Biblio

Present networks within safety-critical systems rely on complex and inflexible network configurations. New technologies such as software-defined networking are more dynamic and offer more flexibility, but due care needs to be exercised to ensure that safety and security are not compromised by incorrect configurations. To this end, this paper proposes the use of pre-generated and optimized configuration templates. These provide alternate routes for traffic considering availability, resilience and timing constraints where network components fail due to attacks or faults.To obtain these templates, two heuristics based on Dijkstra's algorithm and an optimization algorithm providing the maximum resilience were investigated. While the configurations obtained through optimization yield appropriate templates, the heuristics investigated are not suitable to obtain configuration templates, since they cannot fulfill all requirements.

In the Network on Chip (NoC), performance optimization has always been a research focus. Compared with the static routing scheme, dynamical routing schemes can better reduce the data of packet transmission latency under network congestion. In this paper, we propose a dynamical Q-learning routing approach with real-time monitoring of NoC. Firstly, we design a real-time monitoring scheme and the corresponding circuits to record the status of traffic congestion for NoC. Secondly, we propose a novel method of Q-learning. This method finds an optimal path based on the lowest traffic congestion. Finally, we dynamically redistribute network tasks to increase the packet transmission speed and balance the traffic load. Compared with the C-XY routing and DyXY routing, our method achieved improvement in terms of 25.6%-49.5% and 22.9%-43.8%.

The pattern recognition in the sparse representation (SR) framework has been very successful. In this model, the test sample can be represented as a sparse linear combination of training samples by solving a norm-regularized least squares problem. However, the value of regularization parameter is always indiscriminating for the whole dictionary. To enhance the group concentration of the coefficients and also to improve the sparsity, we propose a new SR model called adaptive sparse representation classifier(ASRC). In ASRC, a sparse coefficient strengthened item is added in the objective function. The model is solved by the artificial bee colony (ABC) algorithm with variable step to speed up the convergence. Also, a partition strategy for large scale dictionary is adopted to lighten bee's load and removes the irrelevant groups. Through different data sets, we empirically demonstrate the property of the new model and its recognition performance.

This paper proposes a generic SATCOM control loop in a generic multivector structure to facilitate predictive analysis for achieving resiliency under time varying circumstances. The control loop provides strategies and actions in the context of game theory to optimize the resources for SATCOM networks. Details of the theoretic game and resources optimization approaches are discussed in the paper.

Security breaches and attacks are becoming a more critical and, simultaneously, a challenging problems for many firms in networked supply chains. A game theory-based model is developed to investigate how interdependent feature of information security risk influence the optimal strategy of firms to invest in information security. The equilibrium levels of information security investment under non-cooperative game condition are compared with socially optimal solutions. The results show that the infectious risks often induce firms to invest inefficiently whereas trust risks lead to overinvest in information security. We also find that firm's investment may not necessarily monotonous changes with infectious risks and trust risks in a centralized case. Furthermore, relative to the socially efficient level, firms facing infectious risks may invest excessively depending on whether trust risks is large enough.

How to protect users' private data during network data mining has become a hot issue in the fields of big data and network information security. Most current researches on differential privacy k-means clustering algorithms focus on optimizing the selection of initial centroids. However, the traditional privacy budget allocation has the problem that the random noise becomes too large as the number of iterations increases, which will reduce the performance of data clustering. To solve the problem, we improved the way of privacy budget allocation in differentially private clustering algorithm DPk-means, and proposed APDPk-means, a new differential privacy clustering algorithm based on arithmetic progression privacy budget allocation. APDPk-means decomposes the total privacy budget into a decreasing arithmetic progression, allocating the privacy budgets from large to small in the iterative process, so as to ensure the rapid convergence in early iteration. The experiment results show that compared with the other differentially private k-means algorithms, APDPk-means has better performance in availability and quality of the clustering result under the same level of privacy protection.

