OS and Networks Commons^™

Certified Continual Learning For Neural Network Regression, Hong Long Pham, Jun Sun

Research Collection School Of Computing and Information Systems

On the one hand, there has been considerable progress on neural network verification in recent years, which makes certifying neural networks a possibility. On the other hand, neural network in practice are often re-trained over time to cope with new data distribution or for solving different tasks (a.k.a. continual learning). Once re-trained, the verified correctness of the neural network is likely broken, particularly in the presence of the phenomenon known as catastrophic forgetting. In this work, we propose an approach called certified continual learning which improves existing continual learning methods by preserving, as long as possible, the established correctness properties …

Neural Network Semantic Backdoor Detection And Mitigation: A Causality-Based Approach, Bing Sun, Jun Sun, Wayne Koh, Jie Shi

Research Collection School Of Computing and Information Systems

Different from ordinary backdoors in neural networks which are introduced with artificial triggers (e.g., certain specific patch) and/or by tampering the samples, semantic backdoors are introduced by simply manipulating the semantic, e.g., by labeling green cars as frogs in the training set. By focusing on samples with rare semantic features (such as green cars), the accuracy of the model is often minimally affected. Since the attacker is not required to modify the input sample during training nor inference time, semantic backdoors are challenging to detect and remove. Existing backdoor detection and mitigation techniques are shown to be ineffective with respect …

Neuron Sensitivity Guided Test Case Selection, Dong Huang, Qingwen Bu, Yichao Fu, Yuhao Qing, Xiaofei Xie, Junjie Chen, Heming Cui

Research Collection School Of Computing and Information Systems

Deep Neural Networks (DNNs) have been widely deployed in software to address various tasks (e.g., autonomous driving, medical diagnosis). However, they can also produce incorrect behaviors that result in financial losses and even threaten human safety. To reveal and repair incorrect behaviors in DNNs, developers often collect rich, unlabeled datasets from the natural world and label them to test DNN models. However, properly labeling a large number of datasets is a highly expensive and time-consuming task. To address the above-mentioned problem, we propose NSS, Neuron Sensitivity Guided Test Case Selection, which can reduce the labeling time by selecting valuable test …

Coca: Improving And Explaining Graph Neural Network-Based Vulnerability Detection Systems, Sicong Cao, Xiaobing Sun, Xiaoxue Wu, David Lo, Lili Bo, Bin Li, Wei Liu

Research Collection School Of Computing and Information Systems

Recently, Graph Neural Network (GNN)-based vulnerability detection systems have achieved remarkable success. However, the lack of explainability poses a critical challenge to deploy black-box models in security-related domains. For this reason, several approaches have been proposed to explain the decision logic of the detection model by providing a set of crucial statements positively contributing to its predictions. Unfortunately, due to the weakly-robust detection models and suboptimal explanation strategy, they have the danger of revealing spurious correlations and redundancy issue.In this paper, we propose Coca, a general framework aiming to 1) enhance the robustness of existing GNN-based vulnerability detection models to …

Robust Test Selection For Deep Neural Networks, Weifeng Sun, Meng Yan, Zhongxin Liu, David Lo

Research Collection School Of Computing and Information Systems

Deep Neural Networks (DNNs) have been widely used in various domains, such as computer vision and software engineering. Although many DNNs have been deployed to assist various tasks in the real world, similar to traditional software, they also suffer from defects that may lead to severe outcomes. DNN testing is one of the most widely used methods to ensure the quality of DNNs. Such method needs rich test inputs with oracle information (expected output) to reveal the incorrect behaviors of a DNN model. However, manually labeling all the collected test inputs is a labor-intensive task, which delays the quality assurance …

Dexbert: Effective, Task-Agnostic And Fine-Grained Representation Learning Of Android Bytecode, Tiezhu Sun, Kevin Allix, Kisub Kim, Xin Zhou, Dongsun Kim, David Lo, Tegawendé F. Bissyande, Jacques Klein

Research Collection School Of Computing and Information Systems

The automation of an increasingly large number of software engineering tasks is becoming possible thanks to Machine Learning (ML). One foundational building block in the application of ML to software artifacts is the representation of these artifacts ( e.g. , source code or executable code) into a form that is suitable for learning. Traditionally, researchers and practitioners have relied on manually selected features, based on expert knowledge, for the task at hand. Such knowledge is sometimes imprecise and generally incomplete. To overcome this limitation, many studies have leveraged representation learning, delegating to ML itself the job of automatically devising suitable …

Qebverif: Quantization Error Bound Verification Of Neural Networks, Yedi Zhang, Fu Song, Jun Sun

