Biblio
Denial of Service (DoS) attacks have been a serious security concern, as no service is, in principle, protected against them. Although a Dolev-Yao intruder with unlimited resources can trivially render any service unavailable, DoS attacks do not necessarily have to be carried out by such (extremely) powerful intruders. It is useful in practice and more challenging for formal protocol verification to determine whether a service is vulnerable even to resource-bounded intruders that cannot generate or intercept arbitrary large volumes of traffic. This paper proposes a novel, more refined intruder model where the intruder can only consume at most some specified amount of resources in any given time window. Additionally, we propose protocol theories that may contain timeouts and specify service resource usage during protocol execution. In contrast to the existing resource-conscious protocol verification models, our model allows finer and more subtle analysis of DoS problems. We illustrate the power of our approach by representing a number of classes of DoS attacks, such as, Slow, Asymmetric and Amplification DoS attacks, exhausting different types of resources of the target, such as, number of workers, processing power, memory, and network bandwidth. We show that the proposed DoS problem is undecidable in general and is PSPACE-complete for the class of resource-bounded, balanced systems. Finally, we implemented our formal verification model in the rewriting logic tool Maude and analyzed a number of DoS attacks in Maude using Rewriting Modulo SMT in an automated fashion.
As malware family classification methods, image-based classification methods have attracted much attention. Especially, due to the fast classification speed and the high classification accuracy, Convolutional Neural Network (CNN)-based malware family classification methods have been studied. However, previous studies on CNN-based classification methods focused only on improving the classification accuracy of malware families. That is, previous studies did not consider the cases that the accuracy of CNN-based malware classification methods can be decreased under the existence of adversarial attacks. In this paper, we analyze the robustness of various CNN-based malware family classification models under adversarial attacks. While adding imperceptible non-random perturbations to the input image, we measured how the accuracy of the CNN-based malware family classification model can be affected. Also, we showed the influence of three significant visualization parameters(i.e., the size of input image, dimension of input image, and conversion color of a special character)on the accuracy variation under adversarial attacks. From the evaluation results using the Microsoft malware dataset, we showed that even the accuracy over 98% of the CNN-based malware family classification method can be decreased to less than 7%.
The technological development of the energy sector also produced complex data. In this study, the relationship between smart grid and big data approaches have been investigated. After analyzing which areas of the smart grid system use big data technologies and technologies, big data technologies for detecting smart grid attacks have received attention. Big data analytics can produce efficient solutions and it is especially important to choose which algorithms and metrics to use. For this reason, an application prototype has been proposed that uses a big data method to detect attacks on the smart grid. The algorithm with high accuracy was determined to be 92% for random forests and 87% for decision trees.
Threat actors are constantly seeking new attack surfaces, with ransomeware being one the most successful attack vectors that have been used for financial gain. This has been achieved through the dispersion of unlimited polymorphic samples of ransomware whilst those responsible evade detection and hide their identity. Nonetheless, every ransomware threat actor adopts some similar style or uses some common patterns in their malicious code writing, which can be significant evidence contributing to their identification. he first step in attempting to identify the source of the attack is to cluster a large number of ransomware samples based on very little or no information about the samples, accordingly, their traits and signatures can be analysed and identified. T herefore, this paper proposes an efficient fuzzy analysis approach to cluster ransomware samples based on the combination of two fuzzy techniques fuzzy hashing and fuzzy c-means (FCM) clustering. Unlike other clustering techniques, FCM can directly utilise similarity scores generated by a fuzzy hashing method and cluster them into similar groups without requiring additional transformational steps to obtain distance among objects for clustering. Thus, it reduces the computational overheads by utilising fuzzy similarity scores obtained at the time of initial triaging of whether the sample is known or unknown ransomware. The performance of the proposed fuzzy method is compared against k-means clustering and the two fuzzy hashing methods SSDEEP and SDHASH which are evaluated based on their FCM clustering results to understand how the similarity score affects the clustering results.
Existing secure deletion approaches are inefficient in erasing data permanently because file systems have no knowledge of the data layout on the storage device, nor is the storage device aware of file information within the file systems. This inefficiency is exaggerated on the emerging shingled magnetic recording (SMR) drive due to its inherent sequential-write constraint. On SMR drives, secure deletion requests may lead to serious write amplification and performance degradation if the data layout is not properly configured. Such observation motivates us to propose a file-oriented fast secure deletion (FFSD) strategy to alleviate the negative impacts of SMR drives' sequential-write constraint and improve the efficiency of secure deletion operations on SMR drives. A series of experiments was conducted to demonstrate the capability of the proposed strategy on improving the efficiency of secure deletion on SMR drives.
