Biblio

Starting from our previous research where we in- troduced a general framework for supporting data-driven privacy-preserving big data management in distributed environments, such as emerging Cloud settings, in this paper we further and significantly extend our past research contributions, and provide several novel contributions that complement our previous work in the investigated research field. Our proposed framework can be viewed as an alternative to classical approaches where the privacy of big data is ensured via security-inspired protocols that check several (protocol) layers in order to achieve the desired privacy. Unfortunately, this injects considerable computational overheads in the overall process, thus introducing relevant challenges to be considered. Our approach instead tries to recognize the “pedigree” of suitable summary data representatives computed on top of the target big data repositories, hence avoiding computational overheads due to protocol checking. We also provide a relevant realization of the framework above, the so- called Data-dRIven aggregate-PROvenance privacy-preserving big Multidimensional data (DRIPROM) framework, which specifically considers multidimensional data as the case of interest. Extensions and discussion on main motivations and principles of our proposed research, two relevant case studies that clearly state the need-for and covered (related) properties of supporting privacy- preserving management and analytics of big data in modern distributed systems, and an experimental assessment and analysis of our proposed DRIPROM framework are the major results of this paper.

Big data of mobile network privacy is vulnerable to clear text attack in the process of storage and mixed network information sharing, which leads to information leakage. Through the mixed encryption of data of mobile network privacy big data to improve the confidentiality and security of mobile network privacy big data, a mobile network privacy big data hybrid encryption algorithm based on hyperchaos theory is proposed. The hybrid encryption key of mobile network privacy big data is constructed by using hyperchaotic nonlinear mapping hybrid encryption technology. Combined with the feature distribution of mobile network privacy big data, the mixed encrypted public key is designed by using Logistic hyperchaotic arrangement method, and a hyperchaotic analytic cipher and block cipher are constructed by using Rossle chaotic mapping. The random piecewise linear combination method is used to design the coding and key of mobile network privacy big data. According to the two-dimensional coding characteristics of mobile network privacy big data in the key authorization protocol, the hybrid encryption and decryption key of mobile network privacy big data is designed, and the mixed encryption and decryption key of mobile network privacy big data is constructed, Realize the privacy of mobile network big data mixed encryption output and key design. The simulation results show that this method has good confidentiality and strong steganography performance, which improves the anti-attack ability of big data, which is used to encrypt the privacy of mobile network.

Big data will bring revolutionary changes from life to thinking for society as a whole. At the same time, the massive data and potential value of big data are subject to many security risks. Aiming at the above problems, a data privacy protection model for big data platform is proposed. First, the data privacy protection model of big data for data owners is introduced in detail, including protocol design, logic design, complexity analysis and security analysis. Then, the query privacy protection model of big data for ordinary users is introduced in detail, including query protocol design and query mode design. Complexity analysis and safety analysis are performed. Finally, a stand-alone simulation experiment is built for the proposed privacy protection model. Experimental data is obtained and analyzed. The feasibility of the privacy protection model is verified.

Geocoding, the process of translating addresses to geographic coordinates, is a relatively straight-forward and well-studied process, but limitations due to privacy concerns may restrict usage of geographic data. The impact of these limitations are further compounded by the scale of the data, and in turn, also limits viable geocoding strategies. For example, healthcare data is protected by patient privacy laws in addition to possible institutional regulations that restrict external transmission and sharing of data. This results in the implementation of “in-house” geocoding solutions where data is processed behind an organization's firewall; quality assurance for these implementations is problematic because sensitive data cannot be used to externally validate results. In this paper, we present our software framework called bench4gis which benchmarks privacy-aware geocoding solutions by leveraging open big data as surrogate data for quality assurance; the scale of open big data sets for address data can ensure that results are geographically meaningful for the locale of the implementing institution.

Cloud-assisted Internet of Vehicles (IoV)which merges the advantages of both cloud computing and Internet of Things that can provide numerous online services, and bring lots of benefits and conveniences to the connected vehicles. However, the security and privacy issues such as confidentiality, access control and driver privacy may prevent it from being widely utilized for message dissemination. Existing attribute-based message encryption schemes still bring high computational cost to the lightweight vehicles. In this paper, we introduce a secure and privacy-preserving dissemination scheme for warning message in cloud-assisted IoV. Firstly, we adopt attribute-based encryption to protect the disseminated warning message, and present a verifiable encryption and decryption outsourcing construction to reduce the computational overhead on vehicles. Secondly, we present a conditional privacy preservation mechanism which utilizes anonymous identity-based signature technique to ensure anonymous vehicle authentication and message integrity checking, and also allows the trusted authority to trace the real identity of malicious vehicle. We further achieve batch verification to improve the authentication efficiency. The analysis indicate that our scheme gains more security properties and reduces the computational overhead on the vehicles.