Research Collection School Of Computing and Information Systems

To alleviate the practical constraints for deploying deep neural networks (DNNs) on edge devices, quantization is widely regarded as one promising technique. It reduces the resource requirements for computational power and storage space by quantizing the weights and/or activation tensors of a DNN into lower bit-width fixed-point numbers, resulting in quantized neural networks (QNNs). While it has been empirically shown to introduce minor accuracy loss, critical verified properties of a DNN might become invalid once quantized. Existing verification methods focus on either individual neural networks (DNNs or QNNs) or quantization error bound for partial quantization. In this work, we propose …

Context-Aware Neural Fault Localization, Zhuo Zhang, Xiaoguang Mao, Meng Yan, Xin Xia, David Lo, David Lo

Research Collection School Of Computing and Information Systems

Numerous fault localization techniques identify suspicious statements potentially responsible for program failures by discovering the statistical correlation between test results (i.e., failing or passing) and the executions of the different statements of a program (i.e., covered or not covered). They rarely incorporate a failure context into their suspiciousness evaluation despite the fact that a failure context showing how a failure is produced is useful for analyzing and locating faults. Since a failure context usually contains the transitive relationships among the statements of causing a failure, its relationship complexity becomes one major obstacle for the context incorporation in suspiciousness evaluation of …

Seed Selection For Testing Deep Neural Networks, Yuhan Zhi, Xiaofei Xie, Chao Shen, Jun Sun, Xiaoyu Zhang, Xiaohong Guan

Research Collection School Of Computing and Information Systems

Deep learning (DL) has been applied in many applications. Meanwhile, the quality of DL systems is becoming a big concern. To evaluate the quality of DL systems, a number of DL testing techniques have been proposed. To generate test cases, a set of initial seed inputs are required. Existing testing techniques usually construct seed corpus by randomly selecting inputs from training or test dataset. Till now, there is no study on how initial seed inputs affect the performance of DL testing and how to construct an optimal one. To fill this gap, we conduct the first systematic study to evaluate …

On-Device Deep Multi-Task Inference Via Multi-Task Zipping, Xiaoxi He, Xu Wang, Zimu Zhou, Jiahang Wu, Zheng Yang, Lothar Thiele

Research Collection School Of Computing and Information Systems

Future mobile devices are anticipated to perceive, understand and react to the world on their own by running multiple correlated deep neural networks locally on-device. Yet the complexity of these deep models needs to be trimmed down both within-model and cross-model to fit in mobile storage and memory. Previous studies squeeze the redundancy within a single model. In this work, we aim to reduce the redundancy across multiple models. We propose Multi-Task Zipping (MTZ), a framework to automatically merge correlated, pre-trained deep neural networks for cross-model compression. Central in MTZ is a layer-wise neuron sharing and incoming weight updating scheme …

Chatgpt As Metamorphosis Designer For The Future Of Artificial Intelligence (Ai): A Conceptual Investigation, Amarjit Kumar Singh (Library Assistant), Dr. Pankaj Mathur (Deputy Librarian)

Library Philosophy and Practice (e-journal)

Abstract

Purpose: The purpose of this research paper is to explore ChatGPT’s potential as an innovative designer tool for the future development of artificial intelligence. Specifically, this conceptual investigation aims to analyze ChatGPT’s capabilities as a tool for designing and developing near about human intelligent systems for futuristic used and developed in the field of Artificial Intelligence (AI). Also with the helps of this paper, researchers are analyzed the strengths and weaknesses of ChatGPT as a tool, and identify possible areas for improvement in its development and implementation. This investigation focused on the various features and functions of ChatGPT that …

Which Neural Network Makes More Explainable Decisions? An Approach Towards Measuring Explainability, Mengdi Zhang, Jun Sun, Jingyi Wang

Research Collection School Of Computing and Information Systems

Neural networks are getting increasingly popular thanks to their exceptional performance in solving many real-world problems. At the same time, they are shown to be vulnerable to attacks, difficult to debug and subject to fairness issues. To improve people’s trust in the technology, it is often necessary to provide some human-understandable explanation of neural networks’ decisions, e.g., why is that my loan application is rejected whereas hers is approved? That is, the stakeholder would be interested to minimize the chances of not being able to explain the decision consistently and would like to know how often and how easy it …

Qvip: An Ilp-Based Formal Verification Approach For Quantized Neural Networks, Yedi Zhang, Zhe Zhao, Guangke Chen, Fu Song, Min Zhang, Taolue Chen, Jun Sun

