The application of secure multiparty computation (MPC) in machine learning, especially privacy-preserving neural network training, has attracted tremendous attention from the research community in recent years. MPC enables several data owners to jointly train a neural network while preserving the data privacy of each participant. However, most of the previous works focus on semi-honest threat model that cannot withstand fraudulent messages sent by malicious participants. In this paper, we propose an approach for constructing efficient $n$-party protocols for secure neural network training that can provide security for all honest participants even when a majority of the parties are malicious. Compared to the other designs that provide semi-honest security in a dishonest majority setting, our actively secure neural network training incurs affordable efficiency overheads of around 2X and 2.7X in LAN and WAN settings, respectively. Besides, we propose a scheme to allow additive shares defined over an integer ring $\mathbb{Z}_N$ to be securely converted to additive shares over a finite field $\mathbb{Z}_Q$, which may be of independent interest. Such conversion scheme is essential in securely and correctly converting shared Beaver triples defined over an integer ring generated in the preprocessing phase to triples defined over a field to be used in the calculation in the online phase.
Many organizations stand to benefit from pooling their data together in order to draw mutually beneficial insights -- e.g., for fraud detection across banks, better medical studies across hospitals, etc. However, such organizations are often prevented from sharing their data with each other by privacy concerns, regulatory hurdles, or business competition. We present Senate, a system that allows multiple parties to collaboratively run analytical SQL queries without revealing their individual data to each other. Unlike prior works on secure multi-party computation (MPC) that assume that all part…
We present CrypTFlow, a first of its kind system that converts TensorFlow inference code into Secure Multi-party Computation (MPC) protocols at the push of a button. To do this, we build three components. Our first component, Athos, is an end-to-end compiler from TensorFlow to a variety of semi-honest MPC protocols. The second component, Porthos, is an improved semi-honest 3-party protocol that provides significant speedups for TensorFlow like applications. Finally, to provide malicious secure MPC protocols, our third component, Aramis, is a novel technique that uses hardware with integrity gu…
Federated Learning (FL) enables multiple parties to distributively train a ML model without revealing their private datasets. However, it assumes trust in the centralized aggregator which stores and aggregates model updates. This makes it prone to gradient tampering and privacy leakage by a malicious aggregator. Malicious parties can also introduce backdoors into the joint model by poisoning the training data or model gradients. To address these issues, we present BEAS, the first blockchain-based framework for N-party FL that provides strict privacy guarantees of training data using gradient p…
Secure Multi-Party Computation (MPC) is an area of cryptography that enables computation on sensitive data from multiple sources while maintaining privacy guarantees. However, theoretical MPC protocols often do not scale efficiently to real-world data. This project investigates the efficiency of the SPDZ framework, which provides an implementation of an MPC protocol with malicious security, in the context of popular machine learning (ML) algorithms. In particular, we chose applications such as linear regression and logistic regression, which have been implemented and evaluated using semi-hones…
A Trustworthy AIoT-enabled Localization System via Federated Learning and Blockchain
School of Electrical and Electronics Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）；Chainbase Inc.（Chainbase公司）；PublicAI Inc.（PublicAI公司）
Trojan of Things: Embedding Malicious NFC Tags into Common Objects
我们提出了一种名为Trojan of Things（ToT）的新型概念验证攻击，旨在攻击支持NFC的移动设备，如智能手机。ToT攻击的关键思想是将恶意编程的NFC标签秘密嵌入日常生活中经常遇到的常见物体，如钞票，衣服或家具，这些物体不被视为NFC接触点。为了充分探讨ToT的威胁，我们开发了两种引人注目的技术，即ToT设备和Phantom touch generator。这些技术使攻击者能够在无意中将设备靠近ToT的设备所有者不知情的情况下执行各种严重和复杂的攻击。我们讨论了攻击的可行性以及可能的对策对ToT攻击的威胁。
Microsoft Research（微软研究院）；Algorand Foundation（Algorand 基金会）；Technion（以色列理工学院）；Princeton University（普林斯顿大学）；UC Berkeley（加州大学伯克利分校）
We propose Falcon, an end-to-end 3-party protocol for efficient private training and inference of large machine learning models. Falcon presents four main advantages - (i) It is highly expressive with support for high capacity networks such as VGG16 (ii) it supports batch normalization which is important for training complex networks such as AlexNet (iii) Falcon guarantees security with abort against malicious adversaries, assuming an honest majority (iv) Lastly, Falcon presents new theoretical insights for protocol design that make it highly efficient and allow it to outperform existing secur…
The COVID-19 pandemic enabled "quishing", or phishing with malicious QR codes, as they became a convenient go-between for sharing URLs, including malicious ones. To explore the quishing phenomenon, we conducted a 173-participant study where we used a COVID-19 digital passport sign-up trial with a malicious QR code as a pretext. We found that 67 % of the participants were happy to sign-up with their Google or Facebook credentials, 18.5% to create a new account, and only 14.5% to skip on the sign-up. Convenience was the single most cited factor for the willingness to yield participants' credenti…
