wang, et al. ∙ 57 ∙ share

read it
Continuous Release of Data Streams under both Centralized and Local Differential Privacy

In this paper, we study the problem of publishing a stream of real-value...
05/24/2020 ∙ by Tianhao Wang, et al. ∙ 0 ∙ share

read it
Towards Effective Differential Privacy Communication for Users' Data Sharing Decision and Comprehension

Differential privacy protects an individual's privacy by perturbing data...
03/31/2020 ∙ by Aiping Xiong, et al. ∙ 0 ∙ share

read it
Obliviousness Makes Poisoning Adversaries Weaker

Poisoning attacks have emerged as a significant security threat to machi...
03/26/2020 ∙ by Sanjam Garg, et al. ∙ 5 ∙ share

read it
Face-Off: Adversarial Face Obfuscation

Advances in deep learning have made face recognition increasingly feasib...
03/19/2020 ∙ by Chuhan Gao, et al. ∙ 0 ∙ share

read it
Analyzing Accuracy Loss in Randomized Smoothing Defenses

Recent advances in machine learning (ML) algorithms, especially deep neu...
03/03/2020 ∙ by Yue Gao, et al. ∙ 15 ∙ share

read it
CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods

We study the problem of learning Granger causality between event types f...
02/18/2020 ∙ by Wei Zhang, et al. ∙ 10 ∙ share

read it
Query-Efficient Physical Hard-Label Attacks on Deep Learning Visual Classification

We present Survival-OPT, a physical adversarial example algorithm in the...
02/17/2020 ∙ by Ryan Feng, et al. ∙ 5 ∙ share

read it
Semantic Robustness of Models of Source Code

Deep neural networks are vulnerable to adversarial examples - small inpu...
02/07/2020 ∙ by Goutham Ramakrishnan, et al. ∙ 1 ∙ share

read it
Generating Semantic Adversarial Examples with Differentiable Rendering

Machine learning (ML) algorithms, especially deep neural networks, have ...
10/02/2019 ∙ by Lakshya Jain, et al. ∙ 23 ∙ share

read it
On Need for Topology Awareness of Generative Models

Manifold assumption in learning states that: the data lie approximately ...
09/07/2019 ∙ by Uyeong Jang, et al. ∙ 20 ∙ share

read it
On Need for Topology-Aware Generative Models for Manifold-Based Defenses

ML algorithms or models, especially deep neural networks (DNNs), have sh...
09/07/2019 ∙ by Uyeong Jang, et al. ∙ 0 ∙ share

read it
MURS: Practical and Robust Privacy Amplification with Multi-Party Differential Privacy

When collecting information, local differential privacy (LDP) alleviates...
08/30/2019 ∙ by Tianhao Wang, et al. ∙ 0 ∙ share

read it
Practical and Robust Privacy Amplification with Multi-Party Differential Privacy

When collecting information, local differential privacy (LDP) alleviates...
08/30/2019 ∙ by Tianhao Wang, et al. ∙ 0 ∙ share

read it
Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models

Directed graphical models (DGMs) are a class of probabilistic models tha...
05/30/2019 ∙ by Amrita Roy Chowdhury, et al. ∙ 1 ∙ share

read it
Adversarially Robust Learning Could Leverage Computational Hardness

Over recent years, devising classification algorithms that are robust to...
05/28/2019 ∙ by Sanjam Garg, et al. ∙ 4 ∙ share

read it
Enhancing ML Robustness Using Physical-World Constraints

Recent advances in Machine Learning (ML) have demonstrated that neural n...
05/26/2019 ∙ by Varun Chandrasekaran, et al. ∙ 0 ∙ share

read it
Robust Attribution Regularization

An emerging problem in trustworthy machine learning is to train models t...
05/23/2019 ∙ by Jiefeng Chen, et al. ∙ 4 ∙ share

read it
Attribution-driven Causal Analysis for Detection of Adversarial Examples

Attribution methods have been developed to explain the decision of a mac...
03/14/2019 ∙ by Susmit Jha, et al. ∙ 6 ∙ share