Aiming at the problem that the traditional intrusion detection method can not effectively deal with the massive and high-dimensional network traffic data of industrial control system (ICS), an ICS intrusion detection strategy based on bidirectional generative adversarial network (BiGAN) is proposed in this paper. In order to improve the applicability of BiGAN model in ICS intrusion detection, the optimal model was obtained through the single variable principle and cross-validation. On this basis, the supervised control and data acquisition (SCADA) standard data set is used for comparative experiments to verify the performance of the optimized model on ICS intrusion detection. The results show that the ICS intrusion detection method based on optimized BiGAN has higher accuracy and shorter detection time than other methods.

In this paper, we formulate a combinatorial optimization problem that aims to maximize the accuracy of a lower bound estimate of the probability of security of a multi-robot system (MRS), while minimizing the computational complexity involved in its calculation. Security of an MRS is defined using the well-known control theoretic notion of left invertiblility, and the probability of security of an MRS can be calculated using binary decision diagrams (BDDs). The complexity of a BDD depends on the number of disjoint path sets considered during its construction. Taking into account all possible disjoint paths results in an exact probability of security, however, selecting an optimal subset of disjoint paths leads to a good estimate of the probability while significantly reducing computation. To deal with the dynamic nature of MRSs, we introduce two methods: (1) multi-point optimization, a technique that requires some a priori knowledge of the topology of the MRS over time, and (2) online optimization, a technique that does not require a priori knowledge, but must construct BDDs while the MRS is operating. Finally, our approach is validated on an MRS performing a rendezvous objective while exchanging information according to a noisy state agreement process.

Gatys et al. recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer. However, their framework requires a slow iterative optimization process, which limits its practical application. Fast approximations with feed-forward neural networks have been proposed to speed up neural style transfer. Unfortunately, the speed improvement comes at a cost: the network is usually tied to a fixed set of styles and cannot adapt to arbitrary new styles. In this paper, we present a simple yet effective approach that for the first time enables arbitrary style transfer in real-time. At the heart of our method is a novel adaptive instance normalization (AdaIN) layer that aligns the mean and variance of the content features with those of the style features. Our method achieves speed comparable to the fastest existing approach, without the restriction to a pre-defined set of styles. In addition, our approach allows flexible user controls such as content-style trade-off, style interpolation, color & spatial controls, all using a single feed-forward neural network.

{Surrogate model-based optimization algorithm remains as an important solution to expensive black-box function optimization. The introduction of ensemble model enables the algorithm to automatically choose a proper model integration mode and adapt to various parameter spaces when dealing with different problems. However, this also significantly increases the computational burden of the algorithm. On the other hand, utilizing parallel computing resources and improving efficiency of black-box function optimization also require combination with surrogate optimization algorithm in order to design and realize an efficient parallel parameter space sampling mechanism. This paper makes use of parallel computing technology to speed up the weight updating related computation for the ensemble model based on Dempster-Shafer theory, and combines it with stochastic response surface method to develop a novel parallel sampling mechanism for asynchronous parameter optimization. Furthermore, it designs and implements corresponding parallel computing framework and applies the developed algorithm to quantitative trading strategy tuning in financial market. It is verified that the algorithm is both feasible and effective in actual application. The experiment demonstrates that with guarantee of optimizing performance, the parallel optimization algorithm can achieve excellent accelerating effect.

We construct targeted audio adversarial examples on automatic speech recognition. Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose (recognizing up to 50 characters per second of audio). We apply our white-box iterative optimization-based attack to Mozilla's implementation DeepSpeech end-to-end, and show it has a 100% success rate. The feasibility of this attack introduce a new domain to study adversarial examples.

