This paper proposes an interval combination prediction model for Shanghai composite index, utilizing the Theil coefficient and the induced continuous generalized ordered weighted logarithmic harmonic averaging (ICGOWLHA) operator. The effectiveness of the proposed model under specific weight conditions and the existence of its analytical solution are demonstrated. Shanghai composite index's case analysis demonstrates that, in terms of interval root mean squared error (IRMSE), interval mean absolute error (IMAE), interval mean absolute percentage error (IMAPE), and interval mean squared percentage error (IMSPE), the proposed model's predictive performance improvements over the best-performing single prediction model are 29.33%, 25.72%, 26.10%, and 28.86%, respectively. At the same time, the theoretical properties of the model are verified in the results of the case analysis, and the model's convergence is reflected in sensitivity analysis. Through extensive model comparisons, it is observed that the model proposed in this paper exhibits strong generalization, without specific limitations on data size or feature count. It demonstrates good aggregation prediction performance for interval data. Moreover, it is applicable to various fields, including finance, environment, and others.

Federated learning (FL) as a secure distributed learning framework gains interests in Internet of Things (IoT) due to its capability of protecting the privacy of participant data. However, traditional FL systems are vulnerable to free-rider (FR) attacks, which causes unfairness, privacy leakage and inferior performance to FL systems. The prior defense mechanisms against FR attacks assumed that malicious clients (namely, adversaries) declare less than 50% of the total amount of clients. Moreover, they aimed for anonymous FR (AFR) attacks and lost effectiveness in resisting selfish FR (SFR) attacks. In this article, we propose a parameter audit-based secure and fair FL scheme (PASS) against FR attack. PASS has the following key features: 1) prevent from privacy leakage with less accuracy loss; 2) be effective in countering both AFR and SFR attacks; and 3) work well no matter whether AFR and SFR adversaries occupy the majority of clients or not. Extensive experimental results validate that PASS: 1) has the same level as the state-of-the-art method in mean square error against privacy leakage; 2) defends against AFR and SFR attacks in terms of a higher defense success rate, lower false positive rate, and higher F1-score; and 3) is still effective where adversaries exceed 50%, with F1-score 89% against AFR attack and F1-score 87% against SFR attack. Note that PASS produces no negative effect on FL accuracy when there is no FR adversary.

Federated Learning (FL) is a distributed learning framework and gains interest due to protecting the privacy of participants. Thus, if some participants are free-riders who are attackers without contributing any computation resources and privacy data, the model faces privacy leakage and inferior performance. In this paper, we explore and define two free-rider attack scenarios, anonymous and selfish free-rider attacks. Then we propose two methods, namely novel and advanced methods, to construct these two attacks. Extensive experiment results reveal the effectiveness in terms of the less deviation with conventional FL using the novel method, and high false positive rate to puzzle defense model using the advanced method.

The widespread application of deep neural network (DNN) techniques is being challenged by adversarial examples—the legitimate input added with imperceptible and well-designed perturbation that can fool DNNs easily in the DNN testing/deploying stage. Previous white-box adversarial example generation algorithms used the Jacobian gradient information to add the perturbation. This imprecise and inexplicit information can cause unnecessary perturbation when generating adversarial examples. This paper aims to address this issue. We first propose to apply the more informative and distilled gradient information, namely, integrated gradient, to generate adversarial examples. To further make the perturbation more imperceptible, we propose to employ the restriction combination of L 0 and L 1 / L 2 second, which can restrict the total perturbation and the perturbation points simultaneously. Meanwhile, to address the nondifferentiable problem of L 1 , we explore a proximal operation of L 1 third. On the basis of these three works, we propose two Integrated gradient-based White-box Adversarial example generation algorithms (IWA): Integrated gradient-based Finite Point Attack (IFPA) and Integrated gradient-based Universe Attack (IUA). IFPA is suitable for situations where there are a determined number of points to be perturbed. IUA is suitable for situations where no perturbation point number is preset to obtain more adversarial examples. We verify the effectiveness of the proposed algorithms on both structured and unstructured data sets, and compare them with five baseline generation algorithms. The results show that our proposed algorithms craft adversarial examples with more imperceptible perturbation and satisfactory crafting rate. L 2 restriction is suitable for unstructured data sets and L 1 restriction performs better in the structured data set.

