Guanqin Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Guanqin Zhang has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Yulei Sui
University of New South Wales, Sydney, Australia
5 shared publications - Herath Mudiyanselage Nelanga Dilum Bandara
Data61, CSIRO, Sydney, NSW, Australia
3 shared publications - Shiping Chen
DATA61, CSIRO
3 shared publications - Feng Xu
UNSW Sydney
2 shared publications - Zhenya Zhang
Kyushu University
2 shared publications - Jianjun Zhao
Kyushu University, Fukuoka, Japan
1 shared publication
Latest Publications
- Open Access
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1320-1332
Tensor-Based Batch Fuzzing with Adaptive Perturbation Scaling for Deep Neural Networks
- 7 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1320-1332
Open AccessTensor-Based Batch Fuzzing with Adaptive Perturbation Scaling for Deep Neural Networks
- Open Access
- 18 May 2026
- Published by Springer Nature
- p. 67-88
Mining Verdict Boundaries for Neural Network Verification
Branch and Bound ( $$\texttt{BaB}$$ ) aims to achieve complete verification of neural networks by adaptively partitioning the problem and applying off-the-shelf verifiers to subproblems. Its problem-splitting history can be represented as a tree, where each subproblem corresponds to a child node. A key problem of $$\texttt{BaB}$$ lies in searching for the verdict boundaries across all the paths that divide the verified and unverified subproblems. We observe that the existing $$\texttt{BaB}$$ approach tackles this problem by solving each expensive subproblem sequentially along the tree path as its depth increases, requiring costly bounds propagation at every visited $$\texttt{BaB}$$ tree node (i.e., subproblem), which is inefficient. To address this issue, we propose effective search approaches that leverage the monotonicity of each path to efficiently and precisely locate the verdict boundary by simultaneously splitting multiple activation functions (e.g., ReLU), rather than processing them one at a time as in the classical approach. Our approach performs an effective exponential search along each path, allowing us to skip many boundary-unrelated subproblems when identifying the verdict boundary. The enhanced version further improves this process by estimating the boundary’s position using quantitative information obtained from subproblem solving. We perform experimental evaluation on commonly-used benchmarks to assess our proposed techniques, and compare them with recent $$\texttt{BaB}$$ -based approaches.- 18 May 2026
- Published by Springer Nature
- p. 67-88
Open AccessMining Verdict Boundaries for Neural Network Verification
Branch and Bound ( $$\texttt{BaB}$$ ) aims to achieve complete verification of neural networks by adaptively partitioning the problem and applying off-the-shelf verifiers to subproblems. Its problem-splitting history can be represented as a tree, where each subproblem corresponds to a child node. A key problem of $$\texttt{BaB}$$ lies in searching for the verdict boundaries across all the paths that divide the verified and unverified subproblems. We observe that the existing $$\texttt{BaB}$$ approach tackles this problem by solving each expensive subproblem sequentially along the tree path as its depth increases, requiring costly bounds propagation at every visited $$\texttt{BaB}$$ tree node (i.e., subproblem), which is inefficient. To address this issue, we propose effective search approaches that leverage the monotonicity of each path to efficiently and precisely locate the verdict boundary by simultaneously splitting multiple activation functions (e.g., ReLU), rather than processing them one at a time as in the classical approach. Our approach performs an effective exponential search along each path, allowing us to skip many boundary-unrelated subproblems when identifying the verdict boundary. The enhanced version further improves this process by estimating the boundary’s position using quantitative information obtained from subproblem solving. We perform experimental evaluation on commonly-used benchmarks to assess our proposed techniques, and compare them with recent $$\texttt{BaB}$$ -based approaches. - 7 July 2025
- Published by Springer Nature
- p. 307-326
Understanding the Robustness of Machine-Unlearning Models
- 7 July 2025
- Published by Springer Nature
- p. 307-326
Understanding the Robustness of Machine-Unlearning Models
- Open Access
- 9 April 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 9 (OOPSLA1) , 85-112
Efficient Incremental Verification of Neural Networks Guided by Counterexample Potentiality
Incremental verification is an emerging neural network verification approach that aims to accelerate the verification of a neural network N * by reusing the existing verification result (called a template ) of a similar neural network N . To date, the state-of-the-art incremental verification approach leverages the problem splitting history produced by branch and bound ( BaB in verification of N , to select only a part of the sub-problems for verification of N * , thus more efficient than verifying N * from scratch. While this approach identifies whether each sub-problem should be re-assessed, it neglects the information of how necessary each sub-problem should be re-assessed, in the sense that the sub-problems that are more likely to contain counterexamples should be prioritized, in order to terminate the verification process as soon as a counterexample is detected. To bridge this gap, we first define a counterexample potentiality order over different sub-problems based on the template, and then we propose Olive , an incremental verification approach that explores the sub-problems of verifying N * orderly guided by counterexample potentiality. Specifically, Olive has two variants, including Olive g , a greedy strategy that always prefers to exploit the sub-problems that are more likely to contain counterexamples, and Olive b , a balanced strategy that also explores the sub-problems that are less likely, in case the template is not sufficiently precise. We experimentally evaluate the efficiency of Olive on 1445 verification problem instances derived from 15 neural networks spanning over two datasets MNIST and CIFAR-10. Our evaluation demonstrates significant performance advantages of Olive over state-of-the-art classic verification and incremental approaches. In particular, Olive shows evident superiority on the problem instances that contain counterexamples, and performs as well as Ivan on the certified problem instances.