``Style transfer'' among images has recently emerged as a very active research topic, fuelled by the power of convolution neural networks (CNNs), and has become fast a very popular technology in social media. This paper investigates the analogous problem in the audio domain: How to transfer the style of a reference audio signal to a target audio content? We propose a flexible framework for the task, which uses a sound texture model to extract statistics characterizing the reference audio style, followed by an optimization-based audio texture synthesis to modify the target content. In contrast to mainstream optimization-based visual transfer method, the proposed process is initialized by the target content instead of random noise and the optimized loss is only about texture, not structure. These differences proved key for audio style transfer in our experiments. In order to extract features of interest, we investigate different architectures, whether pre-trained on other tasks, as done in image style transfer, or engineered based on the human auditory system. Experimental results on different types of audio signal confirm the potential of the proposed approach.

With the growing scale of Cyber-Physical Systems (CPSs), it is challenging to maintain their stability under all operating conditions. How to reduce the downtime and locate the failures becomes a core issue in system design. In this paper, we employ a hierarchical contract-based resilience framework to guarantee the stability of CPS. In this framework, we use Assume Guarantee (A-G) contracts to monitor the non-functional properties of individual components (e.g., power and latency), and hierarchically compose such contracts to deduce information about faults at the system level. The hierarchical contracts enable rapid fault detection in large-scale CPS. However, due to the vast number of components in CPS, manually designing numerous contracts and the hierarchy becomes challenging. To address this issue, we propose a technique to automatically decompose a root contract into multiple lower-level contracts depending on I/O dependencies between components. We then formulate a multi-objective optimization problem to search the optimal parameters of each lower-level contract. This enables automatic contract refinement taking into consideration the communication overhead between components. Finally, we use a case study from the manufacturing domain to experimentally demonstrate the benefits of the proposed framework.

Adversarial attacks have been the hot research field in artificial intelligence security. Decision-based black-box adversarial attacks are much more appropriate in the real-world scenarios, where only the final decisions of the targeted deep neural networks are accessible. However, since there is no available guidance for searching the imperceptive adversarial perturbation, boundary attack, one of the best performing decision-based black-box attacks, carries out computationally expensive search. For improving attack efficiency, we propose a novel black box explanation guided decision-based black-box adversarial attack. Firstly, the problem of decision-based adversarial attacks is modeled as a derivative-free and constraint optimization problem. To solve this optimization problem, the black box explanation guided constrained random search method is proposed to more quickly find the imperceptible adversarial example. The insights into the targeted deep neural networks explored by the black box explanation are fully used to accelerate the computationally expensive random search. Experimental results demonstrate that our proposed attack improves the attack efficiency by 64% compared with boundary attack.

Generating adversarial samples is gathering much attention as an intuitive approach to evaluate the robustness of learning models. Extensive recent works have demonstrated that numerous advanced image classifiers are defenseless to adversarial perturbations in the white-box setting. However, the white-box setting assumes attackers to have prior knowledge of model parameters, which are generally inaccessible in real world cases. In this paper, we concentrate on the hard-label black-box setting where attackers can only pose queries to probe the model parameters responsible for classifying different images. Therefore, the issue is converted into minimizing non-continuous function. A black-box approach is proposed to address both massive queries and the non-continuous step function problem by applying a combination of a linear fine-grained search, Fibonacci search, and a zeroth order optimization algorithm. However, the input dimension of a image is so high that the estimation of gradient is noisy. Hence, we adopt a zeroth-order optimization method in high dimensions. The approach converts calculation of gradient into a linear regression model and extracts dimensions that are more significant. Experimental results illustrate that our approach can relatively reduce the amount of queries and effectively accelerate convergence of the optimization method.

The design of low power chip for IoT applications is very challenge, especially for self-powered wireless sensors. Achieving ultra low power requires both system level optimization and circuit level innovation. This paper presents a continuous-in-time and discrete-in-amplitude (CTDA) system architecture that facilitates adaptive data rate sampling and clockless implementation for a wireless sensor SoC.

