Search Results for author: Xiaowei Huang

Found 58 papers, 30 papers with code

Regression of Instance Boundary by Aggregated CNN and GCN

no code implementations ECCV 2020 Yanda Meng, Wei Meng, Dongxu Gao, Yitian Zhao, Xiaoyun Yang, Xiaowei Huang, Yalin Zheng

In particular, thanks to the proposed aggregation GCN, our network benefits from direct feature learning of the instances’ boundary locations and the spatial information propagation across the image.

Image Segmentation regression +1

A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation

no code implementations19 May 2023 Xiaowei Huang, Wenjie Ruan, Wei Huang, Gaojie Jin, Yi Dong, Changshun Wu, Saddek Bensalem, Ronghui Mu, Yi Qi, Xingyu Zhao, Kaiwen Cai, Yanghao Zhang, Sihao Wu, Peipei Xu, Dengyu Wu, Andre Freitas, Mustafa A. Mustafa

Considering the fast development of LLMs, this survey does not intend to be complete (although it includes 300 references), especially when it comes to the applications of LLMs in various domains, but rather a collection of organised literature reviews and discussions to support the quick understanding of the safety and trustworthiness issues from the perspective of V&V.

Model-Agnostic Reachability Analysis on Deep Neural Networks

no code implementations3 Apr 2023 Chi Zhang, Wenjie Ruan, Fu Wang, Peipei Xu, Geyong Min, Xiaowei Huang

Verification plays an essential role in the formal analysis of safety-critical systems.

Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPT

1 code implementation3 Apr 2023 Yi Qi, Xingyu Zhao, Xiaowei Huang

While LLMs are being quickly applied to many AI application domains, we are interested in the following question: Can safety analysis for safety-critical systems make use of LLMs?

Randomized Adversarial Training via Taylor Expansion

1 code implementation CVPR 2023 Gaojie Jin, Xinping Yi, Dengyu Wu, Ronghui Mu, Xiaowei Huang

The randomized weights enable our design of a novel adversarial training method via Taylor expansion of a small Gaussian noise, and we show that the new adversarial training method can flatten loss landscape and find flat minima.

Decentralised and Cooperative Control of Multi-Robot Systems through Distributed Optimisation

no code implementations3 Feb 2023 Yi Dong, Zhongguo Li, Xingyu Zhao, Zhengtao Ding, Xiaowei Huang

Then, based on the distributed optimisation algorithm, an output regulation method is utilised to solve the optimal coordination problem for general linear dynamic systems.

Towards Verifying the Geometric Robustness of Large-scale Neural Networks

1 code implementation29 Jan 2023 Fu Wang, Peipei Xu, Wenjie Ruan, Xiaowei Huang

Deep neural networks (DNNs) are known to be vulnerable to adversarial geometric transformation.

Optimising Event-Driven Spiking Neural Network with Regularisation and Cutoff

1 code implementation23 Jan 2023 Dengyu Wu, Gaojie Jin, Han Yu, Xinping Yi, Xiaowei Huang

Two novel optimisation techniques are presented to achieve AOI-SNNs: a regularisation and a cutoff.

Towards Relation-centered Pooling and Convolution for Heterogeneous Graph Learning Networks

1 code implementation31 Oct 2022 Tiehua Zhang, Yuze Liu, Yao Yao, Youhua Xia, Xin Chen, Xiaowei Huang, Jiong Jin

Heterogeneous graph neural network has unleashed great potential on graph representation learning and shown superior performance on downstream tasks such as node classification and clustering.

Graph Learning Graph Representation Learning +1

Reachability Verification Based Reliability Assessment for Deep Reinforcement Learning Controlled Robotics and Autonomous Systems

no code implementations26 Oct 2022 Yi Dong, Xingyu Zhao, Sen Wang, Xiaowei Huang

Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RASs).

