Biblio

Aiming at the problems of single protection, lack of monitoring and unable to be physically isolated in time under abnormal conditions, an industrial control boundary network security protection method is provided. Realize the real-time monitoring and analysis of the network behavior of the industrial control boundary, realize the in-depth defense of the industrial control boundary, and timely block it in the way of logical link and physical link isolation in case of illegal intrusion, so as to comprehensively improve the protection level of the boundary security of the industrial control system.

The model-free adaptive security tracking control (MFASTC) problem of nonlinear networked control systems is explored in this paper with DoS attacks and delays consideration. In order to alleviate the impact of DoS attack and RTT delays on NCSs performance, an attack compensation mechanism and a networked predictive-based delay compensation mechanism are designed, respectively. The data-based designed method need not the dynamic and structure of the system, The MFASTC algorithm is proposed to ensure the output tracking error being bounded in the mean-square sense. Finally, an example is given to illustrate the effectiveness of the new algorithm by a comparison.

Due to the wide deployment of deep learning applications in safety-critical systems, robust and secure execution of deep learning workloads is imperative. Adversarial examples, where the inputs are carefully designed to mislead the machine learning model is among the most challenging attacks to detect and defeat. The most dominant approach for defending against adversarial examples is to systematically create a network architecture that is sufficiently robust. Neural Architecture Search (NAS) has been heavily used as the de facto approach to design robust neural network models, by using the accuracy of detecting adversarial examples as a key metric of the neural network's robustness. While NAS has been proven effective in improving the robustness (and accuracy in general), the NAS-generated network models run noticeably slower on typical DNN accelerators than the hand-crafted networks, mainly because DNN accelerators are not optimized for robust NAS-generated models. In particular, the inherent multi-branch nature of NAS-generated networks causes unacceptable performance and energy overheads.To bridge the gap between the robustness and performance efficiency of deep learning applications, we need to rethink the design of AI accelerators to enable efficient execution of robust (auto-generated) neural networks. In this paper, we propose a novel hardware architecture, NASGuard, which enables efficient inference of robust NAS networks. NASGuard leverages a heuristic multi-branch mapping model to improve the efficiency of the underlying computing resources. Moreover, NASGuard addresses the load imbalance problem between the computation and memory-access tasks from multi-branch parallel computing. Finally, we propose a topology-aware performance prediction model for data prefetching, to fully exploit the temporal and spatial localities of robust NAS-generated architectures. We have implemented NASGuard with Verilog RTL. The evaluation results show that NASGuard achieves an average speedup of 1.74× over the baseline DNN accelerator.

Batched network coding is a low-complexity network coding solution to feedbackless multi-hop wireless packet network transmission with packet loss. The data to be transmitted is encoded into batches where each of which consists of a few coded packets. Unlike the traditional forwarding strategy, the intermediate network nodes have to perform recoding, which generates recoded packets by network coding operations restricted within the same batch. Adaptive recoding is a technique to adapt the fluctuation of packet loss by optimizing the number of recoded packets per batch to enhance the throughput. The input rank distribution, which is a piece of information regarding the batches arriving at the node, is required to apply adaptive recoding. However, this distribution is not known in advance in practice as the incoming link's channel condition may change from time to time. On the other hand, to fully utilize the potential of adaptive recoding, we need to have a good estimation of this distribution. In other words, we need to guess this distribution from a few samples so that we can apply adaptive recoding as soon as possible. In this paper, we propose a distributionally robust optimization for adaptive recoding with a small-sample inferred prediction of the input rank distribution. We develop an algorithm to efficiently solve this optimization with the support of theoretical guarantees that our optimization's performance would constitute as a confidence lower bound of the optimal throughput with high probability.

Modulated signal identification plays a crucial role in both military reconnaissance and civilian signal regulation. Traditionally, modulated signal identification is based on high-order statistics, but this approach has many drawbacks. With the development of deep learning, its advantages are fully exploited by combining it with modulated signals to avoid the complex process of computing a priori knowledge while having good fault tolerance. In this paper, ten digital modulated signals are classified and recognized, and improvements are made on the basis of convolutional neural networks, using feature reuse to increase the depth of the convolutional layer and extract signal features with better results. After experimental analysis, the recognition accuracy increases with the rise of the signal-to-noise ratio, and can reach 90% and above when the signal-to-noise ratio is 30dB.

