Biblio

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.

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.

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.

Machine learning (ML) applications are increasingly prevalent. Protecting the confidentiality of ML models becomes paramount for two reasons: (a) a model can be a business advantage to its owner, and (b) an adversary may use a stolen model to find transferable adversarial examples that can evade classification by the original model. Access to the model can be restricted to be only via well-defined prediction APIs. Nevertheless, prediction APIs still provide enough information to allow an adversary to mount model extraction attacks by sending repeated queries via the prediction API. In this paper, we describe new model extraction attacks using novel approaches for generating synthetic queries, and optimizing training hyperparameters. Our attacks outperform state-of-the-art model extraction in terms of transferability of both targeted and non-targeted adversarial examples (up to +29-44 percentage points, pp), and prediction accuracy (up to +46 pp) on two datasets. We provide take-aways on how to perform effective model extraction attacks. We then propose PRADA, the first step towards generic and effective detection of DNN model extraction attacks. It analyzes the distribution of consecutive API queries and raises an alarm when this distribution deviates from benign behavior. We show that PRADA can detect all prior model extraction attacks with no false positives.

The traditional network used today is unable to meet the increasing needs of technology in terms of management, scaling, and performance criteria. Major developments in information and communication technologies show that the traditional network structure is quite lacking in meeting the current requirements. In order to solve these problems, Software Defined Network (SDN) is capable of responding as it, is flexible, easier to manage and offers a new structure. Software Defined Networks have many advantages over traditional network structure. However, it also brings along many security threats due to its new architecture. For example, the DoS attack, which overloads the controller's processing and communication capacity in the SDN structure, is a significant threat. Mobile Ad Hoc Network (MANET), which is one of the wireless network technologies, is different from SDN technology. MANET is exposed to various attacks such as DoS due to its security vulnerabilities. The aim of the study is to reveal the security problems in SDN structure presented with a new understanding. This is based on the currently used network structures such as MANET. The study consists of two parts. First, DoS attacks against the SDN controller were performed. Different SDN controllers were used for more accurate results. Second, MANET was established and DoS attacks against this network were performed. Different MANET routing protocols were used for more accurate results. According to the scenario, attacks were performed and the performance values of the networks were tested. The reason for using two different networks in this study is to compare the performance values of these networks at the time of attack. According to the test results, both networks were adversely affected by the attacks. It was observed that network performance decreased in MANET structure but there was no network interruption. The SDN controller becomes dysfunctional and collapses as a result of the attack. While the innovations offered by the SDN structure are expected to provide solutions to many problems in traditional networks, there are still many vulnerabilities for network security.

UAANET (UAV Ad hoc Network) is defined as an autonomous system made of swarm of UAVs (Unmanned Aerial Vehicle) and GCS (Ground Control Station). Compared to other types of MANET (Mobile Ad hoc network), UAANET have some unique features and bring several challenges. One of them is the design of routing protocol. It must be efficient for creating routes between nodes and dynamically adjusting to the rapidly changing topology. It must also be secure to protect the integrity of the network against malicious attackers. In this paper, we will present the architecture and the performance evaluation (based on both real-life experimental and emulation studies) of a secure routing protocol called SUAP (Secure UAV Ad hoc routing Protocol). SUAP ensures routing services between nodes to exchange real-time traffic and also guarantees message authentication and integrity to protect the network integrity. Additional security mechanisms were added to detect Wormhole attacks. Wormhole attacks represent a high level of risk for UAV ad hoc network and this is the reason why we choose to focus on this specific multi node attack. Through performance evaluation campaign, our results show that SUAP ensures the expected security services against different types of attacks while providing an acceptable quality of service for real-time data exchanges.

Biometric recognition systems based on ultrasound images have been investigated for several decades, and nowadays ultrasonic fingerprint sensors are fully integrated in portable devices. Main advantage of the Ultrasound over other technologies are the possibility to collect 3D images, allowing to gain information on under-skin features, which improve recognition accuracy and resistance to spoofing. Also, ultrasound images are not sensible to several skin contaminations, humidity and not uniform ambient illumination. An ultrasound system, able to acquire 3D images of the human palm has been recently proposed. In this work, a recognition procedure based on 2D palmprint images collected with this system is proposed and evaluated through verification experiments carried out on a home made database composed of 141 samples collected from 24 users. Perspective of the proposed method by upgrading the recognition procedure to provide a 3D template able to accounts for palm lines' depth are finally highlighted and discussed.