Generative Adversarial Networks (GANs) are one of the well-known models to generate synthetic data including images, especially for research communities that cannot use original sensitive datasets because they are not publicly accessible. One of the main challenges in this area is to preserve the privacy of individuals who participate in the training of the GAN models. To address this challenge, we introduce a Differentially Private Conditional GAN (DP-CGAN) training framework based on a new clipping and perturbation strategy, which improves the performance of the model while preserving privacy of the training dataset. DP-CGAN generates both synthetic data and corresponding labels and leverages the recently introduced Renyi differential privacy accountant to track the spent privacy budget. The experimental results show that DP-CGAN can generate visually and empirically promising results on the MNIST dataset with a single-digit epsilon parameter in differential privacy.

Children and teenagers that have been a victim of bullying can possibly suffer its psychological effects for a lifetime. With the increase of online social media, cyberbullying incidents have been increased as well. In this paper we discuss how we can detect cyberbullying with AI techniques, using term frequency-inverse document frequency. We label messages as benign or bully. We want our method of cyberbullying detection to be privacy-preserving, such that the subscribers' benign messages should not be revealed to the operator. Moreover, the operator labels subscribers as normal, bully and victim. The operator utilizes policy control in 5G networks, to protect victims of cyberbullying from harmful traffic.

Machine Learning as a Service (MLaaS) is becoming a popular practice where Service Consumers, e.g., end-users, send their data to a ML Service and receive the prediction outputs. However, the emerging usage of MLaaS has raised severe privacy concerns about users' proprietary data. PrivacyPreserving Machine Learning (PPML) techniques aim to incorporate cryptographic primitives such as Homomorphic Encryption (HE) and Multi-Party Computation (MPC) into ML services to address privacy concerns from a technology standpoint. Existing PPML solutions have not been widely adopted in practice due to their assumed high overhead and integration difficulty within various ML front-end frameworks as well as hardware backends. In this work, we propose PlaidML-HE, the first end-toend HE compiler for PPML inference. Leveraging the capability of Domain-Specific Languages, PlaidML-HE enables automated generation of HE kernels across diverse types of devices. We evaluate the performance of PlaidML-HE on different ML kernels and demonstrate that PlaidML-HE greatly reduces the overhead of the HE primitive compared to the existing implementations.

The huge volume, variety, and velocity of big data have empowered Machine Learning (ML) techniques and Artificial Intelligence (AI) systems. However, the vast portion of data used to train AI systems is sensitive information. Hence, any vulnerability has a potentially disastrous impact on privacy aspects and security issues. Nevertheless, the increased demands for high-quality AI from governments and companies require the utilization of big data in the systems. Several studies have highlighted the threats of big data on different platforms and the countermeasures to reduce the risks caused by attacks. In this paper, we provide an overview of the existing threats which violate privacy aspects and security issues inflicted by big data as a primary driving force within the AI/ML workflow. We define an adversarial model to investigate the attacks. Additionally, we analyze and summarize the defense strategies and countermeasures of these attacks. Furthermore, due to the impact of AI systems in the market and the vast majority of business sectors, we also investigate Standards Developing Organizations (SDOs) that are actively involved in providing guidelines to protect the privacy and ensure the security of big data and AI systems. Our far-reaching goal is to bridge the research and standardization frame to increase the consistency and efficiency of AI systems developments guaranteeing customer satisfaction while transferring a high degree of trustworthiness.

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.

Different tools and sources are used to collect big data, which may create privacy issues. k-anonymity, l-diversity, t-closeness etc. privacy preserving data publishing approaches are used data de-identification, but as multiple sources is used to collect the data, chance of re-identification is very high. Anonymization large data is not a trivial task, hence, privacy preserving approaches scalability has become a challenging research area. Researchers explore it by proposing algorithms for scalable anonymization. We further found that in some scenarios efficient anonymization is not enough, timely anonymization is also required. Hence, to incorporate the velocity of data with Scalable k-Anonymization (SKA) approach, we propose a novel approach, Scalable ( α, k)-Anonymization (SAKA). Our proposed approach outperforms in terms of information loss and running time as compared to existing approaches. With best of our knowledge, this is the first proposed scalable anonymization approach for the velocity of data.

Artificial Intelligence (AI) can and does use individual's data to make predictions about their wants, their needs, their influences on them and predict what they could do. The use of individual's data naturally raises privacy concerns. This article focuses on AI, the privacy issue against the backdrop of the endless growth of the Digital Universe where Big Data, AI, Data Analytics and 5G Technology live and grow in The Internet of Things (IoT).

