95 citations · 855 across the 81 of their papers we have counts for
9 papers · 1 filter
Analyzing and Improving Neural Networks by Generating Semantic Counterexamples through Differentiable Rendering
Lakshya Jain, Varun Chandrasekaran, Uyeong Jang +6
Even as deep neural networks (DNNs) have achieved remarkable success on vision-related tasks, their performance is brittle to transformations in the input. Of particular interest a…
On the Need for Topology-Aware Generative Models for Manifold-Based Defenses
Uyeong Jang, Susmit Jha, Somesh Jha
Machine-learning (ML) algorithms or models, especially deep neural networks (DNNs), have shown significant promise in several areas. However, researchers have recently demonstrated…
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…
Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models
Amrita Roy Chowdhury, Theodoros Rekatsinas, Somesh Jha
Directed graphical models (DGMs) are a class of probabilistic models that are widely used for predictive analysis in sensitive domains, such as medical diagnostics. In this paper w…
Adversarially Robust Learning Could Leverage Computational Hardness
Sanjam Garg, Somesh Jha, Saeed Mahloujifar +1
Over recent years, devising classification algorithms that are robust to adversarial perturbations has emerged as a challenging problem. In particular, deep neural nets (DNNs) seem…
Rearchitecting Classification Frameworks For Increased Robustness
Varun Chandrasekaran, Brian Tang, Nicolas Papernot +3
While generalizing well over natural inputs, neural networks are vulnerable to adversarial inputs. Existing defenses against adversarial inputs have largely been detached from the…
Robust Attribution Regularization
Jiefeng Chen, Xi Wu, Vaibhav Rastogi +2
An emerging problem in trustworthy machine learning is to train models that produce robust interpretations for their predictions. We take a step towards solving this problem throug…
Attribution-driven Causal Analysis for Detection of Adversarial Examples
Susmit Jha, Sunny Raj, Steven Lawrence Fernandes +5
Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to defi…
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.…