Security Issues and Privacy Preserving in Machine Learning

Ride-hailing service has become a popular means of transportation due to its convenience and low cost. However, it also raises privacy concerns. Since riders' mobility information including the pick-up and drop-off location is tracked, the service provider can infer sensitive information about the riders such as where they live and work. To address these concerns, we propose location privacy preserving techniques that efficiently match riders and drivers while preserving riders' location privacy. We first propose a baseline solution that allows a rider to select the driver who is the closest to his pick-up location. However, with some side information, the service provider can launch location inference attacks. To overcome these attacks, we propose an enhanced scheme that allows a rider to specify his privacy preference. Novel techniques are designed to preserve rider's personalized privacy with limited loss of matching accuracy. Through trace-driven simulations, we compare our enhanced privacy preserving solution to existing work. Evaluation results show that our solution provides much better ride matching results that are close to the optimal solution, while preserving personalized location privacy for riders.

Artificial Intelligence (AI) has attracted a large amount of attention in recent years. However, several new problems, such as privacy violations, security issues, or effectiveness, have been emerging. Differential privacy has several attractive properties that make it quite valuable for AI, such as privacy preservation, security, randomization, composition, and stability. Therefore, this paper presents differential privacy mechanisms for multi-agent systems, reinforcement learning, and knowledge transfer based on those properties, which proves that current AI can benefit from differential privacy mechanisms. In addition, the previous usage of differential privacy mechanisms in private machine learning, distributed machine learning, and fairness in models is discussed, bringing several possible avenues to use differential privacy mechanisms in AI. The purpose of this paper is to deliver the initial idea of how to integrate AI with differential privacy mechanisms and to explore more possibilities to improve AIs performance.

This dissertation addresses two significant issues in the effective application of machine learning algorithms and models for the physical and engineering sciences. The first is the broad challenge of automated modeling of data across different processes in a physical system. The second is the dilemma of obtaining insightful interpretations on the relationships between the inputs and outcome of a system as inferred from complex, black box machine learning models.Automated Geometric Shape Deviation Modeling for Additive Manufacturing SystemsAdditive manufacturing systems possess an intrinsic capability for one-of-a-kind manufacturing of a vast variety of shapes across a wide spectrum of processes. One major issue in AM systems is geometric accuracy control for the inevitable shape deviations that arise in AM processes. Current effective approaches for shape deviation control in AM involve the specification of statistical or machine learning deviation models for additively manufactured products. However, this task is challenging due to the constraints on the number of test shapes that can be manufactured in practice, and limitations on user efforts that can be devoted for learning deviation models across different shape classes and processes in an AM system. We develop an automated, Bayesian neural network methodology for comprehensive shape deviation modeling in an AM system. A fundamental innovation in this machine learning method is our new and connectable neural network structures that facilitate the transfer of prior knowledge and models on deviations across different shape classes and AM processes. Several case studies on in-plane and out-of-plane deviations, regular and free-form shapes, and different settings of lurking variables serve to validate the power and broad scope of our methodology, and its potential to advance high-quality manufacturing in an AM system.Interpretable Machine LearningMachine learning algorithms and models constitute the dominant set of predictive methods for a wide range of complex, real-world processes. However, interpreting what such methods effectively infer from data is difficult in general. This is because their typical black box natures possess a limited ability to directly yield insights on the underlying relationships between inputs and the outcome for a process. We develop methodologies based on new predictive comparison estimands that effectively enable one to ``mine’’ machine learning models, in the sense of (a) interpreting their inferred associations between inputs and/or functional forms of inputs with the outcome, (b) identifying the inputs that they effectively consider relevant, and (c) interpreting the inferred conditional and two-way associations of the inputs with the outcome. We establish Fisher consistent estimators, and their corresponding standard errors, for our new estimands under a condition on the inputs' distributions. The significance of our predictive comparison methodology is demonstrated with a wide range of simulation and case studies that involve Bayesian additive regression trees, neural networks, and support vector machines. Our extended study of interpretable machine learning for AM systems demonstrates how our method can contribute to smarter advanced manufacturing systems, especially as current machine learning methods for AM are lacking in their ability to yield meaningful engineering knowledge on AM processes.