We aim at creating a society where we can resolve various social challenges by incorporating the innovations of the fourth industrial revolution (e.g. IoT, big data, AI, robot, and the sharing economy) into every industry and social life. By doing so the society of the future will be one in which new values and services are created continuously, making people's lives more conformable and sustainable. This is Society 5.0, a super-smart society. Security and privacy are key issues to be addressed to realize Society 5.0. Privacy-preserving data analytics will play an important role. In this talk we show our recent works on privacy-preserving data analytics such as privacy-preserving logistic regression and privacy-preserving deep learning. Finally, we show our ongoing research project under JST CREST “AI”. In this project we are developing privacy-preserving financial data analytics systems that can detect fraud with high security and accuracy. To validate the systems, we will perform demonstration tests with several financial institutions and solve the problems necessary for their implementation in the real world.

The edge and fog computing paradigms enable more responsive and smarter systems without relying on cloud servers for data processing and storage. This reduces network load as well as latency. Nonetheless, the addition of new layers in the network architecture increases the number of security vulnerabilities. In privacy-critical systems, the appearance of new vulnerabilities is more significant. To cope with this issue, we propose and implement an Ethereum Blockchain based architecture with edge artificial intelligence to analyze data at the edge of the network and keep track of the parties that access the results of the analysis, which are stored in distributed databases.

With the development of artificial intelligence (AI), multimedia privacy issues have become more challenging than ever. AI-assisted malicious entities can steal private information from multimedia data more easily than humans. Traditional multimedia privacy protection only considers the situation when humans are the adversaries, therefore they are ineffective against AI-assisted attackers. In this paper, we develop a new framework and new algorithms that can protect image privacy from both humans and AI. We combine the idea of adversarial image perturbation which is effective against AI and the obfuscation technique for human adversaries. Experiments show that our proposed methods work well for all types of attackers.

The cyber-physical systems (CPSes) rely on computing and control techniques to achieve system safety and reliability. However, recent attacks show that these techniques are vulnerable once the cyber-attackers have bypassed air gaps. The attacks may cause service disruptions or even physical damages. This paper designs the built-in attack characterization scheme for one general type of cyber-attacks in CPS, which we call time delay attack, that delays the transmission of the system control commands. We use the recurrent neural networks in deep learning to estimate the delay values from the input trace. Specifically, to deal with the long time-sequence data, we design the deep learning model using stacked bidirectional long short-term memory (LSTM) units. The proposed approach is tested by using the data generated from a power plant control system. The results show that the LSTM-based deep learning approach can work well based on data traces from three sensor measurements, i.e., temperature, pressure, and power generation, in the power plant control system. Moreover, we show that the proposed approach outperforms the base approach based on k-nearest neighbors.

Computer worms pose a major threat to computer and communication networks due to the rapid speed at which they propagate. Biologically based epidemic models have been widely used to analyze the propagation of worms in computer networks. For an air-gapped network with an insider threat, we propose a modified Susceptible-Exposed-Infected-Quarantined-Vaccinated (SEIQV) model called the Susceptible-Exposed-Infected-Quarantined-Patched (SEIQP) model. We describe the assumptions that apply to this model, define a set of differential equations that characterize the system dynamics, and solve for the basic reproduction number. We then simulate and analyze the parameters controlled by the insider threat to determine where resources should be allocated to attain different objectives and results.

Air-gapped computers are systems that are kept isolated from the Internet since they store or process sensitive information. In this paper, we introduce an optical covert channel in which an attacker can leak (or, exfiltlrate) sensitive information from air-gapped computers through manipulations on the screen brightness. This covert channel is invisible and it works even while the user is working on the computer. Malware on a compromised computer can obtain sensitive data (e.g., files, images, encryption keys and passwords), and modulate it within the screen brightness, invisible to users. The small changes in the brightness are invisible to humans but can be recovered from video streams taken by cameras such as a local security camera, smartphone camera or a webcam. We present related work and discuss the technical and scientific background of this covert channel. We examined the channel's boundaries under various parameters, with different types of computer and TV screens, and at several distances. We also tested different types of camera receivers to demonstrate the covert channel. Lastly, we present relevant countermeasures to this type of attack.

