activity
20202022
most citedTargeted Attack against Deep Neural Networks via Flipping Limited Weight Bits

29 citations · 99 across the 15 of their papers we have counts for

collaborators

17 papers

cs.CV202222 cited

Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation

Zeyu Qin, Yanbo Fan, Yi Liu +4

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work…

cs.CV2022

VDTR: Video Deblurring with Transformer

Mingdeng Cao, Yanbo Fan, Yong Zhang +2

Video deblurring is still an unsolved problem due to the challenging spatio-temporal modeling process. While existing convolutional neural network-based methods show a limited capa…

cs.CV20224 cited

StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN

Fei Yin, Yong Zhang, Xiaodong Cun +7

One-shot talking face generation aims at synthesizing a high-quality talking face video from an arbitrary portrait image, driven by a video or an audio segment. One challenging qua…

cs.CV20228 cited

LAS-AT: Adversarial Training with Learnable Attack Strategy

Xiaojun Jia, Yong Zhang, Baoyuan Wu +3

Adversarial training (AT) is always formulated as a minimax problem, of which the performance depends on the inner optimization that involves the generation of adversarial examples…

cs.CL2022

E-LANG: Energy-Based Joint Inferencing of Super and Swift Language Models

Mohammad Akbari, Amin Banitalebi-Dehkordi, Yong Zhang

Building huge and highly capable language models has been a trend in the past years. Despite their great performance, they incur high computational cost. A common solution is to ap…

cs.LG2021

Model Composition: Can Multiple Neural Networks Be Combined into a Single Network Using Only Unlabeled Data?

Amin Banitalebi-Dehkordi, Xinyu Kang, Yong Zhang

The diversity of deep learning applications, datasets, and neural network architectures necessitates a careful selection of the architecture and data that match best to a target ap…