Uncertainty Estimation for 3D Dense Prediction via Cross-Point Embeddings

1 code implementation29 Sep 2022 Kaiwen Cai, Chris Xiaoxuan Lu, Xiaowei Huang

In this work, we present CUE, a novel uncertainty estimation method for dense prediction tasks in 3D point clouds.

Metric Learning Semantic Segmentation

SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability

1 code implementation19 Aug 2022 Wei Huang, Xingyu Zhao, Gaojie Jin, Xiaowei Huang

Interpretability of Deep Learning (DL) models is arguably the barrier in front of trustworthy AI.

Short-term Load Forecasting with Distributed Long Short-Term Memory

no code implementations1 Aug 2022 Yi Dong, Yang Chen, Xingyu Zhao, Xiaowei Huang

With the employment of smart meters, massive data on consumer behaviour can be collected by retailers.

Load Forecasting

FedRel: An Adaptive Federated Relevance Framework for Spatial Temporal Graph Learning

no code implementations7 Jun 2022 Tiehua Zhang, Yuze Liu, Zhishu Shen, Rui Xu, Xin Chen, Xiaowei Huang, Xi Zheng

Spatial-temporal data contains rich information and has been widely studied in recent years due to the rapid development of relevant applications in many fields.

Federated Learning Graph Learning

Hierarchical Distribution-Aware Testing of Deep Learning

1 code implementation17 May 2022 Wei Huang, Xingyu Zhao, Alec Banks, Victoria Cox, Xiaowei Huang

In this paper, we propose a new robustness testing approach for detecting AEs that considers both the input distribution and the perceptual quality of inputs.

Data Compression

Enhancing Adversarial Training with Second-Order Statistics of Weights

1 code implementation CVPR 2022 Gaojie Jin, Xinping Yi, Wei Huang, Sven Schewe, Xiaowei Huang

In this paper, we show that treating model weights as random variables allows for enhancing adversarial training through \textbf{S}econd-Order \textbf{S}tatistics \textbf{O}ptimization (S$^2$O) with respect to the weights.

3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs

no code implementations9 Mar 2022 Yanda Meng, Xu Chen, Dongxu Gao, Yitian Zhao, Xiaoyun Yang, Yihong Qiao, Xiaowei Huang, Yalin Zheng

In this paper, we propose a novel multi-level aggregation network to regress the coordinates of the vertices of a 3D face from a single 2D image in an end-to-end manner.

3D Face Alignment 3D Face Reconstruction +1

Counting with Adaptive Auxiliary Learning

1 code implementation8 Mar 2022 Yanda Meng, Joshua Bridge, Meng Wei, Yitian Zhao, Yihong Qiao, Xiaoyun Yang, Xiaowei Huang, Yalin Zheng

This paper proposes an adaptive auxiliary task learning based approach for object counting problems.

Auxiliary Learning Object Counting

STUN: Self-Teaching Uncertainty Estimation for Place Recognition

1 code implementation3 Mar 2022 Kaiwen Cai, Chris Xiaoxuan Lu, Xiaowei Huang

Then, supervised by the pretrained teacher net, a student net with an additional variance branch is trained to finetune the embedding priors and estimate the uncertainty sample by sample.

Metric Learning Simultaneous Localization and Mapping

Weight Expansion: A New Perspective on Dropout and Generalization

no code implementations23 Jan 2022 Gaojie Jin, Xinping Yi, Pengfei Yang, Lijun Zhang, Sven Schewe, Xiaowei Huang

While dropout is known to be a successful regularization technique, insights into the mechanisms that lead to this success are still lacking.

Neuronal Correlation: a Central Concept in Neural Network

no code implementations22 Jan 2022 Gaojie Jin, Xinping Yi, Xiaowei Huang

This paper proposes to study neural networks through neuronal correlation, a statistical measure of correlated neuronal activity on the penultimate layer.

GPS: A Policy-driven Sampling Approach for Graph Representation Learning

no code implementations29 Dec 2021 Tiehua Zhang, Yuze Liu, Xin Chen, Xiaowei Huang, Feng Zhu, Xi Zheng

Graph representation learning has drawn increasing attention in recent years, especially for learning the low dimensional embedding at both node and graph level for classification and recommendations tasks.