University of Washington（华盛顿大学）；Monash University（莫纳什大学）；Ghent University（根特大学）
Existing work on privacy-preserving machine learning with Secure Multiparty Computation (MPC) is almost exclusively focused on model training and on inference with trained models, thereby overlooking the important data pre-processing stage. In this work, we propose the first MPC based protocol for private feature selection based on the filter method, which is independent of model training, and can be used in combination with any MPC protocol to rank features. We propose an efficient feature scoring protocol based on Gini impurity to this end. To demonstrate the feasibility of our approach for …
A significant increase in the number of interconnected devices and data communication through wireless networks has given rise to various threats, risks and security concerns. Internet of Things (IoT) applications is deployed in almost every field of daily life, including sensitive environments. The edge computing paradigm has complemented IoT applications by moving the computational processing near the data sources. Among various security models, Machine Learning (ML) based intrusion detection is the most conceivable defense mechanism to combat the anomalous behavior in edge-enabled IoT netwo…
Software systems are increasingly relying on Artificial Intelligence (AI) and Machine Learning (ML) components. The emerging popularity of AI techniques in various application domains attracts malicious actors and adversaries. Therefore, the developers of AI-enabled software systems need to take into account various novel cyber-attacks and vulnerabilities that these systems may be susceptible to. This paper presents a framework to characterize attacks and weaknesses associated with AI-enabled systems and provide mitigation techniques and defense strategies. This framework aims to support softw…
Leveraging the Power of Ensemble Learning for Secure Low Altitude Economy
National Key Laboratory on Near-Surface Detection（近地表探测国家重点实验室）；Chengdu Fluid Dynamics Innovation Center（成都流体力学创新中心）；College of Computing and Data Science, NTU（南洋理工大学计算与数据科学学院）；College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；Nanyang Technological University（南洋理工大学）
Indian Institute of Science（印度科学学院）；Technical University of Darmstadt（达姆施塔特工业大学）
The growing volumes of data being collected and its analysis to provide better services are creating worries about digital privacy. To address privacy concerns and give practical solutions, the literature has relied on secure multiparty computation. However, recent research has mostly focused on the small-party honest-majority setting of up to four parties, noting efficiency concerns. In this work, we extend the strategies to support a larger number of participants in an honest-majority setting with efficiency at the center stage. Cast in the preprocessing paradigm, our semi-honest protocol im…
Smart grid adopts two-way communication and rich functionalities to gain a positive impact on the sustainability and efficiency of power usage, but on the other hand, also poses serious challenges to customers' privacy. Existing solutions in smart grid usually use cryptographic tools, such as homomorphic encryption, to protect individual privacy, which, however, can only support limited and simple functionalities. Moreover, the resource-constrained smart meters need to perform heavy asymmetric cryptography in these solutions, which is not applied to smart grid. In this paper, we present a prac…
Today, most embedded systems use Dynamic Voltage and Frequency Scaling (DVFS) to minimize energy consumption and maximize performance. The DVFS technique works by regulating the important parameters that govern the amount of energy consumed in a system, voltage and frequency. For the implementation of this technique, the operating system (OS) includes software applications that dynamically control a voltage regulator or a frequency regulator or both. In this paper, we demonstrate for the first time a malicious use of the frequency regulator against a TrustZone-enabled System-on-Chip (SoC). We …
The growing popularity of Internet-of-Things (IoT) has created the need for network-based traffic anomaly detection systems that could identify misbehaving devices. In this work, we propose a lightweight technique, IoT-guard, for identifying malicious traffic flows. IoT-guard uses semi-supervised learning to distinguish between malicious and benign device behaviours using the network traffic generated by devices. In order to achieve this, we extracted 39 features from network logs and discard any features containing redundant information. After feature selection, fuzzy C-Mean (FCM) algorithm w…
The rapid growth of online advertising has fueled the growth of ad-blocking software, such as new ad-blocking and privacy-oriented browsers or browser extensions. In response, both ad publishers and ad networks are constantly trying to pursue new strategies to keep up their revenues. To this end, ad networks have started to leverage the Web Push technology enabled by modern web browsers. As web push notifications (WPNs) are relatively new, their role in ad delivery has not been yet studied in depth. Furthermore, it is unclear to what extent WPN ads are being abused for malvertising (i.e., to d…