The roll-out of smart meters (SMs) in the electric grid has enabled data-driven grid management and planning techniques. SM data can be used together with short-term load forecasts (STLFs) to overcome polling frequency constraints for better grid management. However, the use of SMs that report consumption data at high spatial and temporal resolutions entails consumer privacy risks, motivating work in protecting consumer privacy. The impact of privacy protection schemes on STLF accuracy is not well studied, especially for smaller aggregations of consumers, whose load profiles are subject to more volatility and are, thus, harder to predict. In this paper, we analyse the impact of two user demand shaping privacy protection schemes, model-distribution predictive control (MDPC) and load-levelling, on STLF accuracy. Support vector regression is used to predict the load profiles at different consumer aggregation levels. Results indicate that, while the MDPC algorithm marginally affects forecast accuracy for smaller consumer aggregations, this diminishes at higher aggregation levels. More importantly, the load-levelling scheme significantly improves STLF accuracy as it smoothens out the grid visible consumer load profile.
The main challenge for malware researchers is the large amount of data and files that need to be evaluated for potential threats. Researchers analyze a large number of new malware daily and classify them in order to extract common features. Therefore, a system that can ensure and improve the efficiency and accuracy of the classification is of great significance for the study of malware characteristics. A high-performance, high-efficiency automatic classification system based on multi-feature selection fusion of machine learning is proposed in this paper. Its performance and efficiency, according to our experiments, have been greatly improved compared to single-featured systems.
We aim at creating a society where we can resolve various social challenges by incorporating the innovations of the fourth industrial revolution (e.g. IoT, big data, AI, robot, and the sharing economy) into every industry and social life. By doing so the society of the future will be one in which new values and services are created continuously, making people's lives more conformable and sustainable. This is Society 5.0, a super-smart society. Security and privacy are key issues to be addressed to realize Society 5.0. Privacy-preserving data analytics will play an important role. In this talk we show our recent works on privacy-preserving data analytics such as privacy-preserving logistic regression and privacy-preserving deep learning. Finally, we show our ongoing research project under JST CREST “AI”. In this project we are developing privacy-preserving financial data analytics systems that can detect fraud with high security and accuracy. To validate the systems, we will perform demonstration tests with several financial institutions and solve the problems necessary for their implementation in the real world.
Blockchain is a database technology that provides the integrity and trust of the system can't make arbitrary modifications and deletions by being an append-only distributed ledger. That is, the blockchain is not a modification or deletion but a CRAB (Create-Retrieve-Append-Burn) method in which data can be read and written according to a legitimate user's access right(For example, owner private key). However, this can not delete the created data once, which causes problems such as privacy breach. In this paper, we propose an on-off block-chained Hybrid Blockchain system to separate the data and save the connection history to the blockchain. In addition, the state is changed to the distributed database separately from the ledger record, and the state is changed by generating the arbitrary injection in the XOR form, so that the history of modification / deletion of the Off Blockchain can be efficiently retrieved.
In this work, we applied a deep Convolutional Neural Network (CNN) with Xception model to perform malware image classification. The Xception model is a recently developed special CNN architecture that is more powerful with less over- fitting problems than the current popular CNN models such as VGG16. However only a few use cases of the Xception model can be found in literature, and it has never been used to solve the malware classification problem. The performance of our approach was compared with other methods including KNN, SVM, VGG16 etc. The experiments on two datasets (Malimg and Microsoft Malware Dataset) demonstrated that the Xception model can achieve the highest training accuracy than all other approaches including the champion approach, and highest validation accuracy than all other approaches including VGG16 model which are using image-based malware classification (except the champion solution as this information was not provided). Additionally, we proposed a novel ensemble model to combine the predictions from .bytes files and .asm files, showing that a lower logloss can be achieved. Although the champion on the Microsoft Malware Dataset achieved a bit lower logloss, our approach does not require any features engineering, making it more effective to adapt to any future evolution in malware, and very much less time consuming than the champion's solution.
Steganography means hiding secrete message in cover object in a way that no suspicious from the attackers, the most popular steganography schemes is image steganography. A very common questions that asked in the field are: 1- what is the embedding scheme used?, 2- where is (location) the secrete messages are embedded?, and 3- how the sender will tell the receiver about the locations of the secrete message?. Here in this paper we are deal with and aimed to answer questions number 2 and 3. We used the popular scheme in image steganography which is least significant bits for embedding in edges positions in color images. After we separate the color images into its components Red, Green, and Blue, then we used one of the components as an index to find the edges, while other one or two components used for embedding purpose. Using this technique we will guarantee the same number and positions of edges before and after embedding scheme, therefore we are guaranteed extracting the secrete message as it's without any loss of secrete messages bits.