While enjoying the convenience brought by mobile phones, users have been exposed to high risk of private information leakage. It is known that many applications on mobile devices read private data and send them to remote servers. However how, when and in what scale the private data are leaked are not investigated systematically in the real-world scenario. In this paper, a framework is proposed to analyze the usage data from mobile devices and the traffic data from the mobile network and make a comprehensive privacy leakage detection and privacy inference mining on a large scale of realworld mobile data. Firstly, this paper sets up a training dataset and trains a privacy detection model on mobile traffic data. Then classical machine learning tools are used to discover private usage patterns. Based on our experiments and data analysis, it is found that i) a large number of private information is transmitted in plaintext, and even passwords are transmitted in plaintext by some applications, ii) more privacy types are leaked in Android than iOS, while GPS location is the most leaked privacy in both Android and iOS system, iii) the usage pattern is related to mobile device price. Through our experiments and analysis, it can be concluded that mobile privacy leakage is pervasive and serious.

As digital microfluidic biochips (DMFBs) make the transition to the marketplace for commercial exploitation, security and intellectual property (IP) protection are emerging as important design considerations. Recent studies have shown that DMFBs are vulnerable to reverse engineering aimed at stealing biomolecular protocols (IP theft). The IP piracy of proprietary protocols may lead to significant losses for pharmaceutical and biotech companies. The micro-electrode-dot-array (MEDA) is a next-generation DMFB platform that supports real-time sensing of droplets and has the added advantage of important security protections. However, real-time sensing offers opportunities to an attacker to steal the biochemical IP. We show that the daisychaining of microelectrodes and the use of one-time-programmability in MEDA biochips provides effective bitstream scrambling of biochemical protocols. To examine the strength of this solution, we develop a SAT attack that can unscramble the bitstreams through repeated observations of bioassays executed on the MEDA platform. Based on insights gained from the SAT attack, we propose an advanced defense against IP theft. Simulation results using real-life biomolecular protocols confirm that while the SAT attack is effective for simple instances, our advanced defense can thwart it for realistic MEDA biochips and real-life protocols.

Diagnostic research methods were designed to draw attention to the needs of future engineers in the field of innovative methods of acquiring knowledge, skills and competencies in the protection of intellectual property in order to prepare for functioning in the economy 4.0.

Recently in the vast advancement of Artificial Intelligence, Machine learning and Deep Neural Network (DNN) driven us to the robust applications. Such as Image processing, speech recognition, and natural language processing, DNN Algorithms has succeeded in many drawbacks; especially the trained DNN models have made easy to the researchers to produces state-of-art results. However, sharing these trained models are always a challenging task, i.e. security, and protection. We performed extensive experiments to present some analysis of watermark in DNN. We proposed a DNN model for Digital watermarking which investigate the intellectual property of Deep Neural Network, Embedding watermarks, and owner verification. This model can generate the watermarks to deal with possible attacks (fine tuning and train to embed). This approach is tested on the standard dataset. Hence this model is robust to above counter-watermark attacks. Our model accurately and instantly verifies the ownership of all the remotely expanded deep learning models without affecting the model accuracy for standard information data.

Increased use of secure chat and voice/ video apps has transformed the social life. While the benefits and facilitations are seemingly limitless, so are the asscoiacted vulnerabilities and threats. Besides ensuring confidentiality requirements for common users, known facts of non-readable contents over the network make these apps more attractive for criminals. Though access to contents of cryptograhically secure sessions is not possible, network forensics of secure apps can provide interesting information which can be of great help during criminal invetigations. In this paper, we presented a novel framework of profiling the secure chat and voice/ video calling apps which can be employed to extract hidden patterns about the app, information of involved parties, activities of chatting, voice/ video calls, status indications and notifications while having no information of communication protocol of the app and its security architecture. Signatures of any secure app can be developed though our framework and can become base of a large scale solution. Our methodology is considered very important for different cases of criminal investigations and bussiness intelligence solutions for service provider networks. Our results are applicable to any mobile platform of iOS, android and windows.

In this contemporary world, working on internet is a crucial task owing to the security threats in the network like intrusions, injections etc. To recognize and reduce these system attacks, analysts and academicians have introduced Intrusion Detection Systems (IDSs) with the various standards and applications. There are different types of Intrusion Detection Systems (IDS) arise to solve the attacks in various environments. Though IDS is more powerful, it produces the results on the abnormal behaviours said to be attacks with false positive and false negative rates which leads to inaccurate detection rate. The other problem is that, there are more number of attacks arising simultaneously with different behaviour being detected by the IDS with high false positive rates which spoils the strength and lifetime of the system, system's efficiency and fault tolerance. Complex Event Processing (CEP) plays a vital role in handling the alerts as events in real time environment which mainly helps to recognize and reduce the redundant alerts.CEP identifies and analyses relationships between events in real time, allowing the system to proactively take efficient actions to respond to specific alerts.In this study, the tendency of Complex Event Processing (CEP) over Intrusion Detection System (IDS) which offers effective handling of the alerts received from IDS in real time and the promotion of the better detection of the attacks are discussed. The merits and challenges of CEP over IDS described in this paper helps to understand and educate the IDS systems to focus on how to tackle the dynamic attacks and its alerts in real time.

