Biblio

With the dramatic increase in malicious software, the sophistication and innovation of malware have increased over the years. In particular, the dynamic analysis based on the deep neural network has shown high accuracy in malware detection. However, most of the existing methods only employ the raw API sequence feature, which cannot accurately reflect the actual behavior of malicious programs in detail. The relationship between API calls is critical for detecting suspicious behavior. Therefore, this paper proposes a malware detection method based on the graph neural network. We first connect the API sequences executed by different processes to build a directed process graph. Then, we apply Bert to encode the API sequences of each process into node embedding, which facilitates the semantic execution information inside the processes. Finally, we employ GCN to mine the deep semantic information based on the directed process graph and node embedding. In addition to presenting the design, we have implemented and evaluated our method on 10,000 malware and 10,000 benign software datasets. The results show that the precision and recall of our detection model reach 97.84% and 97.83%, verifying the effectiveness of our proposed method.

At present, code reuse attacks, such as Return Oriented Programming (ROP), execute attacks through the code of the application itself, bypassing the traditional defense mechanism and seriously threatening the security of computer software. The existing two mainstream defense mechanisms, Address Space Layout Randomization (ASLR), are vulnerable to information disclosure attacks, and Control-Flow Integrity (CFI) will bring high overhead to programs. At the same time, due to the widespread use of software of unknown origin, there is no source code provided or available, so it is not always possible to secure the source code. In this paper, we propose FRCFI, an effective method based on binary rewriting to prevent code reuse attacks. FRCFI first disrupts the program's memory space layout through function shuffling and NOP insertion, then verifies the execution of the control-flow branch instruction ret and indirect call/jmp instructions to ensure that the target address is not modified by attackers. Experiment show shows that FRCFI can effectively defend against code reuse attacks. After randomization, the survival rate of gadgets is only 1.7%, and FRCFI adds on average 6.1% runtime overhead on SPEC CPU2006 benchmark programs.

The Cloud Native paradigm has quickly emerged as a new trend in Web Services architectures. Applications are now developed as a network of microservices and functions that can be quickly re-deployed anywhere, decoupled from their state. In this scenario, workloads are usually packaged as container images that can be quickly provisioned anywhere in a provider web service. To enforce security, traditional Docker container runtime mechanisms are now being enhanced by stronger isolation techniques such as lightweight hardware level virtualization. Such sandboxing inserts a strong boundary - the guest space - and therefore security containers do not share filesystem semantics with the host Operating System. However, the existing container storage drivers are designed and optimized to run directly on the host. In this paper we bridge the gap between traditional containers and virtualized containers. We present Deverlay, a container storage driver that prepares a block-based container root filesystem view, targeting lightweight Virtual Machines and keeping host native execution compatibility. We show that, in contrast to other block-based drivers, Deverlay can boot 80 micro VM containers in less than 4s by efficiently sharing host cache buffers among containers and reducing I/O disk access by 97.51 %.

Industrial control systems (ICSs) have become more complex due to their increasing connectivity, heterogeneity and, autonomy. As a result, cyber-threats against such systems have been significantly increased as well. Since a compromised industrial system can easily lead to hazardous safety and security consequences, it is crucial to develop security countermeasures to protect coexisting IT systems and industrial physical processes being involved in modern ICSs. Accordingly, in this study, we propose a deep learning-based semantic anomaly detection framework to model the complex behavior of ICSs. In contrast to the related work assuming only simpler security threats targeting individual controllers in an ICS, we address multi-PLC attacks that are harder to detect as requiring to observe the overall system state alongside single-PLC attacks. Using industrial simulation and emulation frameworks, we create a realistic setup representing both the production and networking aspects of industrial systems and conduct some potential attacks. Our experimental results indicate that our model can detect single-PLC attacks with 95% accuracy and multi-PLC attacks with 80% accuracy and nearly 1% false positive rate.

Generative adversarial networks (GANs) have been increasingly popular among deep learning methods. With many GANs-based models developed since its emergence, among which are conditional generative adversarial networks, progressive growing of generative adversarial networks, Wasserstein generative adversarial networks and so on. These frameworks are currently widely applied in areas such as remote sensing cybersecurity, medical, and architecture. Especially, they have solved problems of cloud removal, semantic segmentation, image-to-image translation and data argumentation in remote sensing. For example, WGANs and ProGANs can be applied in data argumentation, and cGANs can be applied in semantic argumentation and image-to-image translation. This article provides an overview of structures of multiple GANs-based models and what areas they can be applied in remote sensing.

