Biblio

The reigning U.S. paradigm for deterring malicious cyberspace activity carried out by or condoned by other countries is to levy penalties on them. The results have been disappointing. There is little evidence of the permanent reduction of such activity, and the narrative behind the paradigm presupposes a U.S./allied posture that assumes the morally superior role of judge upon whom also falls the burden of proof–-a posture not accepted but nevertheless exploited by other countries. In this paper, we explore an alternative paradigm, obnoxious deterrence, in which the United States itself carries out malicious cyberspace activity that is used as a bargaining chip to persuade others to abandon objectionable cyberspace activity. We then analyze the necessary characteristics of this malicious cyberspace activity, which is generated only to be traded off. It turns out that two fundamental criteria–that the activity be sufficiently obnoxious to induce bargaining but be insufficiently valuable to allow it to be traded away–may greatly reduce the feasibility of such a ploy. Even if symmetric agreements are easier to enforce than pseudo-symmetric agreements (e.g., the XiObama agreement of 2015) or asymmetric red lines (e.g., the Biden demand that Russia not condone its citizens hacking U.S. critical infrastructure), when violations occur, many of today’s problems recur. We then evaluate the practical consequences of this approach, one that is superficially attractive.

Axie infinity is a complicated card game with a huge-scale action space. This makes it difficult to solve this challenge using generic Reinforcement Learning (RL) algorithms. We propose a hybrid RL framework to learn action representations and game strategies. To avoid evaluating every action in the large feasible action set, our method evaluates actions in a fixed-size set which is determined using action representations. We compare the performance of our method with two baseline methods in terms of their sample efficiency and the winning rates of the trained models. We empirically show that our method achieves an overall best winning rate and the best sample efficiency among the three methods.

Though several deep learning (DL) detectors have been proposed for the network attack detection and achieved high accuracy, they are computationally expensive and struggle to satisfy the real-time detection for high-speed networks. Recently, programmable switches exhibit a remarkable throughput efficiency on production networks, indicating a possible deployment of the timely detector. Therefore, we present Soter, a DL enhanced in-network framework for the accurate real-time detection. Soter consists of two phases. One is filtering packets by a rule-based decision tree running on the Tofino ASIC. The other is executing a well-designed lightweight neural network for the thorough inspection of the suspicious packets on the CPU. Experiments on the commodity switch demonstrate that Soter behaves stably in ten network scenarios of different traffic rates and fulfills per-flow detection in 0.03s. Moreover, Soter naturally adapts to the distributed deployment among multiple switches, guaranteeing a higher total throughput for large data centers and cloud networks.

With the rapid development of multimedia and short video, there is a growing concern for video copyright protection. Some work has been proposed to add some copyright or fingerprint information to the video to trace the source of the video when it is stolen and protect video copyright. This paper proposes a video watermarking method based on a deep neural network and curriculum learning for watermarking of sliced videos. The first frame of the segmented video is perturbed by an encoder network, which is invisible and can be distinguished by the decoder network. Our model is trained and tested on an online educational video dataset consisting of 2000 different video clips. Experimental results show that our method can successfully discriminate most watermarked and non-watermarked videos with low visual disturbance, which can be achieved even under a relatively high video compression rate(H.264 video compress with CRF 32).

In this work we propose a novel deep learning approach for ultra-low bitrate video compression for video conferencing applications. To address the shortcomings of current video compression paradigms when the available bandwidth is extremely limited, we adopt a model-based approach that employs deep neural networks to encode motion information as keypoint displacement and reconstruct the video signal at the decoder side. The overall system is trained in an end-to-end fashion minimizing a reconstruction error on the encoder output. Objective and subjective quality evaluation experiments demonstrate that the proposed approach provides an average bitrate reduction for the same visual quality of more than 60% compared to HEVC.

