Usually, a proof of a theorem contains more knowledge than the mere fact that the theorem is true. For instance, to prove that a graph is Hamiltonian it suffices to exhibit a Hamiltonian tour in it; however, this seems to contain more knowledge than the single bit Hamiltonian/non-Hamiltonian.In this paper a computational complexity theory of the “knowledge” contained in a proof is developed. Zero-knowledge proofs are defined as those proofs that convey no additional knowledge other than the correctness of the proposition in question. Examples of zero-knowledge proof systems are given for the languages of quadratic residuosity and 'quadratic nonresiduosity. These are the first examples of zero-knowledge proofs for languages not known to be efficiently recognizable.

/pdf/the-knowledge-complexity-of-interactive-proof-systems-31apre0ecf.pdf

The knowledge complexity of interactive proof-systems

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

The paradigm of Internet of Things (IoT) is paving the way for a world, where many of our daily objects will be interconnected and will interact with their environment in order to collect information and automate certain tasks. Such a vision requires, among other things, seamless authentication, data privacy, security, robustness against attacks, easy deployment, and self-maintenance. Such features can be brought by blockchain, a technology born with a cryptocurrency called Bitcoin. In this paper, a thorough review on how to adapt blockchain to the specific needs of IoT in order to develop Blockchain-based IoT (BIoT) applications is presented. After describing the basics of blockchain, the most relevant BIoT applications are described with the objective of emphasizing how blockchain can impact traditional cloud-centered IoT applications. Then, the current challenges and possible optimizations are detailed regarding many aspects that affect the design, development, and deployment of a BIoT application. Finally, some recommendations are enumerated with the aim of guiding future BIoT researchers and developers on some of the issues that will have to be tackled before deploying the next generation of BIoT applications.

A Review on the Use of Blockchain for the Internet of Things

Ubiquitous sensors and smart devices from factories and communities are generating massive amounts of data, and ever-increasing computing power is driving the core of computation and services from the cloud to the edge of the network. As an important enabler broadly changing people’s lives, from face recognition to ambitious smart factories and cities, developments of artificial intelligence (especially deep learning, DL) based applications and services are thriving. However, due to efficiency and latency issues, the current cloud computing service architecture hinders the vision of “providing artificial intelligence for every person and every organization at everywhere”. Thus, unleashing DL services using resources at the network edge near the data sources has emerged as a desirable solution. Therefore, edge intelligence , aiming to facilitate the deployment of DL services by edge computing, has received significant attention. In addition, DL, as the representative technique of artificial intelligence, can be integrated into edge computing frameworks to build intelligent edge for dynamic, adaptive edge maintenance and management. With regard to mutually beneficial edge intelligence and intelligent edge , this paper introduces and discusses: 1) the application scenarios of both; 2) the practical implementation methods and enabling technologies, namely DL training and inference in the customized edge computing framework; 3) challenges and future trends of more pervasive and fine-grained intelligence. We believe that by consolidating information scattered across the communication, networking, and DL areas, this survey can help readers to understand the connections between enabling technologies while promoting further discussions on the fusion of edge intelligence and intelligent edge , i.e., Edge DL.

Convergence of Edge Computing and Deep Learning: A Comprehensive Survey

Reinforcement learning (RL) algorithms have been around for decades and employed to solve various sequential decision-making problems. These algorithms, however, have faced great challenges when dealing with high-dimensional environments. The recent development of deep learning has enabled RL methods to drive optimal policies for sophisticated and capable agents, which can perform efficiently in these challenging environments. This article addresses an important aspect of deep RL related to situations that require multiple agents to communicate and cooperate to solve complex tasks. A survey of different approaches to problems related to multiagent deep RL (MADRL) is presented, including nonstationarity, partial observability, continuous state and action spaces, multiagent training schemes, and multiagent transfer learning. The merits and demerits of the reviewed methods will be analyzed and discussed with their corresponding applications explored. It is envisaged that this review provides insights about various MADRL methods and can lead to the future development of more robust and highly useful multiagent learning methods for solving real-world problems.

