Biblio

Malicious scripts are an important computer infection threat vector for computer users. For internet-scale processing, static analysis offers substantial computing efficiencies. We propose the ScriptNet system for neural malicious JavaScript detection which is based on static analysis. We also propose a novel deep learning model, Pre-Informant Learning (PIL), which processes Javascript files as byte sequences. Lower layers capture the sequential nature of these byte sequences while higher layers classify the resulting embedding as malicious or benign. Unlike previously proposed solutions, our model variants are trained in an end-to-end fashion allowing discriminative training even for the sequential processing layers. Evaluating this model on a large corpus of 212,408 JavaScript files indicates that the best performing PIL model offers a 98.10% true positive rate (TPR) for the first 60K byte subsequences and 81.66% for the full-length files, at a false positive rate (FPR) of 0.50%. Both models significantly outperform several baseline models. The best performing PIL model can successfully detect 92.02% of unknown malware samples in a hindsight experiment where the true labels of the malicious JavaScript files were not known when the model was trained.

Network dynamics, such as bandwidth fluctuation and unexpected latency, hurt users' quality of experience (QoE) greatly for media services over the Internet. In this work, we propose a neural adaptive transport (NAT) framework to tackle the network dynamics for Internet-scale interactive media services. The entire NAT system has three major components: a learning based cloud overlay routing (COR) scheme for the best delivery path to bypass the network bottlenecks while offering the minimal end-to-end latency simultaneously; a residual neural network based collaborative video processing (CVP) system to trade the computational capability at client-end for QoE improvement via learned resolution scaling; and a deep reinforcement learning (DRL) based adaptive real-time streaming (ARS) strategy to select the appropriate video bitrate for maximal QoE. We have demonstrated that COR could improve the user satisfaction from 5% to 43%, CVP could reduce the bandwidth consumption more than 30% at the same quality, and DRL-based ARS can maintain the smooth streaming with \textbackslashtextless; 50% QoE improvement, respectively.

In the paper, our research of abnormal bus data analysis of intelligent and connected vehicle aims to detect the abnormal data rapidly and accurately generated by the hackers who send malicious commands to attack vehicles through three patterns, including remote non-contact, short-range non-contact and contact. The research routine is as follows: Take the bus data of 10 different brands of intelligent and connected vehicles through the real vehicle experiments as the research foundation, set up the optimized neural network, collect 1000 sets of the normal bus data of 15 kinds of driving scenarios and the other 300 groups covering the abnormal bus data generated by attacking the three systems which are most common in the intelligent and connected vehicles as the training set. In the end after repeated amendments, with 0.5 seconds per detection, the intrusion detection system has been attained in which for the controlling system the abnormal bus data is detected at the accuracy rate of 96% and the normal data is detected at the accuracy rate of 90%, for the body system the abnormal one is 87% and the normal one is 80%, for the entertainment system the abnormal one is 80% and the normal one is 65%.

In view of the problem that the health status and safety monitoring of the traditional intelligent home are mainly dependent on the manual inspection, this paper introduces the intelligent home-based remote monitoring system by introducing the Internet-based Internet of Things technology into the intelligent home condition monitoring and safety assessment. The system's Android remote operation based on the MVP model to develop applications, the use of neural networks to deal with users daily use of operational data to establish the network data model, combined with S3C2440A microcontrollers in the gateway to the embedded Linux to facilitate different intelligent home drivers development. Finally, the power line communication network is used to connect the intelligent electrical appliances to the gateway. By calculating the success rate of the routing nodes, the success rate of the network nodes of 15 intelligent devices is 98.33%. The system can intelligent home many electrical appliances at the same time monitoring, to solve the system data and network congestion caused by the problem can not he security monitoring.