In electronic warfare, communication may not counter reconnaissance and jamming without the help of network-station selection of frequency hopping. The competition in the field of electromagnetic spectrum is becoming more and more fierce with the increasingly complex electromagnetic environment of modern battlefield. The research on detection, identification, parameter estimation and network station selection of frequency hopping communication network has aroused the interest of scholars both at home and abroad, which has been summarized in this paper. Firstly, the working mode and characteristics of two kinds of FH communication networking modes synchronous orthogonal network and asynchronous non orthogonal network are introduced. Then, through the analysis of FH signals time hopping, frequency hopping, bandwidth, frequency, direction of arrival, bad time-frequency analysis, clustering analysis and machine learning method, the feature-based method is adopted Parameter selection technology is used to sort FH network stations. Finally, the key and difficult points of current research on FH communication network separation technology and the research status of blind source separation technology are introduced in details in this paper.

With the rapid development of mobile communication technology, the reconnaissance on terminal capability and identity information is not only an important guarantee to maintain the normal order of mobile communication, but also an essential means to ensure the electromagnetic space security. According to the characteristics of 5G mobile communication terminal's transporting capability and identity information, the smart jamming is first used to make the target terminal away from the 5G network, and then the jamming is turned off at once. Next the terminal will return to the 5G network. Through the time-frequency matching detection method, interactive signals of random access process and network registration between the terminal and the base station are quickly captured in this process, and the scheduling information in Physical Downlink Control Channel (PDCCH) and the capability and identity information in Physical Uplink Shared Channel (PUSCH) are demodulated and decoded under non-cooperative conditions. Finally, the experiment is carried out on the actual 5G communication terminal of China Telecom. The capability and identity information of this terminal are extracted successfully in the Stand Alone (SA) mode, which verifies the effectiveness and correctness of the method. This is a significant technical foundation for the subsequent development on the 5G terminal control equipment.

Automatic modulation recognition (AMR) plays an important role in cognitive radio and electronic reconnaissance applications. In order to solve the problem that the lack of modulation signal data sets, the labeled data sets are generated by the software radio equipment NI-USRP 2920 and LabVIEW software development tool. In this paper, a combined network based on deep learning is proposed to identify ten types of digital modulation signals. Convolutional neural network (CNN) and Inception network are trained on different data sets, respectively. We combine CNN with Inception network to distinguish different modulation signals well. Experimental results show that our proposed method can recognize ten types of digital modulation signals with high identification accuracy, even in scenarios with a low signal-to-noise ratio (SNR).

Network-on-Chip (NoC) fulfills the communication requirements of modern System-on-Chip (SoC) architectures. Due to the resource-constrained nature of NoC-based SoCs, it is a major challenge to secure on-chip communication against eavesdropping attacks using traditional encryption methods. In this paper, we propose a lightweight encryption technique using chaffing and winnowing (C&W) with all-or-nothing transform (AONT) that benefits from the unique NoC traffic characteristics. Our experimental results demonstrate that our proposed encryption technique provides the required security with significantly less area and energy overhead compared to the state-of-the-art approaches.

In recent years, with the continuous development of artificial intelligence algorithms, their applications in network intrusion detection have become more and more widespread. However, as the network speed continues to increase, network traffic increases dramatically, and the drawbacks of traditional machine learning methods such as high false alarm rate and long training time are gradually revealed. CNN(Convolutional Neural Networks) can only extract spatial features of data, which is obviously insufficient for network intrusion detection. In this paper, we propose an intrusion detection model that combines CNN and BiSRU (Bi-directional Simple Recurrent Unit) to achieve the goal of intrusion detection by processing network traffic logs. First, we extract the spatial features of the original data using CNN, after that we use them as input, further extract the temporal features using BiSRU, and finally output the classification results by softmax to achieve the purpose of intrusion detection.

This work seeks to advance the state of the art in HPC I/O performance analysis and interpretation. In particular, we demonstrate effective techniques to: (1) model output performance in the presence of I/O interference from production loads; (2) build features from write patterns and key parameters of the system architecture and configurations; (3) employ suitable machine learning algorithms to improve model accuracy. We train models with five popular regression algorithms and conduct experiments on two distinct production HPC platforms. We find that the lasso and random forest models predict output performance with high accuracy on both of the target systems. We also explore use of the models to guide adaptation in I/O middleware systems, and show potential for improvements of at least 15% from model-guided adaptation on 70% of samples, and improvements up to 10 x on some samples for both of the target systems.