Video summarization aims to improve the efficiency of large-scale video browsing through producting concise summaries. It has been popular among many scenarios such as video surveillance, video review and data annotation. Traditional video summarization techniques focus on filtration in image features dimension or image semantics dimension. However, such techniques can make a large amount of possible useful information lost, especially for many videos with rich text semantics like interviews, teaching videos, in that only the information relevant to the image dimension will be retained. In order to solve the above problem, this paper considers video summarization as a continuous multi-dimensional decision-making process. Specifically, the summarization model predicts a probability for each frame and its corresponding text, and then we designs reward methods for each of them. Finally, comprehensive summaries in two dimensions, i.e. images and semantics, is generated. This approach is not only unsupervised and does not rely on labels and user interaction, but also decouples the semantic and image summarization models to provide more usable interfaces for subsequent engineering use.

To exploit high temporal correlations in video frames of the same scene, the current frame is predicted from the already-encoded reference frames using block-based motion estimation and compensation techniques. While this approach can efficiently exploit the translation motion of the moving objects, it is susceptible to other types of affine motion and object occlusion/deocclusion. Recently, deep learning has been used to model the high-level structure of human pose in specific actions from short videos and then generate virtual frames in future time by predicting the pose using a generative adversarial network (GAN). Therefore, modelling the high-level structure of human pose is able to exploit semantic correlation by predicting human actions and determining its trajectory. Video surveillance applications will benefit as stored “big” surveillance data can be compressed by estimating human pose trajectories and generating future frames through semantic correlation. This paper explores a new way of video coding by modelling human pose from the already-encoded frames and using the generated frame at the current time as an additional forward-referencing frame. It is expected that the proposed approach can overcome the limitations of the traditional backward-referencing frames by predicting the blocks containing the moving objects with lower residuals. Our experimental results show that the proposed approach can achieve on average up to 2.83 dB PSNR gain and 25.93% bitrate savings for high motion video sequences compared to standard video coding.

Deep learning models rely on single word features and location features of text to achieve good results in text relation extraction tasks. However, previous studies have failed to make full use of semantic information contained in sentence dependency syntax trees, and data sparseness and noise propagation still affect classification models. The BERT(Bidirectional Encoder Representations from Transformers) pretrained language model provides a better representation of natural language processing tasks. And entity enhancement methods have been proved to be effective in relation extraction tasks. Therefore, this paper proposes a combination of the shortest dependency path and entity-enhanced BERT pre-training language model for model construction to reduce the impact of noise terms on the classification model and obtain more semantically expressive feature representation. The algorithm is tested on SemEval-2010 Task 8 English relation extraction dataset, and the F1 value of the final experiment can reach 0. 881.

This work-in-progress paper proposes a design methodology that addresses the complexity and heterogeneity of cyber-physical systems (CPS) while simultaneously proving resilient control logic and security properties. The design methodology involves a formal methods-based approach by translating the complex control logic and security properties of a water flow CPS into timed automata. Timed automata are a formal model that describes system behaviors and properties using mathematics-based logic languages with precision. Due to the semantics that are used in developing the formal models, verification techniques, such as theorem proving and model checking, are used to mathematically prove the specifications and security properties of the CPS. This work-in-progress paper aims to highlight the need for formalizing plant models by creating a timed automata of the physical portions of the water flow CPS. Extending the time automata with control logic, network security, and privacy control processes is investigated. The final model will be formally verified to prove the design specifications of the water flow CPS to ensure efficacy and security.

As a mature and open mobile operating system, Android runs on many IoT devices, which has led to Android-based IoT devices have become a hotbed of malware. Existing static detection methods for malware using artificial intelligence algorithms focus only on the java code layer when extracting API features, however there is a lot of malicious behavior involving native layer code. Thus, to make up for the neglect of the native code layer, we propose a heterogeneous information network-based Android malware detection method with cross-layer features. We first translate the semantic information of apps and API calls into the form of meta-paths, and construct the adjacency of apps based on API calls, then combine information from different meta-paths using multi-core learning. We implemented our method on the dataset from VirusShare and AndroZoo, and the experimental results show that the accuracy of our method is 93.4%, which is at least 2% higher than other related methods using heterogeneous information networks for malware detection.