Cloud computing is the expansion of parallel computing, distributed computing. The technology of cloud computing becomes more and more widely used, and one of the fundamental issues in this cloud environment is related to task scheduling. However, scheduling in Cloud environments represents a difficult issue since it is basically NP-complete. Thus, many variants based on approximation techniques, especially those inspired by Swarm Intelligence (SI) have been proposed. This paper proposes a machine learning algorithm to guide the cloud choose the scheduling technique by using multi criteria decision to optimize the performance. The main contribution of our work is to minimize the makespan of a given task set. The new strategy is simulated using the CloudSim toolkit package where the impact of the algorithm is checked with different numbers of VMs varying from 2 to 50, and different task sizes between 30 bytes and 2700 bytes. Experiment results show that the proposed algorithm minimizes the execution time and the makespan between 7% and 75%, and improves the performance of the load balancing scheduling.

In video surveillance, face recognition (FR) systems seek to detect individuals of interest appearing over a distributed network of cameras. Still-to-video FR systems match faces captured in videos under challenging conditions against facial models, often designed using one reference still per individual. Although CNNs can achieve among the highest levels of accuracy in many real-world FR applications, state-of-the-art CNNs that are suitable for still-to-video FR, like trunk-branch ensemble (TBE) CNNs, represent complex solutions for real-time applications. In this paper, an efficient CNN architecture is proposed for accurate still-to-video FR from a single reference still. The CCM-CNN is based on new cross-correlation matching (CCM) and triplet-loss optimization methods that provide discriminant face representations. The matching pipeline exploits a matrix Hadamard product followed by a fully connected layer inspired by adaptive weighted cross-correlation. A triplet-based training approach is proposed to optimize the CCM-CNN parameters such that the inter-class variations are increased, while enhancing robustness to intra-class variations. To further improve robustness, the network is fine-tuned using synthetically-generated faces based on still and videos of non-target individuals. Experiments on videos from the COX Face and Chokepoint datasets indicate that the CCM-CNN can achieve a high level of accuracy that is comparable to TBE-CNN and HaarNet, but with a significantly lower time and memory complexity. It may therefore represent the better trade-off between accuracy and complexity for real-time video surveillance applications.

Training a feed-forward network for the fast neural style transfer of images has proven successful, but the naive extension of processing videos frame by frame is prone to producing flickering results. We propose the first end-to-end network for online video style transfer, which generates temporally coherent stylized video sequences in near realtime. Two key ideas include an efficient network by incorporating short-term coherence, and propagating short-term coherence to long-term, which ensures consistency over a longer period of time. Our network can incorporate different image stylization networks and clearly outperforms the per-frame baseline both qualitatively and quantitatively. Moreover, it can achieve visually comparable coherence to optimization-based video style transfer, but is three orders of magnitude faster.

Universal style transfer methods typically leverage rich representations from deep Convolutional Neural Network (CNN) models (e.g., VGG-19) pre-trained on large collections of images. Despite the effectiveness, its application is heavily constrained by the large model size to handle ultra-resolution images given limited memory. In this work, we present a new knowledge distillation method (named Collaborative Distillation) for encoder-decoder based neural style transfer to reduce the convolutional filters. The main idea is underpinned by a finding that the encoder-decoder pairs construct an exclusive collaborative relationship, which is regarded as a new kind of knowledge for style transfer models. Moreover, to overcome the feature size mismatch when applying collaborative distillation, a linear embedding loss is introduced to drive the student network to learn a linear embedding of the teacher's features. Extensive experiments show the effectiveness of our method when applied to different universal style transfer approaches (WCT and AdaIN), even if the model size is reduced by 15.5 times. Especially, on WCT with the compressed models, we achieve ultra-resolution (over 40 megapixels) universal style transfer on a 12GB GPU for the first time. Further experiments on optimization-based stylization scheme show the generality of our algorithm on different stylization paradigms. Our code and trained models are available at https://github.com/mingsun-tse/collaborative-distillation.

