activity
20182022
most citedPOBA-GA: Perturbation Optimized Black-Box Adversarial Attacks via Genetic Algorithm

78 citations · 141 across the 13 of their papers we have counts for

collaborators

26 papers

cs.SE2022

ActGraph: Prioritization of Test Cases Based on Deep Neural Network Activation Graph

Jinyin Chen, Jie Ge, Haibin Zheng

Widespread applications of deep neural networks (DNNs) benefit from DNN testing to guarantee their quality. In the DNN testing, numerous test cases are fed into the model to explor…

cs.CL2022

Improving robustness of language models from a geometry-aware perspective

Bin Zhu, Zhaoquan Gu, Le Wang +2

Recent studies have found that removing the norm-bounded projection and increasing search steps in adversarial training can significantly improve robustness. However, we observe th…

cs.CR20222 cited

GAIL-PT: A Generic Intelligent Penetration Testing Framework with Generative Adversarial Imitation Learning

Jinyin Chen, Shulong Hu, Haibin Zheng +2

Penetration testing (PT) is an efficient network testing and vulnerability mining tool by simulating a hacker's attack for valuable information applied in some areas. Compared with…

cs.AI20211 cited

Dyn-Backdoor: Backdoor Attack on Dynamic Link Prediction

Jinyin Chen, Haiyang Xiong, Haibin Zheng +3

Dynamic link prediction (DLP) makes graph prediction based on historical information. Since most DLP methods are highly dependent on the training data to achieve satisfying predict…

cs.LG20212 cited

Blockchain Phishing Scam Detection via Multi-channel Graph Classification

Dunjie Zhang, Jinyin Chen

With the popularity of blockchain technology, the financial security issues of blockchain transaction networks have become increasingly serious. Phishing scam detection methods wil…

cs.CV2021

Salient Feature Extractor for Adversarial Defense on Deep Neural Networks

Jinyin Chen, Ruoxi Chen, Haibin Zheng +3

Recent years have witnessed unprecedented success achieved by deep learning models in the field of computer vision. However, their vulnerability towards carefully crafted adversari…