activity
20172022
most citedPeer-to-peer Federated Learning on Graphs

139 citations · 448 across the 27 of their papers we have counts for

collaborators

43 papers

cs.CV20227 cited

FastStamp: Accelerating Neural Steganography and Digital Watermarking of Images on FPGAs

Shehzeen Hussain, Nojan Sheybani, Paarth Neekhara +3

Steganography and digital watermarking are the tasks of hiding recoverable data in image pixels. Deep neural network (DNN) based image steganography and watermarking techniques are…

cs.CL202213 cited

Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers

Ruisi Zhang, Seira Hidano, Farinaz Koushanfar

Text classification has become widely used in various natural language processing applications like sentiment analysis. Current applications often use large transformer-based langu…

cs.AI2022

AdaTest:Reinforcement Learning and Adaptive Sampling for On-chip Hardware Trojan Detection

Huili Chen, Xinqiao Zhang, Ke Huang +1

This paper proposes AdaTest, a novel adaptive test pattern generation framework for efficient and reliable Hardware Trojan (HT) detection. HT is a backdoor attack that tampers with…

cs.CR20221 cited

An Adaptive Black-box Backdoor Detection Method for Deep Neural Networks

Xinqiao Zhang, Huili Chen, Ke Huang +1

With the surge of Machine Learning (ML), An emerging amount of intelligent applications have been developed. Deep Neural Networks (DNNs) have demonstrated unprecedented performance…

cs.CV20228 cited

FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering Deepfakes

Paarth Neekhara, Shehzeen Hussain, Xinqiao Zhang +3

Deepfakes and manipulated media are becoming a prominent threat due to the recent advances in realistic image and video synthesis techniques. There have been several attempts at co…

cs.CR20226 cited

Backdoor Defense in Federated Learning Using Differential Testing and Outlier Detection

Yein Kim, Huili Chen, Farinaz Koushanfar

The goal of federated learning (FL) is to train one global model by aggregating model parameters updated independently on edge devices without accessing users' private data. Howeve…