Graph Classification Graph Representation Learning

Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance

no code implementations30 Nov 2021 Yi Dong, Wei Huang, Vibhav Bharti, Victoria Cox, Alec Banks, Sen Wang, Xingyu Zhao, Sven Schewe, Xiaowei Huang

The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) -- has resulted in the pressing need to assure their functional safety.

BI-GCN: Boundary-Aware Input-Dependent Graph Convolution Network for Biomedical Image Segmentation

1 code implementation27 Oct 2021 Yanda Meng, Hongrun Zhang, Dongxu Gao, Yitian Zhao, Xiaoyun Yang, Xuesheng Qian, Xiaowei Huang, Yalin Zheng

Our model is well-suited to obtain global semantic region information while also accommodates local spatial boundary characteristics simultaneously.

Image Segmentation Semantic Segmentation

Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking

1 code implementation14 Sep 2021 Yi Dong, Xingyu Zhao, Xiaowei Huang

While Deep Reinforcement Learning (DRL) provides transformational capabilities to the control of Robotics and Autonomous Systems (RAS), the black-box nature of DRL and uncertain deployment environments of RAS pose new challenges on its dependability.

Reinforcement Learning (RL)

Adversarial Robustness of Deep Learning: Theory, Algorithms, and Applications

no code implementations24 Aug 2021 Wenjie Ruan, Xinping Yi, Xiaowei Huang

This tutorial aims to introduce the fundamentals of adversarial robustness of deep learning, presenting a well-structured review of up-to-date techniques to assess the vulnerability of various types of deep learning models to adversarial examples.

Adversarial Robustness Learning Theory

Spatial Uncertainty-Aware Semi-Supervised Crowd Counting

1 code implementation ICCV 2021 Yanda Meng, Hongrun Zhang, Yitian Zhao, Xiaoyun Yang, Xuesheng Qian, Xiaowei Huang, Yalin Zheng

Semi-supervised approaches for crowd counting attract attention, as the fully supervised paradigm is expensive and laborious due to its request for a large number of images of dense crowd scenarios and their annotations.

Crowd Counting

Learning Robust Variational Information Bottleneck with Reference

no code implementations29 Apr 2021 Weizhu Qian, Bowei Chen, Xiaowei Huang

We propose a new approach to train a variational information bottleneck (VIB) that improves its robustness to adversarial perturbations.

Detecting Operational Adversarial Examples for Reliable Deep Learning

no code implementations13 Apr 2021 Xingyu Zhao, Wei Huang, Sven Schewe, Yi Dong, Xiaowei Huang

The utilisation of Deep Learning (DL) raises new challenges regarding its dependability in critical applications.

Abstraction and Symbolic Execution of Deep Neural Networks with Bayesian Approximation of Hidden Features

1 code implementation5 Mar 2021 Nicolas Berthier, Amany Alshareef, James Sharp, Sven Schewe, Xiaowei Huang

Intensive research has been conducted on the verification and validation of deep neural networks (DNNs), aiming to understand if, and how, DNNs can be applied to safety critical applications.

Dimensionality Reduction

A Little Energy Goes a Long Way: Build an Energy-Efficient, Accurate Spiking Neural Network from Convolutional Neural Network

1 code implementation1 Mar 2021 Dengyu Wu, Xinping Yi, Xiaowei Huang

In this paper, we argue that this trend of "energy for accuracy" is not necessary -- a little energy can go a long way to achieve the near-zero accuracy loss.

BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations

2 code implementations5 Dec 2020 Xingyu Zhao, Wei Huang, Xiaowei Huang, Valentin Robu, David Flynn

Given the pressing need for assuring algorithmic transparency, Explainable AI (XAI) has emerged as one of the key areas of AI research.