Various Machine Learning (ML) models have been developed for malware detection. But their widespread application is challenged by adversarial attacks using adversarial malware examples. Generative Adversarial Networks (GAN) is one of the effective approaches to help build possible unknown attacks and expose the vulnerability of targeted systems. The existing GAN-based ML models have the weaknesses of unstable training and low-quality adversarial examples. In this paper, we propose a novel Mal-LSGAN model to tackle these weaknesses. By using a Least Square (LS) loss function and new activation function combinations, Mal-LSGAN achieves a higher Attack Success Rate (ASR) and a lower True Positive Rate (TPR) in 6 ML detectors, compared with the existing MalGAN and Imp-MalGAN. In Multi-Layer Perceptron (MLP), Mal-LSGAN can even decrease TPR from 97.81% of original examples to 2.92% of adversarial examples. The experimental results also demonstrate that Mal-Lsgangets the preferable transferability of adversarial malware examples.

Abstract Adversarial Malware Example (AME)-based adversarial training can effectively enhance the robustness of Machine Learning (ML)-based malware detectors against AME. AME quality is a key factor to the robustness enhancement. Generative Adversarial Network (GAN) is a kind of AME generation method, but the existing GAN-based AME generation methods have the issues of inadequate optimization, mode collapse and training instability. In this paper, we propose a novel approach (denote as LSGAN-AT) to enhance ML-based malware detector robustness against Adversarial Examples, which includes LSGAN module and AT module. LSGAN module can generate more effective and smoother AME by utilizing brand-new network structures and Least Square (LS) loss to optimize boundary samples. AT module makes adversarial training using AME generated by LSGAN to generate ML-based Robust Malware Detector (RMD). Extensive experiment results validate the better transferability of AME in terms of attacking 6 ML detectors and the RMD transferability in terms of resisting the MalGAN black-box attack. The results also verify the performance of the generated RMD in the recognition rate of AME.

Reward shaping is an effective technique for incorporating domain knowledge into reinforcement learning (RL). Existing approaches such as potential-based reward shaping normally make full use of a given shaping reward function. However, since the transformation of human knowledge into numeric reward values is often imperfect due to reasons such as human cognitive bias, completely utilizing the shaping reward function may fail to improve the performance of RL algorithms. In this paper, we consider the problem of adaptively utilizing a given shaping reward function. We formulate the utilization of shaping rewards as a bi-level optimization problem, where the lower level is to optimize policy using the shaping rewards and the upper level is to optimize a parameterized shaping weight function for true reward maximization. We formally derive the gradient of the expected true reward with respect to the shaping weight function parameters and accordingly propose three learning algorithms based on different assumptions. Experiments in sparse-reward cartpole and MuJoCo environments show that our algorithms can fully exploit beneficial shaping rewards, and meanwhile ignore unbeneficial shaping rewards or even transform them into beneficial ones.

Abstract Deep learning (DL) has exhibited its exceptional performance in fields like intrusion detection. Various augmentation methods have been proposed to improve data quality and eventually to enhance the performance of DL models. However, the classic augmentation methods cannot be applied to those DL models which exploit the system-call sequences to detect intrusion. Previously, the seq2seq model has been explored to augment system-call sequences. Following this work, we propose a gated convolutional neural network (GCNN) model to thoroughly extract the potential information of augmented sequences. Also, in order to enhance the model’s robustness, we adopt adversarial training to reduce the impact of adversarial examples on the model. Adversarial examples used in adversarial training are generated by the proposed adversarial sequence generation algorithm. The experimental results on different verified models show that GCNN model can better obtain the potential information of the augmented data and achieve the best performance. Furthermore, GCNN with adversarial training can enhance robustness significantly.

Machine learning (ML) algorithms provide better performance than traditional algorithms in various applications. However, some unknown flaws in ML classifiers make them sensitive to adversarial examples generated by adding small but fooled purposeful distortions to natural examples. This paper aims to investigate the transferability of adversarial examples generated on a sparse and structured dataset and the ability of adversarial training in resisting adversarial examples. The results demonstrate that adversarial examples generated by DNN can fool a set of ML classifiers such as decision tree, random forest, SVM, CNN and RNN. Also, adversarial training can improve the robustness of DNN in terms of resisting attacks.