Now-a-days, video steganography has developed for a secured communication among various users. The two important factor of steganography method are embedding potency and embedding payload. Here, a Multiple Object Tracking (MOT) algorithmic programs used to detect motion object, also shows foreground mask. Discrete wavelet Transform (DWT) and Discrete Cosine Transform (DCT) are used for message embedding and extraction stage. In existing system Least significant bit method was proposed. This technique of hiding data may lose some data after some file transformation. The suggested Multiple object tracking algorithm increases embedding and extraction speed, also protects secret message against various attackers.
Crowdsensing, driven by the proliferation of sensor-rich mobile devices, has emerged as a promising data sensing and aggregation paradigm. Despite useful, traditional crowdsensing systems typically rely on a centralized third-party platform for data collection and processing, which leads to concerns like single point of failure and lack of operation transparency. Such centralization hinders the wide adoption of crowdsensing by wary participants. We therefore explore an alternative design space of building crowdsensing systems atop the emerging decentralized blockchain technology. While enjoying the benefits brought by the public blockchain, we endeavor to achieve a consolidated set of desirable security properties with a proper choreography of latest techniques and our customized designs. We allow data providers to safely contribute data to the transparent blockchain with the confidentiality guarantee on individual data and differential privacy on the aggregation result. Meanwhile, we ensure the service correctness of data aggregation and sanitization by delicately employing hardware-assisted transparent enclave. Furthermore, we maintain the robustness of our system against faulty data providers that submit invalid data, with a customized zero-knowledge range proof scheme. The experiment results demonstrate the high efficiency of our designs on both mobile client and SGX-enabled server, as well as reasonable on-chain monetary cost of running our task contract on Ethereum.
There has been a growing expansion in the use of steganography, due to the evolution in using internet technology and multimedia technology. Hence, nowadays, the information is not secured sufficiently while transmitting it over the network. Therefore, information security has taken an important role to provide security against unauthorized individuals. This paper proposes steganography and cryptography technique to secure image based on hybrid edge detector. Cryptography technique is used to encrypt a secret image by using Vernam cipher algorithm. The robust of this algorithm is depending on pseudorandom key. Therefore, pseudo-random key is generated from a nonlinear feedback shift register (Geffe Generator). While in steganography, Hybrid Sobel and Kirch edge detector have been applied on the cover image to locate edge pixels. The least significant bit (LSB) steganography technique is used to embed secret image bits in the cover image in which 3 bits are embedded in edge pixel and 2 bits in smooth pixel. The proposed method can be used in multi field such as military, medical, communication, banking, Electronic governance, and so on. This method gives an average payload ratio of 1.96 with 41.5 PSNR on average. Besides, the maximum size of secret image that can be hidden in the cover image of size 512*512 is 262*261. Also, when hiding 64800 bits in baboon cover image of size 512*512, it gives PSNR of 50.42 and MSE of 0.59.
Online Social Networks(OSN) plays a vital role in our day to day life. The most popular social network, Facebook alone counts currently 2.23 billion users worldwide. Online social network users are aware of the various security risks that exist in this scenario including privacy violations and they are utilizing the privacy settings provided by OSN providers to make their data safe. But most of them are unaware of the risk which exists after deletion of their data which is not really getting deleted from the OSN server. Self destruction of data is one of the prime recommended methods to achieve assured deletion of data. Numerous techniques have been developed for self destruction of data and this paper discusses and evaluates these techniques along with the various privacy risks faced by an OSN user in this web centered world.
Video Steganography is an extension of image steganography where any kind of file in any extension is hidden into a digital video. The video content is dynamic in nature and this makes the detection of hidden data difficult than other steganographic techniques. The main motive of using video steganography is that the videos can store large amount of data in it. This paper focuses on security using the combination of hybrid neural networks and hash function for determining the best bits in the cover video to embed the secret data. For the embedding process, the cover video and the data to be hidden is uploaded. Then the hash algorithm and neural networks are applied to form the stego video. For the extraction process, the reverse process is applied and the secret data is obtained. All experiments are done using MatLab2016a software.
With the ever-growing occurrence of networking attacks, robust network security systems are essential to prevent and mitigate their harming effects. In recent years, machine learning-based systems have gain popularity for network security applications, usually considering the application of shallow models, where a set of expert handcrafted features are needed to pre-process the data before training. The main problem with this approach is that handcrafted features can fail to perform well given different kinds of scenarios and problems. Deep Learning models can solve this kind of issues using their ability to learn feature representations from input raw or basic, non-processed data. In this paper we explore the power of deep learning models on the specific problem of detection and classification of malware network traffic, using different representations for the input data. As a major advantage as compared to the state of the art, we consider raw measurements coming directly from the stream of monitored bytes as the input to the proposed models, and evaluate different raw-traffic feature representations, including packet and flow-level ones. Our results suggest that deep learning models can better capture the underlying statistics of malicious traffic as compared to classical, shallow-like models, even while operating in the dark, i.e., without any sort of expert handcrafted inputs.