How does Weight Correlation Affect Generalisation Ability of Deep Neural Networks?

no code implementations NeurIPS 2020 Gaojie Jin, Xinping Yi, Liang Zhang, Lijun Zhang, Sven Schewe, Xiaowei Huang

This paper studies the novel concept of weight correlation in deep neural networks and discusses its impact on the networks' generalisation ability.

Embedding and Extraction of Knowledge in Tree Ensemble Classifiers

2 code implementations16 Oct 2020 Wei Huang, Xingyu Zhao, Xiaowei Huang

Whilst, as the increasing use of machine learning models in security-critical applications, the embedding and extraction of malicious knowledge are equivalent to the notorious backdoor attack and its defence, respectively.

Backdoor Attack BIG-bench Machine Learning

Generalizing Universal Adversarial Attacks Beyond Additive Perturbations

2 code implementations15 Oct 2020 Yanghao Zhang, Wenjie Ruan, Fu Wang, Xiaowei Huang

Extensive experiments are conducted on CIFAR-10 and ImageNet datasets with six deep neural network models including GoogleLeNet, VGG16/19, ResNet101/152, and DenseNet121.

Adversarial Attack

How does Weight Correlation Affect the Generalisation Ability of Deep Neural Networks

1 code implementation12 Oct 2020 Gaojie Jin, Xinping Yi, Liang Zhang, Lijun Zhang, Sven Schewe, Xiaowei Huang

This paper studies the novel concept of weight correlation in deep neural networks and discusses its impact on the networks' generalisation ability.

Towards the Quantification of Safety Risks in Deep Neural Networks

1 code implementation13 Sep 2020 Peipei Xu, Wenjie Ruan, Xiaowei Huang

In this paper, we define safety risks by requesting the alignment of the network's decision with human perception.

CasGCN: Predicting future cascade growth based on information diffusion graph

no code implementations10 Sep 2020 Zhixuan Xu, Minghui Qian, Xiaowei Huang, Jie Meng

In this paper, we propose a novel deep learning architecture for cascade growth prediction, called CasGCN, which employs the graph convolutional network to extract structural features from a graphical input, followed by the application of the attention mechanism on both the extracted features and the temporal information before conducting cascade size prediction.

Adaptable and Verifiable BDI Reasoning

no code implementations23 Jul 2020 Peter Stringer, Rafael C. Cardoso, Xiaowei Huang, Louise A. Dennis

Long-term autonomy requires autonomous systems to adapt as their capabilities no longer perform as expected.

Generating Adversarial Inputs Using A Black-box Differential Technique

no code implementations10 Jul 2020 João Batista Pereira Matos Juúnior, Lucas Carvalho Cordeiro, Marcelo d'Amorim, Xiaowei Huang

Algorithmically, DAEGEN uses a local search-based optimization algorithm to find DIAEs by iteratively perturbing an input to maximize the difference of two models on predicting the input.

Adversarial Attack

A Safety Framework for Critical Systems Utilising Deep Neural Networks

no code implementations7 Mar 2020 Xingyu Zhao, Alec Banks, James Sharp, Valentin Robu, David Flynn, Michael Fisher, Xiaowei Huang

Increasingly sophisticated mathematical modelling processes from Machine Learning are being used to analyse complex data.

Reliability Validation of Learning Enabled Vehicle Tracking

no code implementations6 Feb 2020 Youcheng Sun, Yifan Zhou, Simon Maskell, James Sharp, Xiaowei Huang

However, it is unclear if and how the adversarial examples over learning components can affect the overall system-level reliability.

Coverage Guided Testing for Recurrent Neural Networks

1 code implementation5 Nov 2019 Wei Huang, Youcheng Sun, Xingyu Zhao, James Sharp, Wenjie Ruan, Jie Meng, Xiaowei Huang

The test metrics and test case generation algorithm are implemented into a tool TestRNN, which is then evaluated on a set of LSTM benchmarks.

