Nowadays, embedded systems have been widely used in all types of application areas, some of which belong to the safety and reliability critical domains. The functional correctness and design robustness of the embedded systems involved in such domains are crucial for the safety of personal/enterprise property or even human lives. Thereby, a holistic design procedure that considers all the important design concerns is essential. In this article, we approach embedded systems design from an integral perspective. We consider not only the classic real-time and quality of service requirements, but also the emerging security and power efficiency demands. Modern embedded systems are not any more developed for a fixed purpose, but instead designed for undertaking various processing requests. This leads to the concept of multimode embedded systems, in which the number and nature of active tasks change during runtime. Under dynamic situations, providing high performance along with various design concerns becomes a really difficult problem. Therefore, we propose a novel power-aware secure embedded systems design framework that efficiently solves the problem of runtime quality optimization with security and power constraints. The efficiency of our proposed techniques are evaluated in extensive experiments.

Embedded systems (ESs) have been widely used in various application domains. It is very important to design ESs that guarantee functional correctness of the system under strict timing constraints. Such systems are known as the real-time embedded systems (RTESs). More recently, RTESs started to be utilized in safety and reliability critical areas, which made the overlooked security issues, especially confidentiality of the communication, a serious problem. Differential power analysis attacks (DPAs) pose serious threats to confidentiality protection mechanisms, i.e., implementations of cryptographic algorithms, on embedded platforms. In this work, we present a scheduling policy, SPARTA, that thwarts DPAs. Theoretical guarantees and preliminary experimental results are presented to demonstrate the efficiency of the SPARTA scheduler.

Designing energy-efficient applications has become of critical importance for embedded systems, especially for battery-powered systems. Additionally, the emerging requirements on both security and real-time make it much more difficult to produce ideal solutions. In this work, we address the emerging scheduling problem existed in the design of secure and energy-efficient real-time embedded systems. The objective is to minimize the system energy consumption subject to security and schedulability constraints. Due to the complexity of the problem, we propose a dynamic programming based approximation approach to find efficient solutions under given constraints. The proposed technique has polynomial time complexity which is half of existing approximation approaches. The efficiency of our algorithm is validated by extensive experiments and a real-life case study. Comparing with other approaches, the proposed approach achieves energy-saving up to 37.6% without violating the real-time and security constraints of the system.

Real-time embedded systems (RTESs) have been widely used in modern society. And it is also very common to find them in safety and security critical applications, such as transportation and medical equipment. There are, usually, several constraints imposed on a RTES, for example, timing, resource, energy, and performance, which must be satisfied simultaneously. This makes the design of such systems a difficult problem.

More recently, the security of RTESs emerges as a major design concern, as more and more attacks have been reported. However, RTES security, as a parameter to be considered during the design process, has been overlooked in the past. This thesis approaches the design of secure RTESs focusing on aspects that are particularly important in the context of RTES, such as communication confidentiality and side-channel attack resistance.

Several techniques are presented in this thesis for designing secure RTESs, including hardware/software co-design techniques for communication confidentiality on distributed platforms, a global framework for secure multi-mode real-time systems, and a scheduling policy for thwarting differential power analysis attacks. 

All the proposed solutions have been extensively evaluated in a large amount of experiments, including two real-life case studies, which demonstrate the efficiency of the presented techniques.

In this work, we address the emerging scheduling problem existed in the design of secure and energy-efficient real-time embedded systems. The objective is to minimize the energy consumption subject to security and schedulability constraints. Due to the complexity of the problem, we propose a dynamic programming based approximation approach to find the near-optimal solutions with respect to predefined security constraint. The proposed technique has polynomial time complexity which is about half of traditional approximation approaches. The efficiency of our algorithm is validated by extensive experiments.

Embedded systems (ESs) have been a prominent solution for enhancing system performance and reliability in recent years. ESs that are required to ensure functional correctness under timing constraints are referred to as real-time embedded systems (RTESs). With the emerging trend of utilizing RTESs in safety and reliability critical areas, security of RTESs, especially confidentiality of the communication, becomes of great importance. More recently, side-channel attacks (SCAs) posed serious threats to confidentiality protection mechanisms, namely, cryptographic algorithms. In this work, we present the first analytical framework for quantifying the influence of real-time scheduling policies on the robustness of secret keys against differential power analysis (DPA) attacks, one of the most popular type of SCAs. We validated the proposed concept on two representative scheduling algorithms, earliest deadline first scheduling (EDF) and rate-monotonic scheduling (RMS), via extensive experiments.

In this paper, we approach the design of energy- and security-critical distributed real-time embedded systems from the early mapping and scheduling phases. Modern Distributed Embedded Systems (DESs) are common to be connected to external networks, which is beneficial for various purposes, but also opens up the gate for potential security attacks. However, security protections in DESs result in significant time and energy overhead. In this work, we focus on the problem of providing the best confidentiality protection of internal communication in DESs under time and energy constraints. The complexity of finding the optimal solution grows exponentially as problem size grows. Therefore, we propose an efficient genetic algorithm based heuristic for solving the problem. Extensive experiments demonstrate the efficiency of the proposed technique.

In this paper we are interested in securitysensitive mixed-criticality real-time systems. Existing researches on mixed-criticality systems usually are safety-oriented, which seriously ignore the security requirements. We firstly establish the system model to capture security-critical applications in mixed-criticality systems. Higher security-criticality protection always results in significant time and energy overhead in mixedcriticality systems. Thus, this paper proposes a system-level design framework for energy optimization of security-sensitive mixed-criticality system. Since the time complexity of finding optimal solutions grows exponentially as problem size grows, a GA based efficient heuristic algorithm is devised to address the system-level optimization problem. Extensive experiments demonstrate the efficiency of the proposed technique, which can obtain balanced minimal energy consumption while satisfying strict security and timing constraints.

We approach the emerging area of energy efficient, secure real-time embedded systems design. Many modern embedded systems have to fulfill strict security constraints and are often required to meet stringent deadlines in different operation modes, where the number and nature of active tasks vary (dynamic task sets). In this context, the use of dynamic voltage/frequency scaling (DVFS) techniques and onboard field-programmable gate array (FPGA) co-processors offer new dimensions for energy savings and performance enhancement. We propose a novel design framework that provides the best security protection consuming the minimal energy for all operation modes of a system. Extensive experiments demonstrate the efficiency of our techniques.