Research Collection School Of Computing and Information Systems

Deep learning has become a promising programming paradigm in software development, owing to its surprising performance in solving many challenging tasks. Deep neural networks (DNNs) are increasingly being deployed in practice, but are limited on resource-constrained devices owing to their demand for computational power. Quantization has emerged as a promising technique to reduce the size of DNNs with comparable accuracy as their floating-point numbered counterparts. The resulting quantized neural networks (QNNs) can be implemented energy-efficiently. Similar to their floating-point numbered counterparts, quality assurance techniques for QNNs, such as testing and formal verification, are essential but are currently less explored. In …

Stitching Weight-Shared Deep Neural Networks For Efficient Multitask Inference On Gpu, Zeyu Wang, Xiaoxi He, Zimu Zhou, Xu Wang, Qiang Ma, Xin Miao, Zhuo Liu, Lothar Thiele, Zheng. Yang

Research Collection School Of Computing and Information Systems

Intelligent personal and home applications demand multiple deep neural networks (DNNs) running on resourceconstrained platforms for compound inference tasks, known as multitask inference. To fit multiple DNNs into low-resource devices, emerging techniques resort to weight sharing among DNNs to reduce their storage. However, such reduction in storage fails to translate into efficient execution on common accelerators such as GPUs. Most DNN graph rewriters are blind for multiDNN optimization, while GPU vendors provide inefficient APIs for parallel multi-DNN execution at runtime. A few prior graph rewriters suggest cross-model graph fusion for low-latency multiDNN execution. Yet they request duplication of the shared …

Npc: Neuron Path Coverage Via Characterizing Decision Logic Of Deep Neural Networks, Xiaofei Xie, Tianlin Li, Jian Wang, Lei Ma, Qing Guo, Felix Juefei-Xu, Yang Liu

Research Collection School Of Computing and Information Systems

Deep learning has recently been widely applied to many applications across different domains, e.g., image classification and audio recognition. However, the quality of Deep Neural Networks (DNNs) still raises concerns in the practical operational environment, which calls for systematic testing, especially in safety-critical scenarios. Inspired by software testing, a number of structural coverage criteria are designed and proposed to measure the test adequacy of DNNs. However, due to the blackbox nature of DNN, the existing structural coverage criteria are difficult to interpret, making it hard to understand the underlying principles of these criteria. The relationship between the structural coverage and …

Canary: An Automated Approach To Security Scanning And Remediation, David Wiles

Masters Theses & Specialist Projects

Modern software has a smaller attack surface today than in the past. Memory-safe languages, container runtimes, virtual machines, and a mature web stack all contribute to the relative safety of the web and software in general compared to years ago. Despite this, we still see high-profile bugs, hacks, and outages which affect major companies and widely-used technologies. The extensive work that has gone into hardening virtualization, containerization, and commonly used applications such as Nginx still depends on the end-user to configure correctly to prevent a compromised machine.

In this paper, I introduce a tool, which I call Canary, which can …

Ad-Corre: Adaptive Correlation-Based Loss For Facial Expression Recognition In The Wild, Ali Pourramezan Fard, Mohammad H. Mahoor

Electrical and Computer Engineering: Faculty Scholarship

Automated Facial Expression Recognition (FER) in the wild using deep neural networks is still challenging due to intra-class variations and inter-class similarities in facial images. Deep Metric Learning (DML) is among the widely used methods to deal with these issues by improving the discriminative power of the learned embedded features. This paper proposes an Adaptive Correlation (Ad-Corre) Loss to guide the network towards generating embedded feature vectors with high correlation for within-class samples and less correlation for between-class samples. Ad-Corre consists of 3 components called Feature Discriminator, Mean Discriminator, and Embedding Discriminator. We design the Feature Discriminator component to guide …

Modeling Functional Similarity In Source Code With Graph-Based Siamese Networks, Nikita Mehrotra, Navdha Agarwal, Piyush Gupta, Saket Anand, David Lo, Rahul Purandare

Research Collection School Of Computing and Information Systems

Code clones are duplicate code fragments that share (nearly) similar syntax or semantics. Code clone detection plays an important role in software maintenance, code refactoring, and reuse. A substantial amount of research has been conducted in the past to detect clones. A majority of these approaches use lexical and syntactic information to detect clones. However, only a few of them target semantic clones. Recently, motivated by the success of deep learning models in other fields, including natural language processing and computer vision, researchers have attempted to adopt deep learning techniques to detect code clones. These approaches use lexical information (tokens) …

