Biblio

Cloud Data Center (CDC) security remains a major challenge for business organizations and takes an important concern with research works. The attacker purpose is to guarantee the service unavailability and maximize the financial loss costs. As a result, Distributed Denial of Service (DDoS) attacks have appeared as the most popular attack. The main aim of such attacks is to saturate and overload the system network through a massive data packets size flooding toward a victim server and to block the service to users. This paper provides a defending system in order to mitigate the Denial of Service (DoS) attack in CDC environment. Basically it outlines the different techniques of DoS attacks and its countermeasures by combining the filtering and detection mechanisms. We presented an analytical model based on queueing model to evaluate the impact of flooding attack on cloud environment regarding service availability and QoS performance. Consequently, we have plotted the response time, throughput, drop rate and resource computing utilization varying the attack arrival rate. We have used JMT (Java Modeling Tool) simulator to validate the analytical model. Our approach was appeared powerful for attacks mitigation in the cloud environment.

Intrusion detection systems do not perform well when it comes to detecting zero-day attacks, therefore improving their performance in that regard is an active research topic. In this study, to detect zero-day attacks with high accuracy, we proposed two deep learning based anomaly detection models using autoencoder and denoising autoencoder respectively. The key factor that directly affects the accuracy of the proposed models is the threshold value which was determined using a stochastic approach rather than the approaches available in the current literature. The proposed models were tested using the KDDTest+ dataset contained in NSL-KDD, and we achieved an accuracy of 88.28% and 88.65% respectively. The obtained results show that, as a singular model, our proposed anomaly detection models outperform any other singular anomaly detection methods and they perform almost the same as the newly suggested hybrid anomaly detection models.

Software development for Cyber-Physical Systems (CPS), e.g., autonomous vehicles, requires both functional and non-functional quality assurance to guarantee that the CPS operates safely and effectively. EAST-ADL is a domain specific architectural language dedicated to safety-critical automotive embedded system design. We have previously modified EAST-ADL to include energy constraints and transformed energy-aware real-time (ERT) behaviors modeled in EAST-ADL/Stateflow into UPPAAL models amenable to formal verification. Previous work is extended in this paper by including support for Simulink and an integration of Simulink/Stateflow (S/S) within the same too lchain. S/S models are transformed, based on the extended ERT constraints with probability parameters, into verifiable UPPAAL-SMC models and integrate the translation with formal statistical analysis techniques: Probabilistic extension of EAST-ADL constraints is defined as a semantics denotation. A set of mapping rules is proposed to facilitate the guarantee of translation. Formal analysis on both functional- and non-functional properties is performed using Simulink Design Verifier and UPPAAL-SMC. Our approach is demonstrated on the autonomous traffic sign recognition vehicle case study.

We present a formal method for computing the best security provisioning for Internet of Things (IoT) scenarios characterized by a high degree of mobility. The security infrastructure is intended as a security resource allocation plan, computed as the solution of an optimization problem that minimizes the risk of having IoT devices not monitored by any resource. We employ the shortfall as a risk measure, a concept mostly used in the economics, and adapt it to our scenario. We show how to compute and evaluate an allocation plan, and how such security solutions address the continuous topology changes that affect an IoT environment.

In this study, it is proposed to carry out an efficient formulation in order to figure out the stochastic security-constrained generation capacity expansion planning (SC-GCEP) problem. The main idea is related to directly compute the line outage distribution factors (LODF) which could be applied to model the N - m post-contingency analysis. In addition, the post-contingency power flows are modeled based on the LODF and the partial transmission distribution factors (PTDF). The post-contingency constraints have been reformulated using linear distribution factors (PTDF and LODF) so that both the pre- and post-contingency constraints are modeled simultaneously in the SC-GCEP problem using these factors. In the stochastic formulation, the load uncertainty is incorporated employing a two-stage multi-period framework, and a K - means clustering technique is implemented to decrease the number of load scenarios. The main advantage of this methodology is the feasibility to quickly compute the post-contingency factors especially with multiple-line outages (N - m). This concept would improve the security-constraint analysis modeling quickly the outage of m transmission lines in the stochastic SC-GCEP problem. It is carried out several experiments using two electrical power systems in order to validate the performance of the proposed formulation.