Data poisoning is a type of adversarial attack on training data where an attacker manipulates a fraction of data to degrade the performance of machine learning model. There are several known defensive mechanisms for handling offline attacks, however defensive measures for online learning, where data points arrive sequentially, have not garnered similar interest. In this work, we propose a defense mechanism to minimize the degradation caused by the poisoned training data on a learner's model in an online setup. Our proposed method utilizes an influence function which is a classic technique in robust statistics. Further, we supplement it with the existing data sanitization methods for filtering out some of the poisoned data points. We study the effectiveness of our defense mechanism on multiple datasets and across multiple attack strategies against an online learner.

A direct access (DAX) file system maximizes the benefit of persistent memory(PM)’s low latency through removing the page cache layer from the file system access paths. However, this paper reveals that data block allocation of the DAX file systems in common is significantly slower than that of conventional file systems because the DAX file systems require the zero-out operation for the newly allocated blocks to prevent the leakage of old data previously stored in the allocated data blocks. The retarded block allocation significantly affects the file write performance. In addition to this revelation, this paper proposes an off-critical-path data block sanitization scheme tailored for DAX file systems. The proposed scheme detaches the zero-out operation from the latency-critical I/O path and performs that of released data blocks in the background. The proposed scheme’s design principle is universally applicable to most DAX file systems. For evaluation, we implemented our approach in Ext4-DAX and XFS-DAX. Our evaluation showed that the proposed scheme reduces the append write latency by 36.8%, and improved the performance of FileBench’s fileserver workload by 30.4%, YCSB’s workload A on RocksDB by 3.3%, and the Redis-benchmark by 7.4% on average, respectively.

This paper mainly explores the detection and defense of DDoS attacks in the SDN architecture of the 5G environment, and proposes a DDoS attack detection method based on the deep learning two-level model CNN-LSTM in the SDN network. Not only can it greatly improve the accuracy of attack detection, but it can also reduce the time for classifying and detecting network traffic, so that the transmission of DDoS attack traffic can be blocked in time to ensure the availability of network services.

Network security is a prominent topic that is gaining international attention. Distributed Denial of Service (DDoS) attack is often regarded as one of the most serious threats to network security. Software Defined Network (SDN) decouples the control plane from the data plane, which can meet various network requirements. But SDN can also become the object of DDoS attacks. This paper proposes an automated DDoS attack mitigation method that is based on the programmability of the Ryu controller and the features of the OpenFlow switch flow tables. The Mininet platform is used to simulate the whole process, from SDN traffic generation to using a K-Nearest Neighbor model for traffic classification, as well as identifying and mitigating DDoS attack. The packet counts of the victim's malicious traffic input port are significantly lower after the mitigation method is implemented than before the mitigation operation. The purpose of mitigating DDoS attack is successfully achieved.

With the advent of the 5G era, high-speed and secure network access services have become a common pursuit. The QUIC (Quick UDP Internet Connection) protocol proposed by Google has been studied by many scholars due to its high speed, robustness, and low latency. However, the research on the security of the QUIC protocol by domestic and foreign scholars is insufficient. Therefore, based on the self-similarity of QUIC network traffic, combined with traffic characteristics and signal processing methods, a QUIC-based network traffic anomaly detection model is proposed in this paper. The model decomposes and reconstructs the collected QUIC network traffic data through the Empirical Mode Decomposition (EMD) method. In order to judge the occurrence of abnormality, this paper also intercepts overlapping traffic segments through sliding windows to calculate Hurst parameters and analyzes the obtained parameters to check abnormal traffic. The simulation results show that in the network environment based on the QUIC protocol, the Hurst parameter after being attacked fluctuates violently and exceeds the normal range. It also shows that the anomaly detection of QUIC network traffic can use the EMD method.