It is known that multicast provisioning is important for supporting cloud-based applications, and as the traffics from these applications are increasing quickly, we may rely on optical networks to realize high-throughput multicast. Meanwhile, the flexible-grid elastic optical networks (EONs) achieve agile access to the massive bandwidth in optical fibers, and hence can provision variable bandwidths to adapt to the dynamic demands from the cloud-based applications. In this paper, we consider all-optical multicast in EONs in a practical manner and focus on designing impairment- and splitting-aware multicast provisioning schemes. We first study the procedure of adaptive modulation selection for a light-tree, and point out that the multicast scheme in EONs is fundamentally different from that in the fixed-grid wavelength-division multiplexing networks. Then, we formulate the problem of impairment- and splitting-aware routing, modulation and spectrum assignment (ISa-RMSA) for all-optical multicast in EONs and analyze its hardness. Next, we analyze the advantages brought by the flexibility of routing structures and discuss the ISa-RMSA schemes based on light-trees and light-forests. This paper suggests that for ISa-RMSA, the light-forest-based approach can use less bandwidth than the light-tree-based one, while still satisfying the quality of transmission requirement. Therefore, we establish the minimum light-forest problem for optimizing a light-forest in ISa-RMSA. Finally, we design several time-efficient ISa-RMSA algorithms, and prove that one of them can solve the minimum light-forest problem with a fixed approximation ratio.

This paper tries to solve the location-constrained virtual network embedding (LC-VNE) problem efficiently. We first investigate the complexity of LC-VNE, and by leveraging the graph bisection problem, we provide the first formal proof of the NP-completeness and inapproximability result of LC-VNE. Then, we propose two novel LC-VNE algorithms based on a compatibility graph (CG) to achieve integrated node and link mapping. In particular, in the CG, each node represents a candidate substrate path for a virtual link, and each link indicates the compatible relation between its two endnodes. Our theoretical analysis proves that the maximal clique in the CG is also the maximum one when the substrate network has sufficient resources. With CG, we reduce LC-VNE to the minimumcost maximum clique problem, which inspires us to propose two efficient LC-VNE heuristics. Extensive numerical simulations demonstrate that compared with the existing ones, our proposed LC-VNE algorithms have significantly reduced time complexity and can provide smaller gaps to the optimal solutions, lower blocking probabilities, and higher time-average revenue as well.

This paper proposes a novel quasi-cyclic low-density parity-check convolutional code, and a two-stage construction algorithm with modified progressive edge growth (PEG) method is provided. We propose both encoder and decoder implementation architecture for this code. The quasi-cyclic form provides the parallelism for encoder and decoder, which can increase the throughput and decrease the delay significantly. The proposed modified min-sum decoding algorithm can speed up the process of convergence and reduce the hardware complexity. We also designed a GPU based simulation platform to speed up about 200 times against CPU to verify the code performance. Simulation results show the proposed code can get 0.5~1dB coding gain and lower error floor compared with the LDPC codes in WiMAX standard with the same code length, while the decoder only has 20 iterators.

The traditional method of flow measuring has some shortcomings, which is difficult to accurately measure data. In view of this issue, this paper proposes a new design method of wind speed measuring device, which includes the design principle, impeller design, sensors heat insulation design and assembly design of the measuring device. The measurement devices are verified through wind tunnel test. The experimental data show that this new measuring devices can more accurately measure the flow of pulverized coal, which can be done online control of boiler combustion.

Planation Surface is one of very important issues in the geomorphological research, and plays a major role for reconstructing the evolutional history of landforms in local region. By using remote sensing and geographical information systems, this article discussed the creation of Digital Elevation Models (DEM) in the area of eastern Qilian Mountains, northeastern to Qinghai-Xizang Plateau, and integrtion of both DEM and Landset TM images. Then the characteristics of 3D geomorphological Imagery of the northeastern Qilian Mountains were discussed, and the topographic profiles at several parts of the DEM were got. On the basis of analyzing the system of geomorphological parameters on the planation surface, the exact extent of the planation surface on the eastern Qilian Mountain was got by using the supervised classification technique in the field of image processing. The great potential of this technique was discovered on the analysis of planaion.