Deep Reinforcement Learning for Multiagent Systems: A Review of Challenges, Solutions, and Applications

Recent advances in combining deep neural network architectures with reinforcement learning (RL) techniques have shown promising potential results in solving complex control problems with high-dimensional state and action spaces. Inspired by these successes, in this study, the authors built two kinds of RL algorithms: deep policy-gradient (PG) and value-function-based agents which can predict the best possible traffic signal for a traffic intersection. At each time step, these adaptive traffic light control agents receive a snapshot of the current state of a graphical traffic simulator and produce control signals. The PG-based agent maps its observation directly to the control signal; however, the value-function-based agent first estimates values for all legal control signals. The agent then selects the optimal control action with the highest value. Their methods show promising results in a traffic network simulated in the simulation of urban mobility traffic simulator, without suffering from instability issues during the training process.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-its.2017.0153

Traffic light control using deep policy-gradient and value-function-based reinforcement learning

In recent years, a specific machine learning method called deep learning has gained huge attraction, as it has obtained astonishing results in broad applications such as pattern recognition, speech recognition, computer vision, and natural language processing. Recent research has also been shown that deep learning techniques can be combined with reinforcement learning methods to learn useful representations for the problems with high dimensional raw data input. This article reviews the recent advances in deep reinforcement learning with focus on the most used deep architectures such as autoencoders, convolutional neural networks and recurrent neural networks which have successfully been come together with the reinforcement learning framework.

Deep Reinforcement Learning: An Overview

In recent years, a specific machine learning method called deep learning has gained huge attraction, as it has obtained astonishing results in broad applications such as pattern recognition, speech recognition, computer vision, and natural language processing. Recent research has also been shown that deep learning techniques can be combined with reinforcement learning methods to learn useful representations for the problems with high dimensional raw data input. This chapter reviews the recent advances in deep reinforcement learning with a focus on the most used deep architectures such as autoencoders, convolutional neural networks and recurrent neural networks which have successfully been come together with the reinforcement learning framework.

The use of machine learning techniques has been proven to be a viable solution for smart home energy management. These techniques autonomously control heating and domestic hot water systems, which are the most relevant loads in a dwelling, helping consumers to reduce energy consumption and also improving their comfort. Moreover, the number of houses equipped with renewable energy resources is increasing, and this is a key element for energy usage optimization, where coordinating loads and production can bring additional savings and reduce peak loads. In this regard, we propose the development of a deep reinforcement learning (DRL) algorithm for indoor and domestic hot water temperature control, aiming to reduce energy consumption by optimizing the usage of PV energy production. Furthermore, a methodology for a new dynamic indoor temperature setpoint definition is presented, thus allowing greater flexibility and savings. The results show that the proposed DRL algorithm combined with the dynamic setpoint achieved on average 8% of energy savings compared to a rule-based algorithm, reaching up to 16% of savings over the summer period. Moreover, the users’ comfort has not been compromised, as the algorithm is calibrated to not exceed more than 1% of the time out the specified temperature setpoints. Additional analysis shows that further savings could be achieved if the time out of comfort is increased, which could be agreed according to users’ needs. Regarding demand side management, the DRL control shows efficiency by anticipating and delaying actions for a PV self-consumption optimization, performing over 10% of load shifting. Finally, the renewable energy consumption is 9.5% higher for the DRL-based model compared to the rule-based, which means less energy consumed from the grid.

Deep reinforcement learning for home energy management system control

Wireless Personal Area Networks (WPAN) allow for the implementation of applications such as home automation, remote control services, near-field technologies and personal health care management. Security is a critical requirement of the standards and protocols for these environments. One suite of layered protocols within WPAN is ZigBee. ZigBee is a low bit rate protocol utilised in Wireless Sensor Networks (WSN). Attacks such as physical, crypto key interception, injection and replay are perpetrated on ZigBee networks. These attacks can be instigated and controlled within the physical ZigBee WSN location or via a gateway. This paper creates a honeypot that simulates a ZigBee gateway. It is designed to assess the presence of ZigBee attack intelligence on a SSH attack vector. It captures all attack traffic for retrospective analysis. It sandboxes attacks of interest to determine if any attempts are targeting ZigBee specifically. Finally it concludes that all captured mass attacks are mainstream DDoS and bot malware, whereas individual attackers where attracted to and interacted with the ZigBee simulated Honeypot.

Michael Schukat

Papers

Traffic light control using deep policy-gradient and value-function-based reinforcement learning

Deep Reinforcement Learning: An Overview

Deep Reinforcement Learning: An Overview

Deep reinforcement learning for home energy management system control

A ZigBee honeypot to assess IoT cyberattack behaviour