In this paper, decentralized dynamic power allocation problem has been investigated for mobile ad hoc network (MANET) at tactical edge. Due to the mobility and self-organizing features in MANET and environmental uncertainties in the battlefield, many existing optimal power allocation algorithms are neither efficient nor practical. Furthermore, the continuously increasing large scale of the wireless connection population in emerging Internet of Battlefield Things (IoBT) introduces additional challenges for optimal power allocation due to the “Curse of Dimensionality”. In order to address these challenges, a novel Actor-Critic-Mass algorithm is proposed by integrating the emerging Mean Field game theory with online reinforcement learning. The proposed approach is able to not only learn the optimal power allocation for IoBT in a decentralized manner, but also effectively handle uncertainties from harsh environment at tactical edge. In the developed scheme, each agent in IoBT has three neural networks (NN), i.e., 1) Critic NN learns the optimal cost function that minimizes the Signal-to-interference-plus-noise ratio (SINR), 2) Actor NN estimates the optimal transmitter power adjustment rate, and 3) Mass NN learns the probability density function of all agents' transmitting power in IoBT. The three NNs are tuned based on the Fokker-Planck-Kolmogorov (FPK) and Hamiltonian-Jacobian-Bellman (HJB) equation given in the Mean Field game theory. An IoBT wireless network has been simulated to evaluate the effectiveness of the proposed algorithm. The results demonstrate that the actor-critic-mass algorithm can effectively approximate the probability distribution of all agents' transmission power and converge to the target SINR. Moreover, the optimal decentralized power allocation is obtained through integrated mean-field game theory with reinforcement learning.

The notion of integrated circuit split manufacturing which delegates the front-end-of-line (FEOL) and back-end-of-line (BEOL) parts to different foundries, is to prevent overproduction, piracy of the intellectual property (IP), or targeted insertion of hardware Trojans by adversaries in the FEOL facility. In this work, we challenge the security promise of split manufacturing by formulating various layout-level placement and routing hints as vector- and image-based features. We construct a sophisticated deep neural network which can infer the missing BEOL connections with high accuracy. Compared with the publicly available network-flow attack [1], for the same set of ISCAS-85benchmarks, we achieve 1.21× accuracy when splitting on M1 and 1.12× accuracy when splitting on M3 with less than 1% running time.

Deep neural networks are widely used in many walks of life. Techniques such as transfer learning enable neural networks pre-trained on certain tasks to be retrained for a new duty, often with much less data. Users have access to both pre-trained model parameters and model definitions along with testing data but have either limited access to training data or just a subset of it. This is risky for system-critical applications, where adversarial information can be maliciously included during the training phase to attack the system. Determining the existence and level of attack in a model is challenging. In this paper, we present evidence on how adversarially attacking training data increases the boundary of model parameters using as an example of a CNN model and the MNIST data set as a test. This expansion is due to new characteristics of the poisonous data that are added to the training data. Approaching the problem from the feature space learned by the network provides a relation between them and the possible parameters taken by the model on the training phase. An algorithm is proposed to determine if a given network was attacked in the training by comparing the boundaries of parameters distribution on intermediate layers of the model estimated by using the Maximum Entropy Principle and the Variational inference approach.

Internet application providers now have more incentive than ever to collect user data, which greatly increases the risk of user privacy violations due to the emerging of deep neural networks. In this paper, we propose TensorClog-a poisoning attack technique that is designed for privacy protection against deep neural networks. TensorClog has three properties with each of them serving a privacy protection purpose: 1) training on TensorClog poisoned data results in lower inference accuracy, reducing the incentive of abusive data collection; 2) training on TensorClog poisoned data converges to a larger loss, which prevents the neural network from learning the privacy; and 3) TensorClog regularizes the perturbation to remain a high structure similarity, so that the poisoning does not affect the actual content in the data. Applying our TensorClog poisoning technique to CIFAR-10 dataset results in an increase in both converged training loss and test error by 300% and 272%, respectively. It manages to maintain data's human perception with a high SSIM index of 0.9905. More experiments including different limited information attack scenarios and a real-world application transferred from pre-trained ImageNet models are presented to further evaluate TensorClog's effectiveness in more complex situations.