Taming The Data In The Internet Of Vehicles, Shahab Tayeb

Mineta Transportation Institute

As an emerging field, the Internet of Vehicles (IoV) has a myriad of security vulnerabilities that must be addressed to protect system integrity. To stay ahead of novel attacks, cybersecurity professionals are developing new software and systems using machine learning techniques. Neural network architectures improve such systems, including Intrusion Detection System (IDSs), by implementing anomaly detection, which differentiates benign data packets from malicious ones. For an IDS to best predict anomalies, the model is trained on data that is typically pre-processed through normalization and feature selection/reduction. These pre-processing techniques play an important role in training a neural network to optimize …

Automating App Review Response Generation Based On Contextual Knowledge, Cuiyun Gao, Wenjie Zhou, Xin Xia, David Lo, Qi Xie, Michael R. Lyu

Research Collection School Of Computing and Information Systems

User experience of mobile apps is an essential ingredient that can influence the user base and app revenue. To ensure good user experience and assist app development, several prior studies resort to analysis of app reviews, a type of repository that directly reflects user opinions about the apps. Accurately responding to the app reviews is one of the ways to relieve user concerns and thus improve user experience. However, the response quality of the existing method relies on the pre-extracted features from other tools, including manually labelled keywords and predicted review sentiment, which may hinder the generalizability and flexibility of …

Sofi: Reflection-Augmented Fuzzing For Javascript Engines, Xiaoyu He, Xiaofei Xie, Yuekang Li, Jianwen Sun, Feng Li, Wei Zou, Yang Liu, Lei Yu, Jianhua Zhou, Wenchang Shi, Wei Huo

Research Collection School Of Computing and Information Systems

JavaScript engines have been shown prone to security vulnerabilities, which can lead to serious consequences due to their popularity. Fuzzing is an effective testing technique to discover vulnerabilities. The main challenge of fuzzing JavaScript engines is to generate syntactically and semantically valid inputs such that deep functionalities can be explored. However, due to the dynamic nature of JavaScript and the special features of different engines, it is quite challenging to generate semantically meaningful test inputs.We observed that state-of-the-art semantic-aware JavaScript fuzzers usually require manually written rules to analyze the semantics for a JavaScript engine, which is labor-intensive, incomplete and engine-specific. …

Pruning Meta-Trained Networks For On-Device Adaptation, Dawei Gao, Xiaoxi He, Zimu Zhou, Yongxin Tong, Lothar Thiele

Research Collection School Of Computing and Information Systems

Adapting neural networks to unseen tasks with few training samples on resource-constrained devices benefits various Internet-of-Things applications. Such neural networks should learn the new tasks in few shots and be compact in size. Meta-learning enables few-shot learning, yet the meta-trained networks can be overparameterised. However, naive combination of standard compression techniques like network pruning with meta-learning jeopardises the ability for fast adaptation. In this work, we propose adaptation-aware network pruning (ANP), a novel pruning scheme that works with existing meta-learning methods for a compact network capable of fast adaptation. ANP uses weight importance metric that is based on the sensitivity …

Taxthemis: Interactive Mining And Exploration Of Suspicious Tax Evasion Group, Yating Lin, Kamkwai Wong, Yong Wang, Rong Zhang, Bo Dong, Huamin Qu, Qinghua Zheng

Research Collection School Of Computing and Information Systems

Tax evasion is a serious economic problem for many countries, as it can undermine the government’s tax system and lead to an unfair business competition environment. Recent research has applied data analytics techniques to analyze and detect tax evasion behaviors of individual taxpayers. However, they have failed to support the analysis and exploration of the related party transaction tax evasion (RPTTE) behaviors (e.g., transfer pricing), where a group of taxpayers is involved. In this paper, we present TaxThemis, an interactive visual analytics system to help tax officers mine and explore suspicious tax evasion groups through analyzing heterogeneous tax-related data. A …

Independent Reinforcement Learning For Weakly Cooperative Multiagent Traffic Control Problem, Chengwei Zhang, Shan Jin, Wanli Xue, Xiaofei Xie, Shengyong Chen, Rong Chen

Research Collection School Of Computing and Information Systems

The adaptive traffic signal control (ATSC) problem can be modeled as a multiagent cooperative game among urban intersections, where intersections cooperate to counter the city's traffic conditions. Recently, reinforcement learning (RL) has achieved marked successes in managing sequential decision making problems, which motivates us to apply RL in the ATSC problem. One of the largest challenges of this problem is that the observation of intersection is typically partially observable, which limits the learning performance of RL algorithms. Considering the large scale of intersections in an urban traffic environment, we use independent RL to solve ATSC problem in this study. We …

