• Publications
  • Influence
Analyzing Federated Learning through an Adversarial Lens
TLDR
We explore the threat of model poisoning attacks on federated learning initiated by a single, non-colluding malicious agent where the adversarial objective is to cause the model to misclassify a set of chosen inputs with high confidence. Expand
  • 151
  • 23
  • PDF
Dependence Makes You Vulnberable: Differential Privacy Under Dependent Tuples
TLDR
We introduce the notion of dependent differential privacy (DDP) that accounts for the dependence that exists between tuples and propose a dependent perturbation mechanism (DPM) to achieve the privacy guarantees in DDP. Expand
  • 107
  • 16
  • PDF
Neighborhood based fast graph search in large networks
TLDR
We propose a neighborhood-based similarity measure that could avoid costly graph isomorphism and edit distance computation and find high-quality matches in large social and information networks. Expand
  • 134
  • 13
  • PDF
GenAttack: practical black-box attacks with gradient-free optimization
TLDR
We introduce GenAttack, a gradient-free optimization technique that uses genetic algorithms for synthesizing adversarial examples in the black-box setting. Expand
  • 74
  • 13
  • PDF
Compressive Oversampling for Robust Data Transmission in Sensor Networks
TLDR
We show that CS erasure encoding with random sampling is efficient for handling missing data in erasure channels, paralleling the performance of BCH codes, with the added benefit of graceful degradation of the reconstruction error even when the amount of missing data far exceeds the designed redundancy. Expand
  • 68
  • 10
  • PDF
ipShield: A Framework For Enforcing Context-Aware Privacy
TLDR
We present ipShield, a framework that provides users with greater control over their resources at runtime. Expand
  • 68
  • 7
  • PDF
Interpretability of deep learning models: A survey of results
TLDR
Deep neural networks have achieved near-human accuracy levels in various types of classification and prediction tasks including images, text, speech, and video. Expand
  • 114
  • 3
  • PDF
A framework for context-aware privacy of sensor data on mobile systems
TLDR
We study the competing goals of utility and privacy as they arise when a user shares personal sensor data with apps on a smartphone. Expand
  • 56
  • 2
  • PDF
SenseGen: A deep learning architecture for synthetic sensor data generation
TLDR
In this paper, we take a step towards generating sensory data that can pass a deep learning based discriminator model test designed to distinguish between the synthesized and true data. Expand
  • 52
  • 2
  • PDF
SensorSafe: A Framework for Privacy-Preserving Management of Personal Sensory Information
TLDR
The widespread use of smartphones and body-worn sensors has made continuous and unobtrusive collection of personal data feasible. Expand
  • 39
  • 2
  • PDF