Recent changes to greenhouse gas emission policies are catalyzing the electric vehicle (EV) market making it readily accessible to consumers. While there are challenges that arise with dense deployment of EVs, one of the major future concerns is cyber security threat. In this paper, cyber security threats in the form of tampering with EV battery's State of Charge (SOC) was explored. A Back Propagation (BP) Neural Network (NN) was trained and tested based on experimental data to estimate SOC of battery under normal operation and cyber-attack scenarios. NeuralWare software was used to run scenarios. Different statistic metrics of the predicted values were compared against the actual values of the specific battery tested to measure the stability and accuracy of the proposed BP network under different operating conditions. The results showed that BP NN was able to capture and detect the false entries due to a cyber-attack on its network.

Predicting software faults before software testing activities can help rational distribution of time and resources. Software metrics are used for software fault prediction due to their close relationship with software faults. Thanks to the non-linear fitting ability, Neural networks are increasingly used in the prediction model. We first filter metric set of the embedded software by statistical methods to reduce the dimensions of model input. Then we build a back propagation neural network with simple structure but good performance and apply it to two practical embedded software projects. The verification results show that the model has good ability to predict software faults.

With widely applied in various fields, deep learning (DL) is becoming the key driving force in industry. Although it has achieved great success in artificial intelligence tasks, similar to traditional software, it has defects that, once it failed, unpredictable accidents and losses would be caused. In this paper, we propose a test cases generation technique based on an adversarial samples generation algorithm for image classification deep neural networks (DNNs), which can generate a large number of good test cases for the testing of DNNs, especially in case that test cases are insufficient. We briefly introduce our method, and implement the framework. We conduct experiments on some classic DNN models and datasets. We further evaluate the test set by using a coverage metric based on states of the DNN.

The Internet of Vehicles (IoV) will connect not only mobile devices with vehicles, but it will also connect vehicles with each other, and with smart offices, buildings, homes, theaters, shopping malls, and cities. The IoV facilitates optimal and reliable communication services to connected vehicles in smart cities. The backbone of connected vehicles communication is the critical V2X infrastructures deployment. The spectrum utilization depends on the demand by the end users and the development of infrastructure that includes efficient automation techniques together with the Internet of Things (IoT). The infrastructure enables us to build smart environments for spectrum utilization, which we refer to as Smart Spectrum Utilization (SSU). This paper presents an integrated system consisting of SSU with IoV. However, the tasks of securing IoV and protecting it from cyber attacks present considerable challenges. This paper introduces an IoV security system using deep learning approach to develop secure applications and reliable services. Deep learning composed of unsupervised learning and supervised learning, could optimize the IoV security system. The deep learning methodology is applied to monitor security threats. Results from simulations show that the monitoring accuracy of the proposed security system is superior to that of the traditional system.

With the deep integration of industrial control systems and Internet technologies, how to effectively detect whether industrial control systems are threatened by intrusion is a difficult problem in industrial security research. Aiming at the difficulty of high dimensionality and non-linearity of industrial control system network data, the stacked auto-encoder is used to extract the network data features, and the multi-classification support vector machine is used for classification. The research results show that the accuracy of the intrusion detection model reaches 95.8%.

This paper describes a machine assistance approach to grading decisions for values that might be missing or need validation, using a mathematical algebraic form of an Expert System, instead of the traditional textual or logic forms and builds a neural network computational graph structure. This Experts System approach is also structured into a neural network like format of: input, hidden and output layers that provide a structured approach to the knowledge-base organization, this provides a useful abstraction for reuse for data migration applications in big data, Cyber and relational databases. The approach is further enhanced with a Bayesian probability tree approach to grade the confidences of value probabilities, instead of the traditional grading of the rule probabilities, and estimates the most probable value in light of all evidence presented. This is ground work for a Machine Learning (ML) experts system approach in a form that is closer to a Neural Network node structure.