By broadcasting false Global Navigation Satellite System (GNSS) signals, spoofing attacks will induce false position and time fixes within the victim receiver. In this article, we propose a Sparse Decomposition (SD)-based spoofing detection algorithm in the acquisition process, which can be applied in a single-antenna receiver. In the first step, we map the Fast Fourier transform (FFT)-based acquisition result in a two-dimensional matrix, which is a distorted autocorrelation function when the receiver is under spoof attack. In the second step, the distorted function is decomposed into two main autocorrelation function components of different code phases. The corresponding elements of the result vector of the SD are the code-phase values of the spoofed and the authentic signals. Numerical simulation results show that the proposed method can not only outcome spoofing detection result, but provide reliable estimations of the code phase delay of the spoof attack.

In this work, we conduct a systematic study on data poisoning attacks to Matrix Factorisation (MF) based Recommender Systems (RS) where a determined attacker injects fake users with false user-item feedback, with an objective to promote a target item by increasing its rating. We explore the capability of a MF based approach to reduce the impact of attack on targeted item in the system. We develop and evaluate multiple techniques to update the user and item feature matrices when incorporating new ratings. We also study the effectiveness of attack under increasing filler items and choice of target item.Our experimental results based on two real-world datasets show that the observations from the study could be used to design a more robust MF based RS.

Previous work has shown that a neural network with the rectified linear unit (ReLU) activation function leads to a convex polyhedral decomposition of the input space. These decompositions can be represented by a dual graph with vertices corresponding to polyhedra and edges corresponding to polyhedra sharing a facet, which is a subgraph of a Hamming graph. This paper illustrates how one can utilize the dual graph to detect and analyze adversarial attacks in the context of digital images. When an image passes through a network containing ReLU nodes, the firing or non-firing at a node can be encoded as a bit (1 for ReLU activation, 0 for ReLU non-activation). The sequence of all bit activations identifies the image with a bit vector, which identifies it with a polyhedron in the decomposition and, in turn, identifies it with a vertex in the dual graph. We identify ReLU bits that are discriminators between non-adversarial and adversarial images and examine how well collections of these discriminators can ensemble vote to build an adversarial image detector. Specifically, we examine the similarities and differences of ReLU bit vectors for adversarial images, and their non-adversarial counterparts, using a pre-trained ResNet-50 architecture. While this paper focuses on adversarial digital images, ResNet-50 architecture, and the ReLU activation function, our methods extend to other network architectures, activation functions, and types of datasets.

Model compression is one of the most preferred techniques for efficiently deploying deep neural networks (DNNs) on resource- constrained Internet of Things (IoT) platforms. However, the simply compressed model is often vulnerable to adversarial attacks, leading to a conflict between robustness and efficiency, especially for IoT devices exposed to complex real-world scenarios. We, for the first time, address this problem by developing a novel framework dubbed Magical-Decomposition to simultaneously enhance both robustness and efficiency for hardware. By leveraging a hardware-friendly model compression method called singular value decomposition, the defending algorithm can be supported by most of the existing DNN hardware accelerators. To step further, by using a recently developed DNN interpretation tool, the underlying scheme of how the adversarial accuracy can be increased in the compressed model is highlighted clearly. Ablation studies and extensive experiments under various attacks/models/datasets consistently validate the effectiveness and scalability of the proposed framework.

With the rapid development of general cloud services, more and more individuals or collectives use cloud platforms to store data. Assured data deletion deserves investigation in cloud storage. In time-sensitive data storage scenarios, it is necessary for cloud platforms to automatically destroy data after the data owner-specified expiration time. Therefore, assured time-sensitive data deletion should be sought. In this paper, a fine-grained assured time-sensitive data deletion (ATDD) scheme in cloud storage is proposed by embedding the time trapdoor in Ciphertext-Policy Attribute-Based Encryption (CP-ABE). Time-sensitive data is self-destructed after the data owner-specified expiration time so that the authorized users cannot get access to the related data. In addition, a credential is returned to the data owner for data deletion verification. This proposed scheme provides solutions for fine-grained access control and verifiable data self-destruction. Detailed security and performance analysis demonstrate the security and the practicability of the proposed scheme.