This study proposes to apply an efficient formulation to solve the stochastic security-constrained generation capacity expansion planning (GCEP) problem using an improved method to directly compute the generalized generation distribution factors (GGDF) and the line outage distribution factors (LODF) in order to model the pre- and the post-contingency constraints based on the only application of the partial transmission distribution factors (PTDF). The classical DC-based formulation has been reformulated in order to include the security criteria solving both pre- and post-contingency constraints simultaneously. The methodology also takes into account the load uncertainty in the optimization problem using a two-stage multi-period model, and a clustering technique is used as well to reduce load scenarios (stochastic problem). The main advantage of this methodology is the feasibility to quickly compute the LODF especially with multiple-line outages (N-m). This idea could speed up contingency analyses and improve significantly the security-constrained analyses applied to GCEP problems. It is worth to mentioning that this approach is carried out without sacrificing optimality.

This paper presents a 28nm SoC with a programmable FC-DNN accelerator design that demonstrates: (1) HW support to exploit data sparsity by eliding unnecessary computations (4× energy reduction); (2) improved algorithmic error tolerance using sign-magnitude number format for weights and datapath computation; (3) improved circuit-level timing violation tolerance in datapath logic via timeborrowing; (4) combined circuit and algorithmic resilience with Razor timing violation detection to reduce energy via VDD scaling or increase throughput via FCLK scaling; and (5) high classification accuracy (98.36% for MNIST test set) while tolerating aggregate timing violation rates \textbackslashtextgreater10-1. The accelerator achieves a minimum energy of 0.36μJ/pred at 667MHz, maximum throughput at 1.2GHz and 0.57μJ/pred, or a 10%-margined operating point at 1GHz and 0.58μJ/pred.

Stochastic Computing (SC) is an alternative design paradigm particularly useful for applications where cost is critical. SC has been applied to neural networks, as neural networks are known for their high computational complexity. However previous work in this area has critical limitations such as the fully-parallel architecture assumption, which prevent them from being applicable to recent ones such as convolutional neural networks, or ConvNets. This paper presents the first SC architecture for ConvNets, shows its feasibility, with detailed analyses of implementation overheads. Our SC-ConvNet is a hybrid between SC and conventional binary design, which is a marked difference from earlier SC-based neural networks. Though this might seem like a compromise, it is a novel feature driven by the need to support modern ConvNets at scale, which commonly have many, large layers. Our proposed architecture also features hybrid layer composition, which helps achieve very high recognition accuracy. Our detailed evaluation results involving functional simulation and RTL synthesis suggest that SC-ConvNets are indeed competitive with conventional binary designs, even without considering inherent error resilience of SC.

State-of-the-art convolutional neural networks (ConvNets) are now able to achieve near human performance on a wide range of classification tasks. Unfortunately, current hardware implementations of ConvNets are memory power intensive, prohibiting deployment in low-power embedded systems and IoE platforms. One method of reducing memory power is to exploit the error resilience of ConvNets and accept bit errors under reduced supply voltages. In this paper, we extensively study the effectiveness of this idea and show that further savings are possible by injecting bit errors during ConvNet training. Measurements on an 8KB SRAM in 28nm UTBB FD-SOI CMOS demonstrate supply voltage reduction of 310mV, which results in up to 5.4× leakage power reduction and up to 2.9× memory access power reduction at 99% of floating-point classification accuracy, with no additional hardware cost. To our knowledge, this is the first silicon-validated study on the effect of bit errors in ConvNets.

The evolution of convolutional neural networks (CNNs) into more complex forms of organization, with additional layers, larger convolutions and increasing connections, established the state-of-the-art in terms of accuracy errors for detection and classification challenges in images. Moreover, as they evolved to a point where Gigabytes of memory are required for their operation, we have reached a stage where it becomes fundamental to understand how their inference capabilities can be impaired if data elements somehow become corrupted in memory. This paper introduces fault-injection in these systems by simulating failing bit-cells in hardware memories brought on by relaxing the 100% reliable operation assumption. We analyze the behavior of these networks calculating inference under severe fault-injection rates and apply fault mitigation strategies to improve on the CNNs resilience. For the MNIST dataset, we show that 8x less memory is required for the feature maps memory space, and that in sub-100% reliable operation, fault-injection rates up to 10-1 (with most significant bit protection) can withstand only a 1% error probability degradation. Furthermore, considering the offload of the feature maps memory to an embedded dynamic RAM (eDRAM) system, using technology nodes from 65 down to 28 nm, up to 73 80% improved power efficiency can be obtained.