The world is fundamentally compositional, so it is natural to think of visual recognition as the recognition of basic visually primitives that are composed according to well-defined rules. This strategy allows us to recognize unseen complex concepts from simple visual primitives. However, the current trend in visual recognition follows a data greedy approach where huge amounts of data are required to learn models for any desired visual concept. In this paper, we build on the compositionality principle and develop an "algebra" to compose classifiers for complex visual concepts. To this end, we learn neural network modules to perform boolean algebra operations on simple visual classifiers. Since these modules form a complete functional set, a classifier for any complex visual concept defined as a boolean expression of primitives can be obtained by recursively applying the learned modules, even if we do not have a single training sample. As our experiments show, using such a framework, we can compose classifiers for complex visual concepts outperforming standard baselines on two well-known visual recognition benchmarks. Finally, we present a qualitative analysis of our method and its properties.

We formulate a tracker which performs incessant decision making in order to track objects where the objects may undergo different challenges such as partial occlusions, moving camera, cluttered background etc. In the process, the agent must make a decision on whether to keep track of the object when it is occluded or has moved out of the frame temporarily based on its prediction from the previous location or to reinitialize the tracker based on the belief that the target has been lost. Instead of the heuristic methods we depend on reward and penalty based training that helps the agent reach an optimal solution via this partially observable Markov decision making (POMDP). Furthermore, we employ deeply learned compositional model to estimate human pose in order to better handle occlusion without needing human inputs. By learning compositionality of human bodies via deep neural network the agent can make better decision on presence of human in a frame or lack thereof under occlusion. We adapt skeleton based part representation and do away with the large spatial state requirement. This especially helps in cases where orientation of the target in focus is unorthodox. Finally we demonstrate that the deep reinforcement learning based training coupled with pose estimation capabilities allows us to train and tag multiple large video datasets much quicker than previous works.

Although sequence-to-sequence attentional neural machine translation (NMT) has achieved great progress recently, it is confronted with two challenges: learning optimal model parameters for long parallel sentences and well exploiting different scopes of contexts. In this paper, partially inspired by the idea of segmenting a long sentence into short clauses, each of which can be easily translated by NMT, we propose a hierarchy-to-sequence attentional NMT model to handle these two challenges. Our encoder takes the segmented clause sequence as input and explores a hierarchical neural network structure to model words, clauses, and sentences at different levels, particularly with two layers of recurrent neural networks modeling semantic compositionality at the word and clause level. Correspondingly, the decoder sequentially translates segmented clauses and simultaneously applies two types of attention models to capture contexts of interclause and intraclause for translation prediction. In this way, we can not only improve parameter learning, but also well explore different scopes of contexts for translation. Experimental results on Chinese-English and English-German translation demonstrate the superiorities of the proposed model over the conventional NMT model.

Neural architectures are the foundation for improving performance of deep neural networks (DNNs). This paper presents deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs. The proposed architectures integrate compositionality and reconfigurability of the former and the capability of learning rich features of the latter in a principled way. We utilize AND-OR Grammar (AOG) as network generator in this paper and call the resulting networks AOGNets. An AOGNet consists of a number of stages each of which is composed of a number of AOG building blocks. An AOG building block splits its input feature map into N groups along feature channels and then treat it as a sentence of N words. It then jointly realizes a phrase structure grammar and a dependency grammar in bottom-up parsing the “sentence” for better feature exploration and reuse. It provides a unified framework for the best practices developed in state-of-the-art DNNs. In experiments, AOGNet is tested in the ImageNet-1K classification benchmark and the MS-COCO object detection and segmentation benchmark. In ImageNet-1K, AOGNet obtains better performance than ResNet and most of its variants, ResNeXt and its attention based variants such as SENet, DenseNet and DualPathNet. AOGNet also obtains the best model interpretability score using network dissection. AOGNet further shows better potential in adversarial defense. In MS-COCO, AOGNet obtains better performance than the ResNet and ResNeXt backbones in Mask R-CNN.

Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs of varying sophistication, the defense-attack arms race has been accelerated. In this paper, we present MODEF, a cross-layer model diversity ensemble framework. MODEF intelligently combines unsupervised model denoising ensemble with supervised model verification ensemble by quantifying model diversity, aiming to boost the robustness of the target model against adversarial examples. Evaluated using eleven representative attacks on popular benchmark datasets, we show that MODEF achieves remarkable defense success rates, compared with existing defense methods, and provides a superior capability of repairing adversarial inputs and making correct predictions with high accuracy in the presence of black-box attacks.

CAPTCHA is a web-based authentication method used by websites to distinguish between humans (valid users) and bots (attackers). Audio captcha is an accessible captcha meant for the visually disabled section of users such as color-blind, blind, near-sighted users. Firstly, this paper analyzes how secure current audio captchas are from attacks using machine learning (ML) and deep learning (DL) models. Each audio captcha is made up of five, seven or ten random digits[0-9] spoken one after the other along with varying background noise throughout the length of the audio. If the ML or DL model is able to correctly identify all spoken digits and in the correct order of occurance in a single audio captcha, we consider that captcha to be broken and the attack to be successful. Throughout the paper, accuracy refers to the attack model's success at breaking audio captchas. The higher the attack accuracy, the more unsecure the audio captchas are. In our baseline experiments, we found that attack models could break audio captchas that had no background noise or medium background noise with any number of spoken digits with nearly 99% to 100% accuracy. Whereas, audio captchas with high background noise were relatively more secure with attack accuracy of 85%. Secondly, we propose that the concepts of adversarial examples algorithms can be used to create a new kind of audio captcha that is more resilient towards attacks. We found that even after retraining the models on the new adversarial audio data, the attack accuracy remained as low as 25% to 36% only. Lastly, we explore the benefits of creating adversarial audio captcha through different algorithms such as Basic Iterative Method (BIM) and deepFool. We found that as long as the attacker has less than 45% sample from each kinds of adversarial audio datasets, the defense will be successful at preventing attacks.

In this paper, the two methods for ciphering are presented and compared. The aim is to reveal the suitability of chaotic neural network approach to ciphering compared to AES cipher. The durations in seconds of both methods are presented and the two methods are compared. The results show, that the chaotic neural network is fast, suitable for ciphering of short plaintexts. AES ciphering is suitable for longer plaintexts or images and is also more reliable.

We introduce a novel distributed derivative-free optimization framework that is resilient to stragglers. The proposed method employs coded search directions at which the objective function is evaluated, and a decoding step to find the next iterate. Our framework can be seen as an extension of evolution strategies and structured exploration methods where structured search directions were utilized. As an application, we consider black-box adversarial attacks on deep convolutional neural networks. Our numerical experiments demonstrate a significant improvement in the computation times.

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.

As automatic speech recognition (ASR) systems have been integrated into a diverse set of devices around us in recent years, security vulnerabilities of them have become an increasing concern for the public. Existing studies have demonstrated that deep neural networks (DNNs), acting as the computation core of ASR systems, is vulnerable to deliberately designed adversarial attacks. Based on the gradient descent algorithm, existing studies have successfully generated adversarial samples which can disturb ASR systems and produce adversary-expected transcript texts designed by adversaries. Most of these research simulated white-box attacks which require knowledge of all the components in the targeted ASR systems. In this work, we propose the first semi-black-box attack against the ASR system - Kaldi. Requiring only partial information from Kaldi and none from DNN, we can embed malicious commands into a single audio chip based on the gradient-independent genetic algorithm. The crafted audio clip could be recognized as the embedded malicious commands by Kaldi and unnoticeable to humans in the meanwhile. Experiments show that our attack can achieve high attack success rate with unnoticeable perturbations to three types of audio clips (pop music, pure music, and human command) without the need of the underlying DNN model parameters and architecture.

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.