Medical studies are usually time consuming, cumbersome and extremely costly to perform, and for exploratory research, their results are also difficult to predict a priori. This is particularly the case for rare diseases, for which finding enough patients is difficult and usually requires an international-scale research. In this case, the process can be even more difficult due to the heterogeneity of data-protection regulations, making the data sharing process particularly hard. In this short paper, we propose MedCo2 (pronounced MedCo square), a distributed system that streamlines the process of a medical study by bridging and enabling both data discovery and data analysis among multiple databases, while protecting data confidentiality and patients' privacy. MedCo2 relies on interactive protocols, homomorphic encryption and differential privacy. It enables the privacy-preserving computations of multiple statistics such as cosine similarity and variance, and the training of machine learning models, on patients that are obliviously selected according to specific criteria among multiple databases.

Caveolae are plasma membrane invaginations whose formation requires caveolin-1 (Cav1), the adaptor protein polymerase I, and the transcript release factor (PTRF or CAVIN1). Caveolae have an important role in cell functioning, signaling, and disease. In the absence of CAVIN1/PTRF, Cav1 forms non-caveolar membrane domains called scaffolds. In this work, we train machine learning models to automatically distinguish between caveolae and scaffolds from single molecule localization microscopy (SMLM) data. We apply machine and deep learning algorithms to discriminate biological structures from SMLM data. Our work is the first that is leveraging machine and deep learning approaches to automatically identifying biological structures from SMLM data. In particular, we develop and compare three binary classification methods to identify whether or not a given 3D cluster of Cav1 proteins is a caveolae. The first uses a random forest classifier applied to 28 hand-picked features, the second uses a convolutional neural net (CNN) applied to a projection of the point clouds onto three planes, and the third uses a PointNet model, a recent development that can directly take point clouds as its input. We validate our methods on a dataset of super-resolution microscopy images of PC3 prostate cancer cells labeled for Cav1. Specifically, we have images from two cell populations: 10 PC3 and 10 CAVIN1/PTRF-transfected PC3 cells (PC3-PTRF cells) that form caveolae. We obtained a balanced set of 1714 different cellular structures. Our results show that both the random forest on hand selected features and the deep learning approach achieve high accuracy in distinguishing the intrinsic features of the caveolae and non-caveolae biological structures. More specifically, both random forest and deep CNN classifiers achieve classification accuracy reaching 94% on our test set, while the PointNet model only reached 83% accuracy. We also discuss the pros and cons of the different approaches. Additional information about individual files is in the accompanying CSV file (item_metadata.csv). This dataset was originally deposited in the Simon Fraser University institutional repository.

The Internet of things is a new technological revolution following the computer and Internet. It aims to connect all physical objects existing in the world and forms a network with everything. In recent years, smart home gradually enters into our life. Smart home uses the Internet of things technology to connect all kinds of devices in the home, to achieve a smart home environment. Although the development of smart home has brought a qualitative leap to people’s life, there are many problems in security. Privacy security is one of the challenges to the smart home environment. Attackers can intrude various smart devices in the smart home environment, to achieve the purpose of stealing users’ personal information and privacy. Among these devices, smart cameras are the most intruded frequently. Since many cameras are installed in users’ homes to achieve real-time monitoring of the environment, but the existence of these cameras provides a channel to get information for attackers. In recent years, the leak of video privacy is emerging in an endless stream. According to the researches about privacy protection, this paper proposes a new scheme to selectively encrypt the video captured by the cameras through machine learning technology, so as to protect the personal privacy of users and improve the security of the smart home environment.

Bidirectional Human-Robot Learning: Imitation and Skill Improvement

Recently, with the rapid development of information and communication technologies, the infrastructures, resources, end devices, and applications in communications and networking systems are becoming much more complex and heterogeneous. In addition, the large volume of data and massive end devices may bring serious security, privacy, services provisioning, and network management challenges. In order to achieve decentralized, secure, intelligent, and efficient network operation and management, the joint consideration of blockchain and machine learning (ML) may bring significant benefits and have attracted great interests from both academia and industry. On one hand, blockchain can significantly facilitate training data and ML model sharing, decentralized intelligence, security, privacy, and trusted decision-making of ML. On the other hand, ML will have significant impacts on the development of blockchain in communications and networking systems, including energy and resource efficiency, scalability, security, privacy, and intelligent smart contracts. However, some essential open issues and challenges that remain to be addressed before the widespread deployment of the integration of blockchain and ML, including resource management, data processing, scalable operation, and security issues. In this paper, we present a survey on the existing works for blockchain and ML technologies. We identify several important aspects of integrating blockchain and ML, including overview, benefits, and applications. Then we discuss some open issues, challenges, and broader perspectives that need to be addressed to jointly consider blockchain and ML for communications and networking systems.