In this work, we consider the problem of secure multi-party computation (MPC), consisting of $Γ$ sources, each has access to a large private matrix, $N$ processing nodes or workers, and one data collector or master. The master is interested in the result of a polynomial function of the input matrices. Each source sends a randomized functions of its matrix, called as its share, to each worker. The workers process their shares in interaction with each other, and send some results to the master such that it can derive the final result. There are several constraints: (1) each worker can store a fu…
SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloud
Northeastern University（东北大学）；Indiana University Bloomington（印第安纳大学伯明顿分校）；University of Connecticut（康涅狄格大学）；University of Massachusetts Dartmouth（马萨诸塞大学达特茅斯分校）；North Carolina State University（北卡罗来纳州立大学）
Machine learning is gaining popularity in the network security domain as many more network-enabled devices get connected, as malicious activities become stealthier, and as new technologies like Software Defined Networking emerge. Compromising machine learning model is a desirable goal. In fact, spammers have been quite successful getting through machine learning enabled spam filters for years. While previous works have been done on adversarial machine learning, none has been considered within a defense-in-depth environment, in which correct classification alone may not be good enough. For the …
3GPP has introduced Private 5G to support the next-generation industrial automation system (IAS) due to the versatility and flexibility of 5G architecture. Besides the 3.5GHz CBRS band, unlicensed spectrum bands, like 5GHz, are considered as an additional medium because of their free and abundant nature. However, while utilizing the unlicensed band, industrial equipment must coexist with incumbents, e.g., Wi-Fi, which could introduce new security threats and resuscitate old ones. In this paper, we propose a novel attack strategy conducted by a mobility-enabled malicious Wi-Fi access point (mmA…
Multi-Continental Healthcare Modelling Using Blockchain-Enabled Federated Learning
School of Computing, Newcastle University（新castle大学计算机学院）；Department of Computing, Imperial College London（伦敦帝国理工学院计算机系）；Institute of Health Informatics, University College London（伦敦大学学院健康信息学研究所）；Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University（上海智能自主系统研究所，同济大学）；College of Electronics and Information Engineering, Tongji University（同济大学电子与信息工程学院）；University College London Hospital（伦敦大学学院医院）
In this paper, we design secure multi-party computation (MPC) protocols in the asynchronous communication setting with optimal resilience. Our protocols are secure against a computationally-unbounded malicious adversary, characterized by an adversary structure $\mathcal{Z}$, which enumerates all possible subsets of potentially corrupt parties. Our protocols incur a communication of $\mathcal{O}(|\mathcal{Z}|^2)$ and $\mathcal{O}(|\mathcal{Z}|)$ bits per multiplication for perfect and statistical security respectively. These are the first protocols with this communication complexity, as such pr…
To facilitate monitoring and management, modern Implantable Medical Devices (IMDs) are often equipped with wireless capabilities, which raise the risk of malicious access to IMDs. Although schemes are proposed to secure the IMD access, some issues are still open. First, pre-sharing a long-term key between a patient's IMD and a doctor's programmer is vulnerable since once the doctor's programmer is compromised, all of her patients suffer; establishing a temporary key by leveraging proximity gets rid of pre-shared keys, but as the approach lacks real authentication, it can be exploited by nearby…
Secure Multiparty Computation (MPC) can improve the security and privacy of data owners while allowing analysts to perform high quality analytics. Secure aggregation is a secure distributed mechanism to support federated deep learning without the need for trusted third parties. In this paper we present a highly performant secure aggregation protocol with sub-linear communication complexity. Our protocol achieves greater communication and computation efficiencies through a group-based approach. It is similar to secret sharing protocols extended to vectors of values-aka gradients-but within grou…
Advances in technology have enabled tremendous progress in the development of a highly connected ecosystem of ubiquitous computing devices collectively called the Internet of Things (IoT). Ensuring the security of IoT devices is a high priority due to the sensitive nature of the collected data. Physically Unclonable Functions (PUFs) have emerged as critical hardware primitive for ensuring the security of IoT nodes. Malicious modeling of PUF architectures has proven to be difficult due to the inherently stochastic nature of PUF architectures. Extant approaches to malicious PUF modeling assume t…
Industry 4.0 is all about doing things in a concurrent, secure, and fine-grained manner. IoT edge-sensors and their associated data play a predominant role in today's industry ecosystem. Breaching data or forging source devices after injecting advanced persistent threats (APT) damages the industry owners' money and loss of operators' lives. The existing challenges include APT injection attacks targeting vulnerable edge devices, insecure data transportation, trust inconsistencies among stakeholders, incompliant data storing mechanisms, etc. Edge-servers often suffer because of their lightweight…