Using the keyboard LEDs to send data optically was proposed in 2002 by Loughry and Umphress [1] (Appendix A). In this paper we extensively explore this threat in the context of a modern cyber-attack with current hardware and optical equipment. In this type of attack, an advanced persistent threat (APT) uses the keyboard LEDs (Caps-Lock, Num-Lock and Scroll-Lock) to encode information and exfiltrate data from airgapped computers optically. Notably, this exfiltration channel is not monitored by existing data leakage prevention (DLP) systems. We examine this attack and its boundaries for today's keyboards with USB controllers and sensitive optical sensors. We also introduce smartphone and smartwatch cameras as components of malicious insider and 'evil maid' attacks. We provide the necessary scientific background on optical communication and the characteristics of modern USB keyboards at the hardware and software level, and present a transmission protocol and modulation schemes. We implement the exfiltration malware, discuss its design and implementation issues, and evaluate it with different types of keyboards. We also test various receivers, including light sensors, remote cameras, 'extreme' cameras, security cameras, and smartphone cameras. Our experiment shows that data can be leaked from air-gapped computers via the keyboard LEDs at a maximum bit rate of 3000 bit/sec per LED given a light sensor as a receiver, and more than 120 bit/sec if smartphones are used. The attack doesn't require any modification of the keyboard at hardware or firmware levels.

In this paper we consider the threat surface and security of air gapped wallet schemes for permissioned blockchains as preparation for a Markov based mathematical model, and quantify the risk associated with private key leakage. We identify existing threats to the wallet scheme and existing work done to both attack and secure the scheme. We provide an overview the proposed model and outline justification for our methods. We follow with next steps in our remaining work and the overarching goals and motivation for our methods.

Air-gapped computers are hermetically isolated from the Internet to eliminate any means of information leakage. In this paper we present HOTSPOT - a new type of airgap crossing technique. Signals can be sent secretly from air-gapped computers to nearby smartphones and then on to the Internet - in the form of thermal pings. The thermal signals are generated by the CPUs and GPUs and intercepted by a nearby smartphone. We examine this covert channel and discuss other work in the field of air-gap covert communication channels. We present technical background and describe thermal sensing in modern smartphones. We implement a transmitter on the computer side and a receiver Android App on the smartphone side, and discuss the implementation details. We evaluate the covert channel and tested it in a typical work place. Our results show that it possible to send covert signals from air-gapped PCs to the attacker on the Internet through the thermal pings. We also propose countermeasures for this type of covert channel which has thus far been overlooked.

In this paper we consider the threat surface and security of air gapped wallet schemes for permissioned blockchains as preparation for a Markov based mathematical model, and quantify the risk associated with private key leakage. We identify existing threats to the wallet scheme and existing work done to both attack and secure the scheme. We provide an overview the proposed model and outline justification for our methods. We follow with next steps in our remaining work and the overarching goals and motivation for our methods.

Air-gap attacks and mimic defense are two emerging techniques in the field of network attack and defense, respectively. However, direct confrontation between them has not yet appeared in the real world. Who will be the winner, if air-gap attacks encounter mimic defense? To this end, a preliminary analysis is conducted for exploring the possible the strategy space of game according to the core principles of air-gap attacks and mimic defense. On this basis, an architecture model is proposed, which combines some detectors for air-gap attacks and mimic defense devices. First, a Dynamic Heterogeneous Redundancy (DHR) structure is employed to be on guard against malicious software of air-gap attacks. Second, some detectors for air-gap attacks are used to detect some signal sent by air-gap attackers' transmitter. Third, the proposed architecture model is obtained by organizing the DHR structure and the detectors for air-gap attacks with some logical relationship. The simulated experimental results preliminarily confirm the power of the new model.

This paper addresses the fundamental problem of identifying driver talking directions using a single smartphone, which can help drivers by warning distraction of having conversations with passengers in a vehicle and enable safety enhancement. The basic idea of our system is to perform talking status and direction identification using two microphones on a smartphone. We first use the sound recorded by the two microphones to identify whether the driver is talking or not. If yes, we then extract the so-called channel fingerprint from the speech signal and classify it into one of three typical driver talking directions, namely, front, right and back, using a trained model obtained in advance. The key novelty of our scheme is the proposition of channel fingerprint which leverages the heavy multipath effects in the harsh in-vehicle environment and cancels the variability of human voice, both of which combine to invalidate traditional TDoA, DoA and fingerprint based sound source localization approaches. We conducted extensive experiments using two kinds of phones and two vehicles for four phone placements in three representative scenarios, and collected 23 hours voice data from 20 participants. The results show that our system can achieve 95.0% classification accuracy on average.

Location sharing applications are becoming increasingly common. These applications allow users to share their own locations and view contacts’ current locations on a map. Location applications are commonly used by friends and family members to view Global Positioning System (GPS) location of an individual, but valuable forensic evidence may exist in this data when stored locally on smartphones. This paper aims to discover forensic artifacts from two popular third-party location sharing applications on iOS and Android devices. Industry standard mobile forensic suites are utilized to discover if any locally stored data could be used to assist investigations reliant on knowing the past location of a suspect. Security issues raised regarding the artifacts found during our analysis is also discussed.