The Internet of Things (IoT) has become a foundational element of the digital infrastructure, extending its connectivity across various sectors and embedding intelligence in everyday devices. This article introduces SecureNet, a pioneering approach that integrates Machine Learning (ML), Blockchain, and Federated Learning (FL) to enhance IoT security. To navigate this challenging train, an innovative framework that synergizes Machine Learning (ML), Blockchain technology, and Federated Learning (FL) to fortify IoT security. SecureNet is architected to deliver a robust defense mechanism for IoT ecosystems, providing resilience against increasingly sophisticated cyber threats, and ensuring the preservation of data integrity, privacy, and unwavering system reliability. This study explores the application of advanced ML techniques NSL-KDD dataset, implementing two highly effective classifiers: Random Forest and Logistic Regression. The Random Forest classifier exhibited an exceptional accuracy of 99.85%, while the Logistic Regression model demonstrated a near-perfect accuracy of 99.03%. These compelling results highlight the efficacy of ML in identifying and mitigating activities within network traffic. SecureNet leverages ML’s profound analytical capabilities for intelligent threat discernment, Blockchain’s immutable ledgers for unassailable data verification, and FL’s privacy-centric approach to distribute model training. These outcomes underscore the potential of ML models to enhance IoT security by accurately identifying malicious patterns and anomalies within network traffic.

Privacy preserving in machine learning is a crucial issue in industry informatics since data used for training in industries usually contain sensitive information. Existing differentially private machine learning algorithms have not considered the impact of data correlation, which may lead to more privacy leakage than expected in industrial applications. For example, data collected for traffic monitoring may contain some correlated records due to temporal correlation or user correlation. To fill this gap, in this article, we propose a correlation reduction scheme with differentially private feature selection considering the issue of privacy loss when data have correlation in machine learning tasks. The proposed scheme involves five steps with the goal of managing the extent of data correlation, preserving the privacy, and supporting accuracy in the prediction results. In this way, the impact of data correlation is relieved with the proposed feature selection scheme, and moreover the privacy issue of data correlation in learning is guaranteed. The proposed method can be widely used in machine learning algorithms, which provide services in industrial areas. Experiments show that the proposed scheme can produce better prediction results with machine learning tasks and fewer mean square errors for data queries compared to existing schemes.

Preservation of privacy in data mining and machine learning has emerged as an absolute prerequisite in many practical scenarios, especially when the processing of sensitive data is outsourced to an external third party. Currently, privacy preservation methods are mainly based on randomization and/or perturbation, secure multiparty computations and cryptographic methods. In this paper, we take advantage of the partial homomorphic property of some cryptosystems to train simple machine learning models with encrypted data. Our basic scenario has three parties: multiple Data Owners, which provide encrypted training examples; the Algorithm Owner (or Application), which processes them to adjust the parameters of its models; and a semi-trusted third party, which provides privacy and secure computation services to the Application in some operations not supported by the homomorphic cryptosystem. In particular, we focus on two issues: the use of multiple-key cryptosystems, and the impact of the quantization of real-valued input data required before encryption. In addition, we develop primitives based on the outsourcing of a reduced set of operations that allows to implement general machine learning algorithms using efficient dedicated hardware. As applications, we consider the training of classifiers using privacy-protected data and the tracking of a moving target using encrypted distance measurements.

