Search Results for author: Guanhong Tao

Found 12 papers, 6 papers with code

DECK: Model Hardening for Defending Pervasive Backdoors

no code implementations18 Jun 2022 Guanhong Tao, Yingqi Liu, Siyuan Cheng, Shengwei An, Zhuo Zhang, QiuLing Xu, Guangyu Shen, Xiangyu Zhang

As such, using the samples derived from our attack in adversarial training can harden a model against these backdoor vulnerabilities.

An Extractive-and-Abstractive Framework for Source Code Summarization

no code implementations15 Jun 2022 Weisong Sun, Chunrong Fang, Yuchen Chen, Quanjun Zhang, Guanhong Tao, Tingxu Han, Yifei Ge, Yudu You, Bin Luo

The extractive module in the framework performs a task of extractive code summarization, which takes in the code snippet and predicts important statements containing key factual details.

Code Summarization Machine Translation +1

Code Search based on Context-aware Code Translation

1 code implementation16 Feb 2022 Weisong Sun, Chunrong Fang, Yuchen Chen, Guanhong Tao, Tingxu Han, Quanjun Zhang

We evaluate the effectiveness of our technique, called TranCS, on the CodeSearchNet corpus with 1, 000 queries.

Code Search Code Translation +1

Complex Backdoor Detection by Symmetric Feature Differencing

1 code implementation CVPR 2022 Yingqi Liu, Guangyu Shen, Guanhong Tao, Zhenting Wang, Shiqing Ma, Xiangyu Zhang

Our results on the TrojAI competition rounds 2-4, which have patch backdoors and filter backdoors, show that existing scanners may produce hundreds of false positives (i. e., clean models recognized as trojaned), while our technique removes 78-100% of them with a small increase of false negatives by 0-30%, leading to 17-41% overall accuracy improvement.

Bounded Adversarial Attack on Deep Content Features

1 code implementation CVPR 2022 QiuLing Xu, Guanhong Tao, Xiangyu Zhang

We propose a novel adversarial attack targeting content features in some deep layer, that is, individual neurons in the layer.

Adversarial Attack

Backdoor Scanning for Deep Neural Networks through K-Arm Optimization

1 code implementation9 Feb 2021 Guangyu Shen, Yingqi Liu, Guanhong Tao, Shengwei An, QiuLing Xu, Siyuan Cheng, Shiqing Ma, Xiangyu Zhang

By iteratively and stochastically selecting the most promising labels for optimization with the guidance of an objective function, we substantially reduce the complexity, allowing to handle models with many classes.

D-square-B: Deep Distribution Bound for Natural-looking Adversarial Attack

no code implementations12 Jun 2020 Qiu-Ling Xu, Guanhong Tao, Xiangyu Zhang

We propose a novel technique that can generate natural-looking adversarial examples by bounding the variations induced for internal activation values in some deep layer(s), through a distribution quantile bound and a polynomial barrier loss function.

Adversarial Attack

Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples

1 code implementation NeurIPS 2018 Guanhong Tao, Shiqing Ma, Yingqi Liu, Xiangyu Zhang

Results show that our technique can achieve 94% detection accuracy for 7 different kinds of attacks with 9. 91% false positives on benign inputs.

Face Recognition General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.