The traditional Proof of Existence blockchain service on the Bitcoin network can be used to verify the existence of any research data at a specific point of time, and to validate the data integrity, without revealing its content. Several variants of the blockchain service exist to certify the existence of data relying on cryptographic fingerprinting, thus enabling an efficient verification of the authenticity of such certifications. However, nowadays research data is continuously changing and being modified through different processing steps in most scientific research workflows such that certifications of individual data objects seem to be constantly outdated in this setting. This paper describes how the blockchain and distributed ledger technology can be used to form a new certification model, that captures the research process as a whole in a more meaningful way, including the description of the used data through its different stages and the associated computational pipeline, code for analysis and the experimental design. The scientific blockchain infrastructure bloxberg, together with a deep learning based analysis from the behavioral science field are used to show the applicability of the approach.

With almost every new vehicle being connected, the importance of vehicle data is growing rapidly. Many mobility applications rely on the fusion of data coming from heterogeneous data sources, like vehicle and "smart-city" data or process data generated by systems out of their control. This external data determines much about the behaviour of the relying applications: it impacts the reliability, security and overall quality of the application's input data and ultimately of the application itself. Hence, knowledge about the provenance of that data is a critical component in any data-driven system. The secure traceability of the data handling along the entire processing chain, which passes through various distinct systems, is critical for the detection and avoidance of misuse and manipulation. In this paper, we introduce a mechanism for establishing secure data provenance in real time, demonstrating an exemplary use-case based on a machine learning model that detects dangerous driving situations. We show with our approach based on W3C decentralized identity standards that data provenance in closed data systems can be effectively achieved using technical standards designed for an open data approach.

To improve efficiency of stegosystem on blockchain and balance the time consumption of Encode and Decode operations, we propose a new blockchain-based steganography scheme, called Keys as Secret Messages (KASM), where a codebook of mappings between bitstrings and public keys can be pre-calculated by both sides with some secret parameters pre-negotiated before covert communication. By applying properties of elliptic curves and pseudorandom number generators, we realize key derivation of codebook item, and we construct the stegosystem with provable security under chosen hiddentext attack. By comparing KASM with Blockchain Covert Channel (BLOCCE) and testing on Bitcoin protocol, we conclude that our proposed stegosystem encodes hiddentexts faster than BLOCCE does and can decode stegotexts in highly acceptable time. The balanced time consumption of Encode and Decode operations of KASM make it applicable in the scene of duplex communication. At the same time, KASM does not leak sender’s private keys, so sender’s digital currencies can be protected.

In the era of big data and artificial intelligence, computer networks have become an important infrastructure, and the Internet has become ubiquitous. The most basic property of computer networks is reachability. The needs of the modern Internet mainly include cost, performance, reliability, and security. However, even for experienced network engineers, it is very difficult to manually conFigure the network to meet the needs of the modern large-scale Internet. The engineers often make mistakes, which can cause network paralysis, resulting in incalculable losses. Due to the development of automatic reasoning technology, automatic verification of network configuration is used to avoid mistakes. Network verification is at least an NP-C problem, so it is necessary to compress the network to reduce the network scale, thereby reducing the network verification time. This paper proposes a new model of network modeling, which is more suitable for the verification of network configuration on common protocols (such as RIP, BGP). On the basis of the existing compression method, two compression rules are added to compress the modeled network, reducing network verification time and conducting network reachability verification experiments on common networks. The experimental results are slightly better than the current compression methods.

The popular federated edge learning (FEEL) framework allows privacy-preserving collaborative model training via frequent learning-updates exchange between edge devices and server. Due to the constrained bandwidth, only a subset of devices can upload their updates at each communication round. This has led to an active research area in FEEL studying the optimal device scheduling policy for minimizing communication time. However, owing to the difficulty in quantifying the exact communication time, prior work in this area can only tackle the problem partially by considering either the communication rounds or per-round latency, while the total communication time is determined by both metrics. To close this gap, we make the first attempt in this paper to formulate and solve the communication time minimization problem. We first derive a tight bound to approximate the communication time through cross-disciplinary effort involving both learning theory for convergence analysis and communication theory for per-round latency analysis. Building on the analytical result, an optimized probabilistic scheduling policy is derived in closed-form by solving the approximate communication time minimization problem. It is found that the optimized policy gradually turns its priority from suppressing the remaining communication rounds to reducing per-round latency as the training process evolves. The effectiveness of the proposed scheme is demonstrated via a use case on collaborative 3D objective detection in autonomous driving.

