b'Somesh Jha'

research

∙ 08/28/2023

Identifying and Mitigating the Security Risks of Generative AI

Every major technical invention resurfaces the dual-use dilemma – the ne...

0 Clark Barrett, et al. ∙

research

∙ 07/30/2023

Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attacks

Adversarial examples threaten the integrity of machine learning systems ...

0 Ashish Hooda, et al. ∙

research

∙ 07/03/2023

Pareto-Secure Machine Learning (PSML): Fingerprinting and Securing Inference Serving Systems

With the emergence of large foundational models, model-serving systems a...

0 Debopam Sanyal, et al. ∙

research

∙ 05/25/2023

Rethink Diversity in Deep Learning Testing

Deep neural networks (DNNs) have demonstrated extraordinary capabilities...

0 Zi Wang, et al. ∙

research

∙ 04/07/2023

ASPEST: Bridging the Gap Between Active Learning and Selective Prediction

Selective prediction aims to learn a reliable model that abstains from m...

2 Jiefeng Chen, et al. ∙

research

∙ 03/11/2023

Investigating Stateful Defenses Against Black-Box Adversarial Examples

Defending machine-learning (ML) models against white-box adversarial att...

6 Ryan Feng, et al. ∙

research

∙ 02/27/2023

Formal Analysis of the API Proxy Problem

Implementing a security mechanism on top of APIs requires clear understa...

0 Somesh Jha, et al. ∙

research

∙ 01/26/2023

Learning Modulo Theories

Recent techniques that integrate solver layers into Deep Neural Networks...

8 Matt Fredrikson, et al. ∙

research

∙ 11/23/2022

Private Multi-Winner Voting for Machine Learning

Private multi-winner voting is the task of revealing k-hot binary vector...

1 Adam Dziedzic, et al. ∙

research

∙ 10/06/2022

Federated Boosted Decision Trees with Differential Privacy

There is great demand for scalable, secure, and efficient privacy-preser...

0 Samuel Maddock, et al. ∙

research

∙ 05/18/2022

Constraining the Attack Space of Machine Learning Models with Distribution Clamping Preprocessing

Preprocessing and outlier detection techniques have both been applied to...

6 Ryan Feng, et al. ∙

research

∙ 03/04/2022

Concept-based Explanations for Out-Of-Distribution Detectors

Out-of-distribution (OOD) detection plays a crucial role in ensuring the...

1 Jihye Choi, et al. ∙

research

∙ 03/02/2022

A Quantitative Geometric Approach to Neural Network Smoothness

Fast and precise Lipschitz constant estimation of neural networks is an ...

2 Zi Wang, et al. ∙

research

∙ 02/21/2022

Using Illustrations to Communicate Differential Privacy Trust Models: An Investigation of Users' Comprehension, Perception, and Data Sharing Decision

Proper communication is key to the adoption and implementation of differ...

0 Aiping Xiong, et al. ∙

research

∙ 02/11/2022

Towards Adversarially Robust Deepfake Detection: An Ensemble Approach

Detecting deepfakes is an important problem, but recent work has shown t...

1 Ashish Hooda, et al. ∙

research

∙ 02/09/2022

An Exploration of Multicalibration Uniform Convergence Bounds

Recent works have investigated the sample complexity necessary for fair ...

3 Harrison Rosenberg, et al. ∙

research

∙ 12/23/2021

EIFFeL: Ensuring Integrity for Federated Learning

Federated learning (FL) enables clients to collaborate with a server to ...

0 Amrita Roy Chowdhury, et al. ∙

research

∙ 09/06/2021

Lightweight, Multi-Stage, Compiler-Assisted Application Specialization

Program debloating aims to enhance the performance and reduce the attack...

0 Mohannad Alhanahnah, et al. ∙

research

∙ 08/16/2021

NeuraCrypt is not private

NeuraCrypt (Yara et al. arXiv 2021) is an algorithm that converts a sens...

0 Nicholas Carlini, et al. ∙

research

∙ 08/05/2021

Fairness Properties of Face Recognition and Obfuscation Systems

The proliferation of automated facial recognition in various commercial ...

4 Harrison Rosenberg, et al. ∙

research

∙ 08/02/2021

Domain Adaptation for Autoencoder-Based End-to-End Communication Over Wireless Channels

The problem of domain adaptation conventionally considers the setting wh...

10 Jayaram Raghuram, et al. ∙

research

∙ 06/11/2021

A Shuffling Framework for Local Differential Privacy

ldp deployments are vulnerable to inference attacks as an adversary can ...

2 Casey Meehan, et al. ∙

research

∙ 03/04/2021

Hard-label Manifolds: Unexpected Advantages of Query Efficiency for Finding On-manifold Adversarial Examples

Designing deep networks robust to adversarial examples remains an open p...