An Empirical Study Of Gui Widget Detection For Industrial Mobile Games, Jiaming Ye, Ke Chen, Xiaofei Xie, Lei Ma, Ruochen Huang, Yingfeng Chen, Yinxing Xue, Jianjun Zhao

Research Collection School Of Computing and Information Systems

With the widespread adoption of smartphones in our daily life, mobile games experienced increasing demand over the past years. Meanwhile, the quality of mobile games has been continuously drawing more and more attention, which can greatly affect the player experience. For better quality assurance, general-purpose testing has been extensively studied for mobile apps. However, due to the unique characteristic of mobile games, existing mobile testing techniques may not be directly suitable and applicable. To better understand the challenges in mobile game testing, in this paper, we first initiate an early step to conduct an empirical study towards understanding the challenges …

Ava: Adversarial Vignetting Attack Against Visual Recognition, Binyu Tian, Felix Juefei-Xu, Qing Guo, Xiaofei Xie, Xiaohong Li, Yang Liu

Research Collection School Of Computing and Information Systems

Vignetting is an inherent imaging phenomenon within almost all optical systems, showing as a radial intensity darkening toward the corners of an image. Since it is a common effect for photography and usually appears as a slight intensity variation, people usually regard it as a part of a photo and would not even want to post-process it. Due to this natural advantage, in this work, we study the vignetting from a new viewpoint, i.e., adversarial vignetting attack (AVA), which aims to embed intentionally misleading information into the vignetting and produce a natural adversarial example without noise patterns. This example can …

Deeprepair: Style-Guided Repairing For Deep Neural Networks In The Real-World Operational Environment, Bing Yu, Hua Qi, Guo Qing, Felix Juefei-Xu, Xiaofei Xie, Lei Ma, Jianjun Zhao

Research Collection School Of Computing and Information Systems

Deep neural networks (DNNs) are continuously expanding their application to various domains due to their high performance. Nevertheless, a well-trained DNN after deployment could oftentimes raise errors during practical use in the operational environment due to the mismatching between distributions of the training dataset and the potential unknown noise factors in the operational environment, e.g., weather, blur, noise, etc. Hence, it poses a rather important problem for the DNNs' real-world applications: how to repair the deployed DNNs for correcting the failure samples under the deployed operational environment while not harming their capability of handling normal or clean data with limited …

Code Integrity Attestation For Plcs Using Black Box Neural Network Predictions, Yuqi Chen, Christopher M. Poskitt, Jun Sun

Research Collection School Of Computing and Information Systems

Cyber-physical systems (CPSs) are widespread in critical domains, and significant damage can be caused if an attacker is able to modify the code of their programmable logic controllers (PLCs). Unfortunately, traditional techniques for attesting code integrity (i.e. verifying that it has not been modified) rely on firmware access or roots-of-trust, neither of which proprietary or legacy PLCs are likely to provide. In this paper, we propose a practical code integrity checking solution based on privacy-preserving black box models that instead attest the input/output behaviour of PLC programs. Using faithful offline copies of the PLC programs, we identify their most important …

Bias Field Poses A Threat To Dnn-Based X-Ray Recognition, Bingyu Tian, Qing Guo, Felix Juefei-Xu, Wen Le Chan, Yupeng Cheng, Xiaohong Li, Xiaofei Xie, Shengchao Qin

Research Collection School Of Computing and Information Systems

Chest X-ray plays a key role in screening and diagnosis of many lung diseases including the COVID-19. Many works construct deep neural networks (DNNs) for chest X-ray images to realize automated and efficient diagnosis of lung diseases. However, bias field caused by the improper medical image acquisition process widely exists in the chest X-ray images while the robustness of DNNs to the bias field is rarely explored, posing a threat to the X-ray-based automated diagnosis system. In this paper, we study this problem based on the adversarial attack and propose a brand new attack, i.e., adversarial bias field attack where …

Breaking Neural Reasoning Architectures With Metamorphic Relation-Based Adversarial Examples, Alvin Chan, Lei Ma, Felix Juefei-Xu, Yew-Soon Ong, Xiaofei Xie, Minhui Xue, Yang Liu

Research Collection School Of Computing and Information Systems

The ability to read, reason, and infer lies at the heart of neural reasoning architectures. After all, the ability to perform logical reasoning over language remains a coveted goal of Artificial Intelligence. To this end, models such as the Turing-complete differentiable neural computer (DNC) boast of real logical reasoning capabilities, along with the ability to reason beyond simple surface-level matching. In this brief, we propose the first probe into DNC's logical reasoning capabilities with a focus on text-based question answering (QA). More concretely, we propose a conceptually simple but effective adversarial attack based on metamorphic relations. Our proposed adversarial attack …