A novel method for computation of modal reflectivity at optical waveguide end-facet is presented. The method is based on the characteristic Green's function (CGF) technique. Using separability assumption of the structure and rational function fitting method (RFFM), a closed-form field expression is derived for optical planar waveguide. The uniform derived expression consists of discrete and continuous spectrum contributions which denotes guided and radiation modes effects respectively. An optimization problem is then defined to calculate the exact reflection coefficients at the end-facet for all extracted poles obtained from rational function fitting step. The proposed CGF-RFFM-optimization offers superior exactness in comparison with the previous reported CGF-complex images (CI) technique due to contribution of all components of field in the optimization problem. The main advantage of the proposed method lies in its simple implementation as well as precision for any refractive index contrast. Excellent numerical agreements with rigorous methods are shown in several examples.

The current trend of IoT user is toward the use of services and data externally due to voluminous processing, which demands resourceful machines. Instead of relying on the cloud of poor connectivity or a limited bandwidth, the IoT user prefers to use a cloudlet-based fog computing. However, the choice of cloudlet is solely dependent on its trust and reliability. In practice, even though a cloudlet possesses a required trusted platform module (TPM), we argue that the presence of a TPM is not enough to make the cloudlet trustworthy as the TPM supports only the primitive security of the bootstrap. Besides uncertainty in security, other uncertain conditions of the network (e.g. network bandwidth, latency and expectation time to complete a service request for cloud-based services) may also prevail for the cloudlets. Therefore, in order to evaluate the trust value of multiple cloudlets under uncertainty, this paper broadly proposes the empirical process for evaluation of trust. This will be followed by a measure of trust-based reputation of cloudlets through computational intelligence such as fuzzy logic and ant colony optimization (ACO). In the process, fuzzy logic-based inference and membership evaluation of trust are presented. In addition, ACO and its pheromone communication across different colonies are being modeled with multiple cloudlets. Finally, a measure of affinity or popular trust and reputation of the cloudlets is also proposed. Together with the context of application under multiple cloudlets, the computationally intelligent approaches have been investigated in terms of performance. Hence the contribution is subjected towards building a trusted cloudlet-based fog platform.

A physical layer network coding (PLNC) is a highly efficient scheme for exchanging information between two nodes. Since the relay receives the interfered signal between two signals sent by two nodes, it hardly decodes any information from received signal. Therefore, the secure wireless communication link to the untrusted relay is constructed. The two nodes optimize the transmit power control for maximizing the secure capacity but these depend on the channel state information informed by the relay station. Therefore, the untrusted relay disguises the informed CSI for exploiting the information from two nodes. This paper constructs the game of two optimizations between the legitimate two nodes and the untrusted relay for clarifying the security of PLNC with untrusted relay.

Future automotive systems will be highly automated and they will cooperate to optimize important system qualities and performance. Established safety assurance approaches and standards have been designed with manually controlled stand-alone systems in mind and are thus not fit to ensure safety of this next generation of systems. We argue that, given frequent dynamic changes and unknown contexts, systems need to be enabled to dynamically assess and manage their risks. In doing so, systems become resilient from a safety perspective, i.e. they are able to maintain a state of acceptable risk even when facing changes. This work presents a Dynamic Risk Assessment architecture that implements the concepts of context-awareness, confidence-disclosure and fail-operational. In particular, we demonstrate the utilization of these concepts for the calculation of automotive collision risk metrics, which are at the heart of our architecture.

This paper proposes a context-aware, graph-based approach for identifying anomalous user activities via user profile analysis, which obtains a group of users maximally similar among themselves as well as to the query during test time. The main challenges for the anomaly detection task are: (1) rare occurrences of anomalies making it difficult for exhaustive identification with reasonable false-alarm rate, and (2) continuously evolving new context-dependent anomaly types making it difficult to synthesize the activities apriori. Our proposed query-adaptive graph-based optimization approach, solvable using maximum flow algorithm, is designed to fully utilize both mutual similarities among the user models and their respective similarities with the query to shortlist the user profiles for a more reliable aggregated detection. Each user activity is represented using inputs from several multi-modal resources, which helps to localize anomalies from time-dependent data efficiently. Experiments on public datasets of insider threats and gesture recognition show impressive results.