In the information era, the size of network traffic is complex because of massive Internet-based services and rapid amounts of data. The more network traffic has enhanced, the more cyberattacks have dramatically increased. Therefore, cybersecurity intrusion detection has been a challenge in the current research area in recent years. The Intrusion detection system requires high-level protection and detects modern and complex attacks with more accuracy. Nowadays, big data analytics is the main key to solve marketing, security and privacy in an extremely competitive financial market and government. If a huge amount of stream data flows within a short period time, it is difficult to analyze real-time decision making. Performance analysis is extremely important for administrators and developers to avoid bottlenecks. The paper aims to reduce time-consuming by using Apache Kafka and Spark Streaming. Experiments on the UNSWNB-15 dataset indicate that the integration of Apache Kafka and Spark Streaming can perform better in terms of processing time and fault-tolerance on the huge amount of data. According to the results, the fault tolerance can be provided by the multiple brokers of Kafka and parallel recovery of Spark Streaming. And then, the multiple partitions of Apache Kafka increase the processing time in the integration of Apache Kafka and Spark Streaming.

In this paper, we consider a stochastic model to evaluate the system availability of an intrusion tolerant system (ITS), where the system undergoes the patch management with a periodic vulnerability checking strategy, i.e., a pull-type patch management. Based on the model, this paper discusses the appropriate timing for patch applying. In particular, the paper models the attack behavior of adversary and the system behaviors under reactive defense strategies by a composite stochastic reward net (SRN). Furthermore, we formulate the interval availability by applying the phase-type (PH) approximation to solve the Markov regenerative process (MRGP) models derived from the SRNs. Numerical experiments are conducted to study the sensitivity of the system availability with respect to the number of checking.

Technology development has led to rapid increase in demands for multimedia applications. Due to this demand, digital archives are increasingly used to store these multimedia contents. Cloud is the commonly used archive to store, transmit, receive and share multimedia contents. Cloud makes use of internet to perform these tasks due to which data becomes more prone to attacks. Data security and privacy are compromised. This can be avoided by limiting data access to authenticated users and by hiding the data from cloud services that cannot be trusted. Hiding data from the cloud services involves encrypting the data before storing it into the cloud. Data to be shared with other users can be encrypted by utilizing Cipher Text-Policy Attribute Based Encryption (CP-ABE). CP-ABE is used which is a cryptographic technique that controls access to the encrypted data. The pairing-based computation based on bilinearity is used in ABE due to which the requirements for resources like memory and power supply increases rapidly. Most of the devices that we use today have limited memory. Therefore, an efficient pairing free CP- ABE access control scheme using elliptic curve cryptography has been used. Pairing based computation is replaced with scalar product on elliptic curves that reduces the necessary memory and resource requirements for the users. Even though pairing free CP-ABE is used, it is easier to retrieve the plaintext of a secret message if cryptanalysis is used. Therefore, this paper proposes to combine cryptography with steganography in such a way by embedding crypto text into an image to provide increased level of data security and data ownership for sub-optimal multimedia applications. It makes it harder for a cryptanalyst to retrieve the plaintext of a secret message from a stego-object if steganalysis were not used. This scheme significantly improved the data security as well as data privacy.

White-box cryptography protects cryptographic software in a white-box attack context (WBAC), where the dynamic execution of the cryptographic software is under full control of an adversary. Protecting AES in the white-box setting attracted many scientists and engineers, and several solutions emerged. However, almost all these solutions have been badly broken by various efficient white-box attacks, which target compositions of key-embedding lookup tables. In 2014, Luo, Lai, and You proposed a new WBAC-oriented AES implementation, and claimed that their implementation is secure against both Billet et al.'s attack and De Mulder et al.'s attack. In this study, based on the existing table-composition-targeting cryptanalysis techniques, the authors show that the secret key of the Luo-Lai-You (LLY) implementation can be recovered with a time complexity of about 244. Furthermore, the authors propose a new white-box AES implementation based on table lookups, which is shown to be resistant against the existing table-composition-targeting white-box attacks. The authors, key-embedding tables are obfuscated with large affine mappings, which cannot be cancelled out by table compositions of the existing cryptanalysis techniques. Although their implementation requires twice as much memory as the LLY WBAES to store the tables, its speed is about 63 times of the latter.