As a problem solving method, neural networks have shown broad applicability from medical applications, speech recognition, and natural language processing. This success has even led to implementation of neural network algorithms into hardware. In this paper, we explore two questions: (a) to what extent microelectronic variations affects the quality of results by neural networks; and (b) if the answer to first question represents an opportunity to optimize the implementation of neural network algorithms. Regarding first question, variations are now increasingly common in aggressive process nodes and typically manifest as an increased frequency of timing errors. Combating variations - due to process and/or operating conditions - usually results in increased guardbands in circuit and architectural design, thus reducing the gains from process technology advances. Given the inherent resilience of neural networks due to adaptation of their learning parameters, one would expect the quality of results produced by neural networks to be relatively insensitive to the rising timing error rates caused by increased variations. On the contrary, using two frequently used neural networks (MLP and CNN), our results show that variations can significantly affect the inference accuracy. This paper outlines our assessment methodology and use of a cross-layer evaluation approach that extracts hardware-level errors from twenty different operating conditions and then inject such errors back to the software layer in an attempt to answer the second question posed above.

The assessment of networks is frequently accomplished by using time-consuming analysis tools based on simulations. For example, the blocking probability of networks can be estimated by Monte Carlo simulations and the network resilience can be assessed by link or node failure simulations. We propose in this paper to use Artificial Neural Networks (ANN) to predict the robustness of networks based on simple topological metrics to avoid time-consuming failure simulations. We accomplish the training process using supervised learning based on a historical database of networks. We compare the results of our proposal with the outcome provided by targeted and random failures simulations. We show that our approach is faster than failure simulators and the ANN can mimic the same robustness evaluation provide by these simulators. We obtained an average speedup of 300 times.

Resilience in High Performance Computing (HPC) is a constraining factor for bringing applications to the upcoming exascale systems. Resilience techniques must be able to scale to handle the increasing number of expected errors in an energy efficient manner. Since the purpose of running applications on HPC systems is to perform large scale computations as quick as possible, resilience methods should not add a large delay to the time to completion of the application. In this paper we introduce a novel technique to detect and recover from transient errors in HPC applications. One of the features of our technique is that the energy budget allocated to resilience can be adjusted depending on the operator's resilience needs. For example, on synthetic data, the technique can detect about 50% of transient errors while only using 20% of the dynamic energy required for running the application. For a 60% energy budget, an application that uses 10k cores and takes 128 hours to run, will only require 10% longer to complete.

Due to the recent progress in deep learning and neural acceleration architectures, specialized deep neural network or convolutional neural network (CNNs) accelerators are expected to provide an energy-efficient solution for real-time vision/speech processing. recognition and a wide spectrum of approximate computing applications. In addition to their wide applicability scope, we also found that the fascinating feature of deterministic performance and high energy-efficiency, makes such deep learning (DL) accelerators ideal candidates as application-processor IPs in embedded SoCs concerned with real-time processing. However, unlike traditional accelerator designs, DL accelerators introduce a new aspect of design trade-off between real-time processing (QoS) and computation approximation (QoR) into embedded systems. This work proposes an elastic CNN acceleration architecture that automatically adapts to the hard QoS constraint by exploiting the error-resilience in typical approximate computing workloads For the first time, the proposed design, including network tuning-and-mapping software and reconfigurable accelerator hardware, aims to reconcile the design constraint of QoS and Quality of Result (QoR). which are respectively the key concerns in real-time and approximate computing. It is shown in experiments that the proposed architecture enables the embedded system to work flexibly in an expanded operating space, significantly enhances its real-time ability. and maximizes the energy-efficiency of system within the user-specified QoS-QoR constraint through self-reconfiguration.

Deep learning neural networks (DNNs) have been successful in solving a wide range of machine learning problems. Specialized hardware accelerators have been proposed to accelerate the execution of DNN algorithms for high-performance and energy efficiency. Recently, they have been deployed in datacenters (potentially for business-critical or industrial applications) and safety-critical systems such as self-driving cars. Soft errors caused by high-energy particles have been increasing in hardware systems, and these can lead to catastrophic failures in DNN systems. Traditional methods for building resilient systems, e.g., Triple Modular Redundancy (TMR), are agnostic of the DNN algorithm and the DNN accelerator's architecture. Hence, these traditional resilience approaches incur high overheads, which makes them challenging to deploy. In this paper, we experimentally evaluate the resilience characteristics of DNN systems (i.e., DNN software running on specialized accelerators). We find that the error resilience of a DNN system depends on the data types, values, data reuses, and types of layers in the design. Based on our observations, we propose two efficient protection techniques for DNN systems.