13 Washington Garcia, et al. ∙

research

∙ 02/14/2021

Exploring Adversarial Robustness of Deep Metric Learning

Deep Metric Learning (DML), a widely-used technique, involves learning a...

11 Thomas Kobber Panum, et al. ∙

research

∙ 02/09/2021

CaPC Learning: Confidential and Private Collaborative Learning

Machine learning benefits from large training datasets, which may not al...

2 Christopher A. Choquette-Choo, et al. ∙

research

∙ 12/19/2020

Sample Complexity of Adversarially Robust Linear Classification on Separated Data

We consider the sample complexity of learning with adversarial robustnes...

6 Robi Bhattacharjee, et al. ∙

research

∙ 11/11/2020

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

On-device machine learning (ML) is getting more and more popular as fast...

14 Zhichuang Sun, et al. ∙

research

∙ 09/11/2020

Intertwining Order Preserving Encryption and Differential Privacy

Ciphertexts of an order-preserving encryption (OPE) scheme preserve the ...

0 Amrita Roy Chowdhury, et al. ∙

research

∙ 07/29/2020

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

Detecting anomalous inputs, such as adversarial and out-of-distribution ...

16 Jayaram Raghuram, et al. ∙

research

∙ 07/12/2020

Abstract Universal Approximation for Neural Networks

With growing concerns about the safety and robustness of neural networks...

9 Zi Wang, et al. ∙

research

∙ 07/01/2020

Robust Learning against Logical Adversaries

Test-time adversarial attacks have posed serious challenges to the robus...

57 Yizhen Wang, et al. ∙

research

∙ 05/24/2020

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...

0 Tianhao Wang, et al. ∙

research

∙ 03/31/2020

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

Differential privacy protects an individual's privacy by perturbing data...

0 Aiping Xiong, et al. ∙

research

∙ 03/26/2020

Obliviousness Makes Poisoning Adversaries Weaker

Poisoning attacks have emerged as a significant security threat to machi...

5 Sanjam Garg, et al. ∙

research

∙ 03/19/2020

Face-Off: Adversarial Face Obfuscation

Advances in deep learning have made face recognition increasingly feasib...

0 Chuhan Gao, et al. ∙

research

∙ 03/03/2020

Analyzing Accuracy Loss in Randomized Smoothing Defenses

Recent advances in machine learning (ML) algorithms, especially deep neu...

15 Yue Gao, et al. ∙

research

∙ 02/18/2020

CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods

We study the problem of learning Granger causality between event types f...

10 Wei Zhang, et al. ∙

research

∙ 02/17/2020

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

We present Survival-OPT, a physical adversarial example algorithm in the...

5 Ryan Feng, et al. ∙

research

∙ 02/07/2020

Semantic Robustness of Models of Source Code

Deep neural networks are vulnerable to adversarial examples - small inpu...

1 Goutham Ramakrishnan, et al. ∙

research

∙ 10/02/2019

Generating Semantic Adversarial Examples with Differentiable Rendering

Machine learning (ML) algorithms, especially deep neural networks, have ...

23 Lakshya Jain, et al. ∙

research

∙ 09/07/2019

On Need for Topology Awareness of Generative Models

Manifold assumption in learning states that: the data lie approximately ...

20 Uyeong Jang, et al. ∙

research

∙ 09/07/2019

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

ML algorithms or models, especially deep neural networks (DNNs), have sh...

0 Uyeong Jang, et al. ∙

research

∙ 08/30/2019

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

When collecting information, local differential privacy (LDP) alleviates...

0 Tianhao Wang, et al. ∙

research

∙ 08/30/2019

Practical and Robust Privacy Amplification with Multi-Party Differential Privacy

When collecting information, local differential privacy (LDP) alleviates...

0 Tianhao Wang, et al. ∙

research

∙ 05/30/2019

Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models

Directed graphical models (DGMs) are a class of probabilistic models tha...

1 Amrita Roy Chowdhury, et al. ∙

research

∙ 05/28/2019

Adversarially Robust Learning Could Leverage Computational Hardness

Over recent years, devising classification algorithms that are robust to...

4 Sanjam Garg, et al. ∙

research

∙ 05/26/2019

Enhancing ML Robustness Using Physical-World Constraints

Recent advances in Machine Learning (ML) have demonstrated that neural n...

0 Varun Chandrasekaran, et al. ∙

research

∙ 05/23/2019

Robust Attribution Regularization

An emerging problem in trustworthy machine learning is to train models t...

4 Jiefeng Chen, et al. ∙

research

∙ 03/14/2019

Attribution-driven Causal Analysis for Detection of Adversarial Examples

Attribution methods have been developed to explain the decision of a mac...

6 Susmit Jha, et al. ∙

research

∙ 02/20/2019

Outis: Crypto-Assisted Differential Privacy on Untrusted Servers

Differential privacy has steadily become the de-facto standard for achie...

0 Amrita Roy Chowdhury, et al. ∙

Somesh Jha

Featured Co-authors