With the urbanization process, an increasing number of sensors are being deployed in transportation systems, leading to an explosion of big data. To harness the power of this vast transportation data, various machine learning (ML) and artificial intelligence (AI) methods have been introduced to address numerous transportation challenges. However, these methods often require significant investment in data collection, processing, storage, and the employment of professionals with expertise in transportation and ML. Additionally, privacy issues are a major concern when processing data for real-world traffic control and management. To address these challenges, the research team proposes an innovative multi-agent framework called Independent Mobility Generative Pre-Trained Transformers (IDM-GPT) based on large language models (LLMs) for customized traffic analysis, management suggestions, and privacy preservation. IDM-GPT efficiently connects users, transportation databases, and ML models economically. IDM-GPT trains, customizes, and applies various LLM-based AI agents for multiple functions, including user query comprehension, prompts optimization, data analysis, model selection, and performance evaluation and enhancement. With IDM-GPT, users without any background in transportation or ML can efficiently and intuitively obtain data analysis and customized suggestions in near real-time based on their questions. Experimental results demonstrate that IDM-GPT delivers satisfactory performance across multiple traffic-related tasks, providing comprehensive and actionable insights that support effective traffic management and urban mobility improvement.

With fast growth in Internet and digital imaging knowledge, there are progressive customs to simply generate, distribute and allocate the images. Measured the association among digital imaging and privacy fortification, Visual Cryptography and Secret Image Sharing is an inclusive preamble to original security methods. The secret sharing control system is used to guard unauthorized data access and to secure distribution of responsive information. An efficient color image visual cryptic filtering scheme is to improve the image quality on restored original image from visual cryptic shares. The color image visual cryptic filtering scheme presents a deblurring effect on the non-uniform distribution of visual cryptic share pixels. Fourier transformation and texture overlapping is applied to normalize the unevenly transformed share pixels on the original restored image. This in turn improves the quality of restored visual cryptographic image to its optimality. The privacy preservation in visual cryptography plays a major role to provide an efficient secure communication for the users. To address data sharing issues more sensitively, a privacy preservation achieved by using cache-cache mechanism. The cache-cache mechanism maintains a cache inside a cache to preserve the details about the users who shared the secret parts of digital document, which has been splitted in a scheme of visual cryptography. In this work, the binary spanning trees are used to enhance the progress of secure distributed file sharing in visual cryptography. Privacy of file sharing is done with file block id relating to the participant id using binary trees. Group dynamics is handled effectively with distributed key exchange model, based on the principal operation of minimum spanning tree variants. Experimentation carried out with bench mark data sets of real and synthetically generated data sets to estimate the performance of the proposed controlled adaptable distributed file sharing with multiple participants in visual cryptography in terms of group dynamic rate, tree spanning length and privacy overhead.

As digital innovation advances, concerns surrounding privacy escalate. This manuscript explores the intricate relationship between machine learning and privacy preservation. Beginning with a comprehensive literature review, we delve into the current state of privacy in the digital age and examine machine learning’s role in addressing these concerns. The manuscript highlights key privacy-preserving techniques, including homomorphic encryption, differential privacy, and federated learning, providing in-depth insights into their applications and real-world implementations. Anticipating future challenges and trends, we recommend maintaining a delicate equilibrium between innovation and privacy in the dynamic landscape of machine learning.

Human pose estimation is a pivotal domain within computer vision, underpinning applications from motion capture in cinematic production to sophisticated user interfaces in desktop devices. This research delineates the implementation of real-time human pose estimation within web browsers utilizing TensorFlow.js and the PoseNet model. PoseNet, an advanced machine learning model optimized for browser-based execution, facilitates precise pose detection sans specialized hardware. The primary aim of this study is to integrate PoseNet with TensorFlow.js, achieving efficient real-time pose estimation directly in the browser by leveraging JavaScript, thereby ensuring seamless user interaction and broad accessibility. A modular system architecture is designed, focusing on optimization strategies such as model quantization, asynchronous processing, and on-device computation to enhance performance and privacy preservation. In conclusion, this research establishes a robust framework for deploying PoseNet in web environments, underscoring its potential to revolutionize human-computer interaction within browser-based applications. Our findings contribute significantly to the field of computer vision and machine learning, offering insights into the practical deployment of pose estimation models on widely accessible platforms. Keywords — ReaReal-time Pose Estimation, TensorFlow.js, PoseNet, Machine Learning, Computer Vision, Browser-based Pose Detection, Human-Computer Interaction, Multi-person Tracking, On-device Computation, Asynchronous Processing, Cross-browser Compatibility, Performance Optimization, Privacy-preserving AI, Web-based Machine Learning, Motion Capture, Fitness Tracking, Interactive , Virtual Reality Interfaces, Deep LearningLearning