Phasor measurement units (PMUs) provide high-fidelity situational awareness of electric power grid operations. PMU data are used in real-time to inform wide area state estimation, monitor area control error, and event detection. As PMU data becomes more reliable, these devices are finding roles within control systems such as demand response programs and early fault detection systems. As with other cyber physical systems, maintaining data integrity and security are significant challenges for power system operators. In this paper, we present a comprehensive study of multiple machine learning techniques for detecting malicious data injection within PMU data streams. The two datasets used in this study are from the Bonneville Power Administration's PMU network and an inter-university PMU network among three universities, located in the U.S. Pacific Northwest. These datasets contain data from both the transmission level and the distribution level. Our results show that both SVM and ANN are generally effective in detecting spoofed data, and TensorFlow, the newly released tool, demonstrates potential for distributing the training workload and achieving higher performance. We expect these results to shed light on future work of adopting machine learning and data analytics techniques in the electric power industry.

Due to the large volumes of data that need to be processed, efficient memory access and data transmission are crucial for high-performance implementations of convolutional neural networks (CNNs). Approximate memory is a promising technique to achieve efficient memory access and data transmission in CNN hardware implementations. To assess the feasibility of applying approximate memory techniques, we propose a framework for the data resilience evaluation (DRE) of CNNs and verify its effectiveness on a suite of prevalent CNNs. Simulation results show that a high degree of data resilience exists in these networks. By scaling the bit-width of the first five dominant data subsets, the data volume can be reduced by 80.38% on average with a 2.69% loss in relative prediction accuracy. For approximate memory with random errors, all the synaptic weights can be stored in the approximate part when the error rate is less than 10–4, while 3 MSBs must be protected if the error rate is fixed at 10–3. These results indicate a great potential for exploiting approximate memory techniques in CNN hardware design.

As the era of cloud technology arises, more and more people are beginning to migrate their applications and personal data to the cloud. This makes web-based applications an attractive target for cyber-attacks. As a result, web-based applications now need more protections than ever. However, current anomaly-based web attack detection approaches face the difficulties like unsatisfying accuracy and lack of generalization. And the rule-based web attack detection can hardly fight unknown attacks and is relatively easy to bypass. Therefore, we propose a novel deep learning approach to detect anomalous requests. Our approach is to first train two Recurrent Neural Networks (RNNs) with the complicated recurrent unit (LSTM unit or GRU unit) to learn the normal request patterns using only normal requests unsupervisedly and then supervisedly train a neural network classifier which takes the output of RNNs as the input to discriminate between anomalous and normal requests. We tested our model on two datasets and the results showed that our model was competitive with the state-of-the-art. Our approach frees us from feature selection. Also to the best of our knowledge, this is the first time that the RNN is applied on anomaly-based web attack detection systems.

In this paper, we focus on fraud detection on a signed graph with only a small set of labeled training data. We propose a novel framework that combines deep neural networks and spectral graph analysis. In particular, we use the node projection (called as spectral coordinate) in the low dimensional spectral space of the graph's adjacency matrix as the input of deep neural networks. Spectral coordinates in the spectral space capture the most useful topology information of the network. Due to the small dimension of spectral coordinates (compared with the dimension of the adjacency matrix derived from a graph), training deep neural networks becomes feasible. We develop and evaluate two neural networks, deep autoencoder and convolutional neural network, in our fraud detection framework. Experimental results on a real signed graph show that our spectrum based deep neural networks are effective in fraud detection.

The problem of cross-platform binary code similarity detection aims at detecting whether two binary functions coming from different platforms are similar or not. It has many security applications, including plagiarism detection, malware detection, vulnerability search, etc. Existing approaches rely on approximate graph-matching algorithms, which are inevitably slow and sometimes inaccurate, and hard to adapt to a new task. To address these issues, in this work, we propose a novel neural network-based approach to compute the embedding, i.e., a numeric vector, based on the control flow graph of each binary function, then the similarity detection can be done efficiently by measuring the distance between the embeddings for two functions. We implement a prototype called Gemini. Our extensive evaluation shows that Gemini outperforms the state-of-the-art approaches by large margins with respect to similarity detection accuracy. Further, Gemini can speed up prior art's embedding generation time by 3 to 4 orders of magnitude and reduce the required training time from more than 1 week down to 30 minutes to 10 hours. Our real world case studies demonstrate that Gemini can identify significantly more vulnerable firmware images than the state-of-the-art, i.e., Genius. Our research showcases a successful application of deep learning on computer security problems.