read it
Outis: Crypto-Assisted Differential Privacy on Untrusted Servers

Differential privacy has steadily become the de-facto standard for achie...
02/20/2019 ∙ by Amrita Roy Chowdhury, et al. ∙ 0 ∙ share

read it
Privacy-Preserving Collaborative Prediction using Random Forests

We study the problem of privacy-preserving machine learning (PPML) for e...
11/21/2018 ∙ by Irene Giacomelli, et al. ∙ 2 ∙ share

read it
Model Extraction and Active Learning

Machine learning is being increasingly used by individuals, research ins...
11/05/2018 ∙ by Varun Chandrasekaran, et al. ∙ 14 ∙ share

read it
Adversarial Learning and Explainability in Structured Datasets

We theoretically and empirically explore the explainability benefits of ...
10/15/2018 ∙ by Prasad Chalasani, et al. ∙ 0 ∙ share

read it
Explainable Black-Box Attacks Against Model-based Authentication

Establishing unique identities for both humans and end systems has been ...
09/28/2018 ∙ by Washington Garcia, et al. ∙ 0 ∙ share

read it
Adversarial Binaries for Authorship Identification

Binary code authorship identification determines authors of a binary pro...
09/21/2018 ∙ by Xiaozhu Meng, et al. ∙ 0 ∙ share

read it
Neural-Augmented Static Analysis of Android Communication

We address the problem of discovering communication links between applic...
09/11/2018 ∙ by Jinman Zhao, et al. ∙ 0 ∙ share

read it
Improving Adversarial Robustness by Data-Specific Discretization

A recent line of research proposed (either implicitly or explicitly) gra...
05/20/2018 ∙ by Jiefeng Chen, et al. ∙ 0 ∙ share

read it
Semantic Adversarial Deep Learning

Fueled by massive amounts of data, models produced by machine-learning (...
04/19/2018 ∙ by Tommaso Dreossi, et al. ∙ 0 ∙ share

read it
OEI: Operation Execution Integrity for Embedded Devices

We formulate a new security property, called "Operation Execution Integr...
02/09/2018 ∙ by Zhichuang Sun, et al. ∙ 0 ∙ share

read it
The Manifold Assumption and Defenses Against Adversarial Perturbations

In the adversarial-perturbation problem of neural networks, an adversary...
11/21/2017 ∙ by Xi Wu, et al. ∙ 0 ∙ share

read it
Manifold Assumption and Defenses Against Adversarial Perturbations

In the adversarial perturbation problem of neural networks, an adversary...
11/21/2017 ∙ by Xi Wu, et al. ∙ 0 ∙ share

read it
The Unintended Consequences of Overfitting: Training Data Inference Attacks

Machine learning algorithms that are applied to sensitive data pose a di...
09/05/2017 ∙ by Samuel Yeom, et al. ∙ 0 ∙ share

read it
Analyzing the Robustness of Nearest Neighbors to Adversarial Examples

Motivated by applications such as autonomous vehicles, test-time attacks...
06/13/2017 ∙ by Yizhen Wang, et al. ∙ 0 ∙ share

read it
ROSA: R Optimizations with Static Analysis

R is a popular language and programming environment for data scientists....
04/10/2017 ∙ by Rathijit Sen, et al. ∙ 0 ∙ share

read it
Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics

While significant progress has been made separately on analytics systems...
06/15/2016 ∙ by Xi Wu, et al. ∙ 0 ∙ share

read it
Practical Black-Box Attacks against Machine Learning

Machine learning (ML) models, e.g., deep neural networks (DNNs), are vul...
02/08/2016 ∙ by Nicolas Papernot, et al. ∙ 0 ∙ share

read it
The Limitations of Deep Learning in Adversarial Settings

Deep learning takes advantage of large datasets and computationally effi...
11/24/2015 ∙ by Nicolas Papernot, et al. ∙ 0 ∙ share

read it
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks

Deep learning algorithms have been shown to perform extremely well on ma...
11/14/2015 ∙ by Nicolas Papernot, et al. ∙ 0 ∙ share

read it

Somesh Jha

Featured Co-authors