Unforeseen situations on the shopfloor cause the assembly process to divert from its expected progress. To be able to overcome these deviations in a timely manner, assembly process monitoring and early deviation detection are necessary. However, legal regulations and union policies often limit the direct monitoring of human-intensive assembly processes. Grounded in an industry use case, this paper outlines a novel approach that, based on indirect privacy-respecting monitored data from the shopfloor, enables the near real-time detection of multiple types of process deviations. In doing so, this paper specifically addresses uncertainties stemming from indirect shopfloor observations and how to reason in their presence.

Collaborative learning has gained great popularity due to its benefit of data privacy protection: participants can jointly train a Deep Learning model without sharing their training sets. However, recent works discovered that an adversary can fully recover the sensitive training samples from the shared gradients. Such reconstruction attacks pose severe threats to collaborative learning. Hence, effective mitigation solutions are urgently desired.In this paper, we propose to leverage data augmentation to defeat reconstruction attacks: by preprocessing sensitive images with carefully-selected transformation policies, it becomes infeasible for the adversary to extract any useful information from the corresponding gradients. We design a novel search method to automatically discover qualified policies. We adopt two new metrics to quantify the impacts of transformations on data privacy and model usability, which can significantly accelerate the search speed. Comprehensive evaluations demonstrate that the policies discovered by our method can defeat existing reconstruction attacks in collaborative learning, with high efficiency and negligible impact on the model performance.

In recent years, the commodities industry has grown rapidly under the stimulus of domestic demand and the expansion of cross-border trade. It has also been combined with the rapid development of e-commerce technology in the same period to form a flexible and efficient e-commerce system for bulk commodities. However, the hasty combination of both has inspired a lack of effective regulatory measures in the bulk industry, leading to constant industry chaos. Among them, the problem of lagging evidence in regulatory platforms is particularly prominent. Based on this, we design a blockchain-based evidential and secure bulk-commodity supervisory system (abbr. BeBus). Setting different privacy protection policies for each participant in the system, the solution ensures effective forensics and tamper-proof evidence to meet the needs of the bulk business scenario.

A trusted execution environment (TEE) such as Intel Software Guard Extension (SGX) runs attestation to prove to a data owner the integrity of the initial state of an enclave, including the program to operate on her data. For this purpose, the data-processing program is supposed to be open to the owner or a trusted third party, so its functionality can be evaluated before trust being established. In the real world, however, increasingly there are application scenarios in which the program itself needs to be protected (e.g., proprietary algorithm). So its compliance with privacy policies as expected by the data owner should be verified without exposing its code.To this end, this paper presents DEFLECTION, a new model for TEE-based delegated and flexible in-enclave code verification. Given that the conventional solutions do not work well under the resource-limited and TCB-frugal TEE, we come up with a new design inspired by Proof-Carrying Code. Our design strategically moves most of the workload to the code generator, which is responsible for producing easy-to-check code, while keeping the consumer simple. Also, the whole consumer can be made public and verified through a conventional attestation. We implemented this model on Intel SGX and demonstrate that it introduces a very small part of TCB. We also thoroughly evaluated its performance on micro-and macro-benchmarks and real-world applications, showing that the design only incurs a small overhead when enforcing several categories of security policies.

Advanced persistent threat (APT) attackers usually conduct a large number of network reconnaissance before a formal attack to discover exploitable vulnerabilities in the target network and system. The static configuration in traditional network systems provides a great advantage for adversaries to find network targets and launch attacks. To reduce the effectiveness of adversaries' continuous reconnaissance attacks, this paper develops a moving target defense (MTD) enhanced cyber deception defense system based on software-defined networks (SDN). The system uses virtual network topology to confuse the target network and system information collected by adversaries. Also Besides, it uses IP address randomization to increase the dynamics of network deception to enhance its defense effectiveness. Finally, we implemented the system prototype and evaluated it. In a configuration where the virtual network topology scale is three network segments, and the address conversion cycle is 30 seconds, this system delayed the adversaries' discovery of vulnerable hosts by an average of seven times, reducing the probability of adversaries successfully attacking vulnerable hosts by 83%. At the same time, the increased system overhead is basically within 10%.