VANET network is a new technology on which future intelligent transport systems are based; its purpose is to develop the vehicular environment and make it more comfortable. In addition, it provides more safety for drivers and cars on the road. Therefore, we have to make this technology as secured as possible against many threats. As VANET is a subclass of MANET, it has inherited many security problems but with a different architecture and DOS attacks are one of them. In this paper, we have focused on DOS attacks that prevent users to receive the right information at the right moment. We have analyzed DOS attacks behavior and effects on the network using different mathematical models in order to find an efficient solution.

This paper presents a method to extract important byte sequences in malware samples by application of convolutional neural network (CNN) to images converted from binary data. This method, by combining a technique called the attention mechanism into CNN, enables calculation of an "attention map," which shows regions having higher importance for classification in the image. The extracted region with higher importance can provide useful information for human analysts who investigate the functionalities of unknown malware samples. Results of our evaluation experiment using malware dataset show that the proposed method provides higher classification accuracy than a conventional method. Furthermore, analysis of malware samples based on the calculated attention map confirmed that the extracted sequences provide useful information for manual analysis.

Deep neural networks (DNNs) are one of the most prominent technologies of our time, as they achieve state-of-the-art performance in many machine learning tasks, including but not limited to image classification, text mining, and speech processing. However, recent research on DNNs has indicated ever-increasing concern on the robustness to adversarial examples, especially for security-critical tasks such as traffic sign identification for autonomous driving. Studies have unveiled the vulnerability of a well-trained DNN by demonstrating the ability of generating barely noticeable (to both human and machines) adversarial images that lead to misclassification. Furthermore, researchers have shown that these adversarial images are highly transferable by simply training and attacking a substitute model built upon the target model, known as a black-box attack to DNNs. Similar to the setting of training substitute models, in this paper we propose an effective black-box attack that also only has access to the input (images) and the output (confidence scores) of a targeted DNN. However, different from leveraging attack transferability from substitute models, we propose zeroth order optimization (ZOO) based attacks to directly estimate the gradients of the targeted DNN for generating adversarial examples. We use zeroth order stochastic coordinate descent along with dimension reduction, hierarchical attack and importance sampling techniques to efficiently attack black-box models. By exploiting zeroth order optimization, improved attacks to the targeted DNN can be accomplished, sparing the need for training substitute models and avoiding the loss in attack transferability. Experimental results on MNIST, CIFAR10 and ImageNet show that the proposed ZOO attack is as effective as the state-of-the-art white-box attack (e.g., Carlini and Wagner's attack) and significantly outperforms existing black-box attacks via substitute models.

Cryptanalysis (the study of methods to read encrypted information without knowledge of the encryption key) has traditionally been separated into mathematical analysis of weaknesses in cryptographic algorithms, on the one hand, and side-channel attacks which aim to exploit weaknesses in the implementation of encryption and decryption algorithms. Mathematical analysis generally makes assumptions about the algorithm with the aim of reconstructing the key relating plain text to cipher text through brute-force methods. Complexity issues tend to dominate the systematic search for keys. To date, there has been very little research on a third cryptanalysis method: learning the key through convergence based on associations between plain text and cipher text. Recent advances in deep learning using multi-layered artificial neural networks (ANNs) provide an opportunity to reassess the role of deep learning architectures in next generation cryptanalysis methods based on neurocryptography (NC). In this paper, we explore the capability of deep ANNs to decrypt encrypted messages with minimum knowledge of the algorithm. From the experimental results, it can be concluded that DNNs can encrypt and decrypt to levels of accuracy that are not 100% because of the stochastic aspects of ANNs. This aspect may however be useful if communication is under cryptanalysis attack, since the attacker will not know for certain that key K used for encryption and decryption has been found. Also, uncertainty concerning the architecture used for encryption and decryption adds another layer of uncertainty that has no counterpart in traditional cryptanalysis.

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention of undermining a system. In the case of DNNs, the lack of better understanding of their working has prevented the development of efficient defenses. In this paper, we propose a new defense method based on practical observations which is easy to integrate into models and performs better than state-of-the-art defenses. Our proposed solution is meant to reinforce the structure of a DNN, making its prediction more stable and less likely to be fooled by adversarial samples. We conduct an extensive experimental study proving the efficiency of our method against multiple attacks, comparing it to numerous defenses, both in white-box and black-box setups. Additionally, the implementation of our method brings almost no overhead to the training procedure, while maintaining the prediction performance of the original model on clean samples.