Defect Detection Drug Discovery +3

Explaining Image Classifiers using Statistical Fault Localization

1 code implementation6 Aug 2019 Youcheng Sun, Hana Chockler, Xiaowei Huang, Daniel Kroening

The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for "Explainable AI".

Fault localization

HITSZ-ICRC: A Report for SMM4H Shared Task 2019-Automatic Classification and Extraction of Adverse Effect Mentions in Tweets

no code implementations WS 2019 Shuai Chen, Yuanhang Huang, Xiaowei Huang, Haoming Qin, Jun Yan, Buzhou Tang

This is the system description of the Harbin Institute of Technology Shenzhen (HITSZ) team for the first and second subtasks of the fourth Social Media Mining for Health Applications (SMM4H) shared task in 2019.

testRNN: Coverage-guided Testing on Recurrent Neural Networks

1 code implementation20 Jun 2019 Wei Huang, Youcheng Sun, Xiaowei Huang, James Sharp

Recurrent neural networks (RNNs) have been widely applied to various sequential tasks such as text processing, video recognition, and molecular property prediction.

Molecular Property Prediction Video Recognition

Analyzing Deep Neural Networks with Symbolic Propagation: Towards Higher Precision and Faster Verification

no code implementations26 Feb 2019 Jianlin Li, Pengfei Yang, Jiangchao Liu, Liqian Chen, Xiaowei Huang, Lijun Zhang

Several verification approaches have been developed to automatically prove or disprove safety properties of DNNs.

A Game-Based Approximate Verification of Deep Neural Networks with Provable Guarantees

1 code implementation10 Jul 2018 Min Wu, Matthew Wicker, Wenjie Ruan, Xiaowei Huang, Marta Kwiatkowska

In this paper, we study two variants of pointwise robustness, the maximum safe radius problem, which for a given input sample computes the minimum distance to an adversarial example, and the feature robustness problem, which aims to quantify the robustness of individual features to adversarial perturbations.

Adversarial Attack Adversarial Defense +2

Concolic Testing for Deep Neural Networks

2 code implementations30 Apr 2018 Youcheng Sun, Min Wu, Wenjie Ruan, Xiaowei Huang, Marta Kwiatkowska, Daniel Kroening

Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program.

Global Robustness Evaluation of Deep Neural Networks with Provable Guarantees for the $L_0$ Norm

2 code implementations16 Apr 2018 Wenjie Ruan, Min Wu, Youcheng Sun, Xiaowei Huang, Daniel Kroening, Marta Kwiatkowska

In this paper we focus on the $L_0$ norm and aim to compute, for a trained DNN and an input, the maximal radius of a safe norm ball around the input within which there are no adversarial examples.

Testing Deep Neural Networks

no code implementations10 Mar 2018 Youcheng Sun, Xiaowei Huang, Daniel Kroening, James Sharp, Matthew Hill, Rob Ashmore

In this paper, inspired by the MC/DC coverage criterion, we propose a family of four novel test criteria that are tailored to structural features of DNNs and their semantics.

Feature-Guided Black-Box Safety Testing of Deep Neural Networks

no code implementations21 Oct 2017 Matthew Wicker, Xiaowei Huang, Marta Kwiatkowska

In this paper, we focus on image classifiers and propose a feature-guided black-box approach to test the safety of deep neural networks that requires no such knowledge.

object-detection Object Detection +2

Safety Verification of Deep Neural Networks

2 code implementations21 Oct 2016 Xiaowei Huang, Marta Kwiatkowska, Sen Wang, Min Wu

Our method works directly with the network code and, in contrast to existing methods, can guarantee that adversarial examples, if they exist, are found for the given region and family of manipulations.

Adversarial Attack Adversarial Defense +3

Normative Multiagent Systems: A Dynamic Generalization

no code implementations18 Apr 2016 Xiaowei Huang, Ji Ruan, Qingliang Chen, Kaile Su

Social norms are powerful formalism in coordinating autonomous agents' behaviour to achieve certain objectives.

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