- 9 April 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Programming Languages
- Vol. 9 (OOPSLA1) , 85-112
Open AccessEfficient Incremental Verification of Neural Networks Guided by Counterexample Potentiality
Incremental verification is an emerging neural network verification approach that aims to accelerate the verification of a neural network N * by reusing the existing verification result (called a template ) of a similar neural network N . To date, the state-of-the-art incremental verification approach leverages the problem splitting history produced by branch and bound ( BaB in verification of N , to select only a part of the sub-problems for verification of N * , thus more efficient than verifying N * from scratch. While this approach identifies whether each sub-problem should be re-assessed, it neglects the information of how necessary each sub-problem should be re-assessed, in the sense that the sub-problems that are more likely to contain counterexamples should be prioritized, in order to terminate the verification process as soon as a counterexample is detected. To bridge this gap, we first define a counterexample potentiality order over different sub-problems based on the template, and then we propose Olive , an incremental verification approach that explores the sub-problems of verifying N * orderly guided by counterexample potentiality. Specifically, Olive has two variants, including Olive g , a greedy strategy that always prefers to exploit the sub-problems that are more likely to contain counterexamples, and Olive b , a balanced strategy that also explores the sub-problems that are less likely, in case the template is not sufficiently precise. We experimentally evaluate the efficiency of Olive on 1445 verification problem instances derived from 15 neural networks spanning over two datasets MNIST and CIFAR-10. Our evaluation demonstrates significant performance advantages of Olive over state-of-the-art classic verification and incremental approaches. In particular, Olive shows evident superiority on the problem instances that contain counterexamples, and performs as well as Ivan on the certified problem instances.
- 9 November 2023
- Published by Springer Nature
- p. 267-272
Eager to Stop: Efficient Falsification of Deep Neural Networks
- 9 November 2023
- Published by Springer Nature
- p. 267-272
Eager to Stop: Efficient Falsification of Deep Neural Networks
- 6 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet Computing
- Vol. 27 (6) , 13-20
A Tale of Two Cities: Data and Configuration Variances in Robust Deep Learning
Deep neural networks (DNNs) have widespread applications in industries such as image recognition, supply chain, medical diagnosis, and autonomous driving. However, prior work has shown the high accuracy of a DNN model does not imply high robustness (i.e., consistent performances on new and future datasets) because the input data and external environment (e.g., software and model configurations) for a deployed model are constantly changing. Therefore, ensuring robustness is crucial to enhance business and consumer confidence. Previous research mostly focuses on the data aspect of model variance. This article takes a holistic view of DNN robustness by summarizing issues related to both data and software configuration variances. We also present a predictive framework using search-based optimization to generate representative variances for robust learning, considering data and configurations.
- 6 October 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet Computing
- Vol. 27 (6) , 13-20
A Tale of Two Cities: Data and Configuration Variances in Robust Deep Learning
Deep neural networks (DNNs) have widespread applications in industries such as image recognition, supply chain, medical diagnosis, and autonomous driving. However, prior work has shown the high accuracy of a DNN model does not imply high robustness (i.e., consistent performances on new and future datasets) because the input data and external environment (e.g., software and model configurations) for a deployed model are constantly changing. Therefore, ensuring robustness is crucial to enhance business and consumer confidence. Previous research mostly focuses on the data aspect of model variance. This article takes a holistic view of DNN robustness by summarizing issues related to both data and software configuration variances. We also present a predictive framework using search-based optimization to generate representative variances for robust learning, considering data and configurations.