Conversational systems are computer programs that interact with users using natural language. Considering the complexity and interaction of the different components involved in building intelligent conversational systems that can perform diverse tasks, a promising approach to facilitate their development is by using multiagent systems (MAS). This paper reviews the main concepts and history of conversational systems, and introduces an architecture based on MAS. This architecture was designed to support the development of conversational systems in the domain chosen by the developer while also providing a reusable built-in dialogue control. We present a practical application in the healthcare domain. We observed that it can help developers to create conversational systems in different domains while providing a reusable and centralized dialogue control. We also present derived lessons learned that can be helpful to steer future research on engineering domain-specific conversational systems.

To be able to meet demanding application performance requirements within a tight power budget, runtime power management must track hardware activity at a very fine granularity in both space and time. This gives rise to sophisticated power management algorithms, which need the underlying system to be both highly observable (to be able to sense changes in instantaneous power demand timely) and controllable (to be able to react to changes in instantaneous power demand timely). The end goal is allocating the power budget, which itself represents a very critical shared resource, in a fair way among active tasks of execution. Fundamentally, if not carefully managed, any system-wide shared resource can give rise to covert communication. Power budget does not represent an exception, particularly as systems are becoming more and more observable and controllable. In this paper, we demonstrate how power management vulnerabilities can enable covert communication over a previously unexplored, novel class of covert channels which we will refer to as POWERT channels. We also provide a comprehensive characterization of the POWERT channel capacity under various sharing and activity scenarios. Our analysis based on experiments on representative commercial systems reveal a peak channel capacity of 121.6 bits per second (bps).

Network covert channels are used in various cyberattacks, including disclosure of sensitive information and enabling stealth tunnels for botnet commands. With time and technology, covert channels are becoming more prevalent, complex, and difficult to detect. The current methods for detection are protocol and pattern specific. This requires the investment of significant time and resources into application of various techniques to catch the different types of covert channels. This paper reviews several patterns of network storage covert channels, describes generation of network traffic dataset with covert channels, and proposes a generic, protocol-independent approach for the detection of network storage covert channels using a supervised machine learning technique. The implementation of the proposed generic detection model can lead to a reduction of necessary techniques to prevent covert channel communication in network traffic. The datasets we have generated for experimentation represent storage covert channels in the IP, TCP, and DNS protocols and are available upon request for future research in this area.

Loss of field (LOF) relay, with ANSI code 40, is one of the most important protection functions for synchronous generators in power plants. Although many LOF protection schemes have been presented in the literature during the last decades, a few numbers of them such as impedance and admittance based schemes are accepted by the industry. This paper explores and compares the performances of some industrial LOF protection schemes through simulation studies and from speed, reliability and security viewpoints. The simulation studies are carried out in the real-time-digital-simulator, where a realistic power generation unit is developed by employing the phase domain model of synchronous generator. Using such a realistic system, various types of LOF events can be simulated in accordance with IEEE Standard C37.102-2006, so that the performance of any method can be evaluated through careful LOF studies.

Variable N-parallel code-shift-keying (VN-CSK) system has been proposed for solving the dimming control problem and the adjacent illumination light interference in illumination light communication. VN-CSK system only focuses on separating the light signal in the illumination light overlapping area. While, it is considerable to transmit a new data using the light overlapping. Visual secret sharing (VSS) scheme is a kind of secret sharing scheme, which distributes the secret data for security and restore by overlapping. It has high affinity to visible light communication. In this paper, a system combined with visible light communication and (2,2)-VSS scheme is proposed. In the proposed system, a modified pseudo orthogonal M-sequence is used that the occurrence probability of 0 and 1 of share is one-half in order to achieve a constant illuminance. In addition, this system use Modified Pseudo-Orthogonal M-sequence(MPOM) for ensuring the lighting function. The bit error rate performance of the proposed system is evaluated under the indoor visible light communication channel by simulation.

Visible light communication (VLC) is a burgeoning field in wireless communications as it considers illumination and communication simultaneously. The broadcast nature of VLC makes it necessary to consider the security of underlying transmissions. A physical-layer security (PLS) scheme by introducing jamming LEDs is considered in this paper. The secrecy rate of an indoor VLC system with multiple LEDs, one legitimate receiver, and multiple eavesdroppers is investigated. Three distributions of input signal are assumed, i.e., truncated generalized normal distribution (TGN), uniform distribution, and exponential distribution. The results show that jamming can improve the secrecy performance efficiently. This paper also demonstrates that when the numbers of LEDs transmitting information-bearing signal and jamming signal are equal, the average secrecy rate can be maximized.