Reinforcement Learning Based Sparse Black-box Adversarial Attack on Video Recognition Models

We explore the black-box adversarial attack on video recognition models. Attacks are only performed on selected key regions and key frames to reduce the high computation cost of searching adversarial perturbations on a video due to its high dimensionality. To select key frames, one way is to use heuristic algorithms to evaluate the importance of each frame and choose the essential ones. However, it is time inefficient on sorting and searching. In order to speed up the attack process, we propose a reinforcement learning based frame selection strategy. Specifically, the agent explores the difference between the original class and the target class of videos to make selection decisions. It receives rewards from threat models which indicate the quality of the decisions. Besides, we also use saliency detection to select key regions and only estimate the sign of gradient instead of the gradient itself in zeroth order optimization to further boost the attack process. We can use the trained model directly in the untargeted attack or with little fine-tune in the targeted attack, which saves computation time. A range of empirical results on real datasets demonstrate the effectiveness and efficiency of the proposed method.

Introducing the Common Attack Process Framework for Incident Mapping

The paper presents a new framework that allows both educators and operational personnel to better overlay incidents into a simplified framework. While other attack frameworks exist, they either lack simplicity or are too focused on specific types of attacks. Therefore, the authors have attempted to define a framework that can be used broadly across both physical and cyber incidents. Furthermore, the paper provides several high-profile examples wherein it is shown how this new framework more accurately represents the adversary's actions. Lastly, the framework allows room for expansion in that, within each stage, a plethora of questions can be addressed, giving greater specificity into how that stage was carried out.

Semi-Markov Based Dependability Modeling of Bitcoin Nodes Under Eclipse Attacks and State-Dependent Mitigation

The block chain technology has immense potential in many different applications, including but not limited to cryptocurrencies, financial services, smart contracts, supply chains, healthcare services, and energy trading. Due to the critical nature of these applications, it is pivotal to model and evaluate dependability of the block chain-based systems, contributing to their reliable and robust operation. This paper models and analyzes the dependability of Bitcoin nodes subject to Eclipse attacks and state-dependent mitigation activities. Built upon the block chain technology, the Bitcoin is a peer-to-peer cryptocurrency system enabling an individual user to trade freely without the involvement of banks or any other types of intermediate agents. However, a node in the Bitcoin is vulnerable to the Eclipse attack, which aims to monopolize the information flow of the victim node. A semi-Markov process (SMP) based approach is proposed to model the Eclipse attack behavior and possible mitigation activities that may prevent the attack from being successful during the attack process. The SMP model is then evaluated to determine the steady-state dependability of the Bitcoin node. Numerical examples are provided to demonstrate the influence of the time to restart the Bitcoin software and time to detect and delete the malicious message on the Bitcoin node dependability.

A Hybrid Alarm Association Method Based on AP Clustering and Causality

Internet of Things (IoT) brought great convenience to people’s daily lives. Meanwhile, the IoT devices are facing severe attacks from hackers and malicious attackers. Hackers and malicious attackers use various methods to invade the Internet of Things system, causing the Internet of Things to face a large number of targeted, concealed, and penetrating potential threats, which makes the privacy problem of the Internet of Things suffers serious challenges. But the existing methods and technologies cannot fully identify the attacker’s attack process and protect the privacy of the Internet of Things. Alarm correlation method can construct a complete attack scenario and identify the attacker’s intention by alarming the alarm data which provides an effective protection for user privacy. However, the existing alarm correlation methods still have the disadvantages of low correlation accuracy, poor correlation efficiency, and strong dependence on the knowledge base. To address these issues, we propose an alarm correlation method based on Affinity Propagation (AP) clustering algorithm and causal relationship. Our method considers that the alarm data triggered by the same attack process has high similarity characteristics, adopts the AP algorithm to improve the correlation efficiency, and at the same time constructs a complete attack process based on the causal correlation idea. The new alarm correlation method has a high correlation effect and builds a complete attack process to help managers identify attack intentions and prevent attacks.

Recovery and Incorporation of expanded polystyrene SolidWaste in Lightweight Concrete

Context: The high consumption of parts made from expanded polystyrene (EPS) generates environmental problems when disposed. Due to its low density and the low possibility of being utilized in other applications after its disposal, it is necessary to generate an alternative for the recovery and application of this type of waste. This work aims to generate an alternative in the application of EPS waste, particularly as a coarse aggregate in the manufacturing of lightweight concrete. Method: This study used discarded EPS containers as raw material. The material was cleaned, crushed and subsequently reduced in volume by applying acetone, generating pieces of polystyrene (R-PS) to be applied as a coarse aggregate for the manufacturing of lightweight concrete in different proportions. In addition, the pieces were subjected to a chemical attack process in order to observe their behavior. Results: The results show the degree of volume reduction of the EPS pieces by using different acetone ratios, establishing the best degree of reduction (in volume) of this material. Likewise, chemical attack tests show the behavior of R-PS against different agents in R-PS samples. Meanwhile, the failure tests on different concrete samples determine the best R-PS ratio as coarse aggregate for the manufacturing of lightweight concrete. Conclusions: The data obtained in this study show that the application of acetone on EPSW samples reduces its volume by up to 55 %. Concrete failure tests show that an optimum P-RS addition value, to be used as an aggregate in the manufacturing of lightweight concrete, is 7 %. This improves its resistance to chemical agents and weight reduction without significantly reducing the mechanical properties of concrete.

Research on Speed Scheme for Precise Attack of Miniature Loitering Munition

The loitering munitions are advanced new ammunitions, which reflect both the characteristics of UAV and missile and have their own novel characteristics. This paper analysed the characteristics of the attack process of a small loitering munition and proposed a speed scheme suitable for precise strike of loitering munitions based on the concept of traditional ammunition’s speed-thrust schemes. Then, the boundary conditions and the existence of the solution have been discussed. Finally, flight test results showed that the scheme was effective.

UCAV Formation Online Collaborative Trajectory Planning Using hp Adaptive Pseudospectral Method

In this paper, a novel approach to solving the formation online collaborative trajectory planning for fixed-wing Unmanned Combat Aerial Vehicles (UCAVs) is proposed. In order to describe the problem, the formation attack process which consists of communication framework and synergy elements is analyzed. The collaborative trajectory planning model which is based on avoiding the threat zones, reducing the execution time, and accomplishing the mission combines kinematics/dynamics model of UCAV with formation relative motion model to establish the optimal control problem. The approach based on hp adaptive pseudospectral method is presented to generate formation trajectory that satisfies the collaborative constraints. When a trigger event is detected, based on the offline planning, the online collaborative trajectory replanning using rolling horizon strategy is carried out. Simulated experiments which are divided into offline scenarios and online scenarios demonstrate that the proposed approach can generate trajectories which can meet the actual flight constraints, and the results verify the feasibility and stability of the proposed approach.