The evolution of deep learning has promoted the popularization of smart devices. However, due to the insufficient development of computing hardware, the ability to conduct local training on smart devices is greatly restricted, and it is usually necessary to deploy ready-made models. This opacity makes smart devices vulnerable to deep learning backdoor attacks. Some existing countermeasures against backdoor attacks are based on the attacker’s ignorance of defense. Once the attacker knows the defense mechanism, he can easily overturn it. In this paper, we propose a Trojaning attack defense framework based on moving target defense(MTD) strategy. According to the analysis of attack-defense game types and confrontation process, the moving target defense model based on signaling game was constructed. The simulation results show that in most cases, our technology can greatly increase the attack cost of the attacker, thereby ensuring the availability of Deep Neural Networks(DNN) and protecting it from Trojaning attacks.

With the advancement of network technology, more electronic devices have begun to connect to the Internet. The era of IoE (Internet of Everything) is coming. However, the number of serious incidents of cyberattacks on important facilities has gradually increased at the same time. Security becomes an important issue when setting up plenty of network devices in an environment. Thus, we propose an innovative mechanism of the Moving Target Defense (MTD) to solve the problems happening to other MTD mechanisms in the past. This method applies Dynamic Host Configuration Protocol (DHCP) to dynamically change the IPv4 address of information equipment in the medical environment. In other words, each of the nodes performs IP-Hopping and effectively avoids malicious attacks. Communication between devices relies on DNS lookup. The mechanism avoids problems such as time synchronization and IP conflict. Also, it greatly reduces the costs of large-scale deployment. All of these problems are encountered by other MTD mechanisms in the past. Not only can the mechanism be applied to the medical and information equipment, it can also be applied to various devices connected to the Internet, including Industrial Control System (ICS). The mechanism is implemented in existing technologies and prevents other problems, which makes it easy to build a system.

Fuzzing is a promising method for discovering vulnerabilities. Recently, various techniques are developed to improve the efficiency of fuzzing, and impressive gains are observed in evaluation results. However, evaluation is complex, as many factors affect the results, for example, test suites, baseline and metrics. Even more, most experiment setups are lab-oriented, lacking industrial settings such as large code-base and parallel runs. The correlation between the academic evaluation results and the bug-finding ability in real industrial settings has not been sufficiently studied. In this paper, we test representative fuzzing techniques to reveal their efficiency in industrial settings. First, we apply typical fuzzers on academic widely used small projects from LAVAM suite. We also apply the same fuzzers on large practical projects from Google's fuzzer-test-suite, which is rarely used in academic settings. Both experiments are performed in both single and parallel run. By analyzing the results, we found that most optimizations working well on LAVA-M suite fail to achieve satisfying results on Google's fuzzer-test-suite (e.g. compared to AFL, QSYM detects 82x more synthesized bugs in LAVA-M, but only detects 26% real bugs in Google's fuzzer-test-suite), and the original AFL even outperforms most academic optimization variants in industry widely used parallel runs (e.g. AFL covers 13% more paths than AFLFast). Then, we summarize common pitfalls of those optimizations, analyze the corresponding root causes, and propose potential directions such as orchestrations and synchronization to overcome the problems. For example, when running in parallel on those large practical projects, the proposed horizontal orchestration could cover 36%-82% more paths, and discover 46%-150% more unique crashes or bugs, compared to fuzzers such as AFL, FairFuzz and QSYM.

Multi-processors System-on-Chip (MPSoC) are a key enabling technology for different applications characterized by hyper-connectivity and multi-tenant requirements, where resources are shared and communication is ubiquitous. In such an environment, security plays a major role. To cope with these security needs, MPSoCs usually integrate cryptographic functionalities deployed as software and/or hardware solutions. Quantum computing represents a threat for the current cryptography. To overcome such a threat, Post-quantum cryptography (PQC) can be used, thus ensuring the long term security of different applications. Since 2017, NIST is running a PQC standardization process. While the focus has been the security analysis of the different PQC candidates and the software implementation, the MPSoC PQC implementation has been neglected. To this end, this work presents two contributions. First, the exploration of the multicore capabilities for developing optimized PQC implementations. As a use case, NTRU lattice-based PQC, finalist for the NIST standardization process, is discussed. Second, NTRU was deployed on an AURIX microcontroller of Infineon Technologies AG with the Real-Time Operating System PXROS-HR from HighTec EDV-Systeme GmbH. Results show that NTRU can be efficiently implemented and optimized on a multicore architecture, improving the performance up to 43% when compared to single core solutions.