At present, cloud service providers control the direct management rights of cloud data, and cloud data cannot be effectively and assured deleted, which may easily lead to security problems such as data residue and user privacy leakage. This paper analyzes the related research work of cloud data assured deletion in recent years from three aspects: encryption key deletion, multi-replica association deletion, and verifiable deletion. The advantages and disadvantages of various deletion schemes are analysed in detail, and finally the prospect of future research on assured deletion of cloud data is given.

Documents are a common method of storing infor-mation and one of the most conventional forms of expression of ideas. Cloud servers store a user's documents with thousands of other users in place of physical storage devices. Indexes corresponding to the documents are also stored at the cloud server to enable the users to retrieve documents of their interest. The index includes keywords, document identities in which the keywords appear, along with Term Frequency-Inverse Document Frequency (TF-IDF) values which reflect the keywords' relevance scores of the dataset. Currently, there are no efficient methods to delete keywords from millions of documents over cloud servers while avoiding any compromise to the user's privacy. Most of the existing approaches use algorithms that divide a bigger problem into sub-problems and then combine them like divide and conquer problems. These approaches don't focus entirely on fine-grained deletion. This work is focused on achieving fine-grained deletion of keywords by keeping the size of the TF-IDF matrix constant after processing the deletion query, which comprises of keywords to be deleted. The experimental results of the proposed approach confirm that the precision of ranked search still remains very high after deletion without recalculation of the TF-IDF matrix.

Data secure deletion operation in storage media is an important function of data security management. The internal physical properties of SSDs are different from hard disks, and data secure deletion of disks can not apply to SSDs directly. Copyback operation is used to improve the data migration performance of SSDs but is rarely used due to error accumulation issue. We propose a data securely deletion algorithm based on copyback operation, which improves the efficiency of data secure deletion without affecting the reliability of data. First, this paper proves that the data secure delete operation takes a long time on the channel bus, increasing the I/O overhead, and reducing the performance of the SSDs. Secondly, this paper designs an efficient data deletion algorithm, which can process read requests quickly. The experimental results show that the proposed algorithm can reduce the response time of read requests by 21% and the response time of delete requests by 18.7% over the existing algorithm.

Legacy programs are normally monolithic (that is, all code runs in a single process and is not partitioned), and a bug in a program may result in the entire program being vulnerable and therefore untrusted. Program partitioning can be used to separate a program into multiple partitions, so as to isolate sensitive data or privileged operations. Manual program partitioning requires programmers to rewrite the entire source code, which is cumbersome, error-prone, and not generic. Automatic program partitioning tools can separate programs according to the dependency graph constructed based on data or programs. However, programmers still need to manually implement remote service interfaces for inter-partition communication. Therefore, in this paper, we propose AutoSlicer, whose purpose is to partition a program more automatically, so that the programmer is only required to annotate sensitive data. AutoSlicer constructs accurate data dependency graphs (DDGs) by enabling execution flow graphs, and the DDG-based partitioning algorithm can compute partition information based on sensitive annotations. In addition, the code refactoring toolchain can automatically transform the source code into sensitive and insensitive partitions that can be deployed on the remote procedure call framework. The experimental evaluation shows that AutoSlicer can effectively improve the accuracy (13%-27%) of program partitioning by enabling EFG, and separate real-world programs with a relatively smaller performance overhead (0.26%-9.42%).

Third-party libraries with rich functionalities facilitate the fast development of JavaScript software, leading to the explosive growth of the NPM ecosystem. However, it also brings new security threats that vulnerabilities could be introduced through dependencies from third-party libraries. In particular, the threats could be excessively amplified by transitive dependencies. Existing research only considers direct dependencies or reasoning transitive dependencies based on reachability analysis, which neglects the NPM-specific dependency resolution rules as adapted during real installation, resulting in wrongly resolved dependencies. Consequently, further fine-grained analysis, such as precise vulnerability propagation and their evolution over time in dependencies, cannot be carried out precisely at a large scale, as well as deriving ecosystem-wide solutions for vulnerabilities in dependencies. To fill this gap, we propose a knowledge graph-based dependency resolution, which resolves the inner dependency relations of dependencies as trees (i.e., dependency trees), and investigates the security threats from vulnerabilities in dependency trees at a large scale. Specifically, we first construct a complete dependency-vulnerability knowledge graph (DVGraph) that captures the whole NPM ecosystem (over 10 million library versions and 60 million well-resolved dependency relations). Based on it, we propose a novel algorithm (DTResolver) to statically and precisely resolve dependency trees, as well as transitive vulnerability propagation paths, for each package by taking the official dependency resolution rules into account. Based on that, we carry out an ecosystem-wide empirical study on vulnerability propagation and its evolution in dependency trees. Our study unveils lots of useful findings, and we further discuss the lessons learned and solutions for different stakeholders to mitigate the vulnerability impact in NPM based on our findings. For example, we implement a dependency tree based vulnerability remediation method (DTReme) for NPM packages, and receive much better performance than the official tool (npm audit fix).

Unsupervised cross-domain NER task aims to solve the issues when data in a new domain are fully-unlabeled. It leverages labeled data from source domain to predict entities in unlabeled target domain. Since training models on large domain corpus is time-consuming, in this paper, we consider an alternative way by introducing syntactic dependency structure. Such information is more accessible and can be shared between sentences from different domains. We propose a novel framework with dependency-aware GNN (DGNN) to learn these common structures from source domain and adapt them to target domain, alleviating the data scarcity issue and bridging the domain gap. Experimental results show that our method outperforms state-of-the-art methods.

In the 21st century, world-leading industries are under the accelerated development of digital transformation. Along with information and data resources becoming more transparent on the Internet, many new network technologies were introduced, but cyber-attack also became a severe problem in cyberspace. Over time, industrial control networks are also forced to join the nodes of the Internet. Therefore, cybersecurity is much more complicated than before, and suffering risk of browsing unknown websites also increases. To practice defenses against cyber-attack effectively, Cyber Range is the best platform to emulate all cyber-attacks and defenses. This article will use VMware virtual machine emulation technology, research cyber range systems under industrial control network architecture, and design and implement an industrial control cyber range system. Using the industrial cyber range to perform vulnerability analyses and exploits on web servers, web applications, and operating systems. The result demonstrates the consequences of the vulnerability attack and raises awareness of cyber security among government, enterprises, education, and other related fields, improving the practical ability to defend against cybersecurity threats.

At the end of the IT Security degree program a simulation game is conducted to repeat and consolidate the core skills of a Bachelor’s graduate. The focus is not on teaching content, but on the application of already learned skills. The scenario shows the students the risks of a completely networked world, which has come to a complete standstill due to a catastrophe. The participants occupy in groups the predefined companies, which are assigned with the reconstruction of the communication infrastructure (the internet). This paper describes the preparation, technical and organizational implementation of the. Also, the most important conclusions drawn by the authors.

There is a stark contrast between the state of cyber security of national infrastructure in Ireland and the efforts underway to support cyber security technologists to work in the country. Notable attacks have recently occurred against the national health service, universities, and various other state bodies, prompting an interest in changing the current situation. This paper presents an overview of the security projects, commercial establishments, and policy in Ireland.

Cyber-Physical System (CPS) is becoming increasingly complicated and integrated into our daily lives, laying the foundation for advanced infrastructures, commodities, and services. In this regard, operational continuity of the system is the most critical objective, and cyber resilience quantification to evaluate and enhance it has garnered attention. However, understanding of the increasingly critical cyber risks is weak, with the focus being solely on the damage that occurs in the physical domain. To address this gap, this work takes aim at shedding some light on the cyber resilience quantification of CPS. We review the numerous resilience quantification techniques presented to date through several metrics to provide systematization of knowledge (SoK). In addition, we discuss the challenges of current quantification methods and give ideas for future research that will lead to more precise cyber resilience measurements.