The SPECTRE family of speculative execution attacks has required a rethinking of formal methods for security. Approaches based on operational speculative semantics have made initial inroads towards finding vulnerable code and validating defenses. However, with each new attack grows the amount of microarchitectural detail that has to be integrated into the underlying semantics. We propose an alternative, lightweight and axiomatic approach to specifying speculative semantics that relies on insights from memory models for concurrency. We use the CAT modeling language for memory consistency to specify execution models that capture speculative control flow, store-to-load forwarding, predictive store forwarding, and memory ordering machine clears. We present a bounded model checking framework parameterized by our speculative CAT models and evaluate its implementation against the state of the art. Due to the axiomatic approach, our models can be rapidly extended to allow our framework to detect new types of attacks and validate defenses against them.

Server-side web applications are vulnerable to request races. While some previous studies of real-world request races exist, they primarily focus on the root cause of these bugs. To better combat request races in server-side web applications, we need a deep understanding of their characteristics. In this paper, we provide a complementary focus on race effects and fixes with an enlarged set of request races from web applications developed with Object-Relational Mapping (ORM) frameworks. We revisit characterization questions used in previous studies on newly included request races, distinguish the external and internal effects of request races, and relate requestrace fixes with concurrency control mechanisms in languages and frameworks for developing server-side web applications. Our study reveals that: (1) request races from ORM-based web applications share the same characteristics as those from raw-SQL web applications; (2) request races violating application semantics without explicit crashes and error messages externally are common, and latent request races, which only corrupt some shared resource internally but require extra requests to expose the misbehavior, are also common; and (3) various fix strategies other than using synchronization mechanisms are used to fix request races. We expect that our results can help developers better understand request races and guide the design and development of tools for combating request races.

Access control is a widely used technology to protect information security. The implementation of access control depends on the response generated by access control policies to users’ access requests. Therefore, ensuring the correctness of access control policies is an important step to ensure the smooth implementation of access control mechanisms. To solve this problem, this paper proposes a constraint based access control policy security analysis framework (CACPSAF) to perform security analysis on access control policies. The framework transforms the problem of security analysis of access control policy into the satisfiability of security principle constraints. The analysis and calculation of access control policy can be divided into formal transformation of access control policy, SMT coding of policy model, generation of security principle constraints, policy detection and evaluation. The security analysis of policies is divided into mandatory security principle constraints, optional security principle constraints and user-defined security principle constraints. The multi-dimensional security analysis of access control policies is realized and the semantic expression of policy analysis is stronger. Finally, the effectiveness of this framework is analyzed by performance evaluation, which proves that this framework can provide strong support for fine-grained security analysis of policies, and help to correctly model and conFigure policies during policy modeling, implementation and verification.

The long-living nature and byte-addressability of persistent memory (PM) amplifies the importance of strong memory protections. This paper develops temporal exposure reduction protection (TERP) as a framework for enforcing memory safety. Aiming to minimize the time when a PM region is accessible, TERP offers a complementary dimension of memory protection. The paper gives a formal definition of TERP, explores the semantics space of TERP constructs, and the relations with security and composability in both sequential and parallel executions. It proposes programming system and architecture solutions for the key challenges for the adoption of TERP, which draws on novel supports in both compilers and hardware to efficiently meet the exposure time target. Experiments validate the efficacy of the proposed support of TERP, in both efficiency and exposure time minimization.

Vulnerability detection has always been an essential part of maintaining information security, and the existing work can significantly improve the performance of vulnerability detection. However, due to the differences in representation forms and deep learning models, various methods still have some limitations. In order to overcome this defect, We propose a vulnerability detection method VDBWGDL, based on weight graphs and deep learning. Firstly, it accurately locates vulnerability-sensitive keywords and generates variant codes that satisfy vulnerability trigger logic and programmer programming style through code variant methods. Then, the control flow graph is sliced for vulnerable code keywords and program critical statements. The code block is converted into a vector containing rich semantic information and input into the weight map through the deep learning model. According to specific rules, different weights are set for each node. Finally, the similarity is obtained through the similarity comparison algorithm, and the suspected vulnerability is output according to different thresholds. VDBWGDL improves the accuracy and F1 value by 3.98% and 4.85% compared with four state-of-the-art models. The experimental results prove the effectiveness of VDBWGDL.

With memory safety and security issues continuing to plague modern systems, security is rapidly becoming a first class priority in new architectures and competes directly with performance and power efficiency. The capability-based architecture model provides a promising solution to many memory vulnerabilities by replacing plain addresses with capabilities, i.e., addresses and related metadata. A key advantage of the capability model is compatibility with existing code bases. Capabilities can be implemented transparently to a programmer, i.e., without source code changes. Capabilities leverage semantics in source code to describe access permissions but require customized compilers to translate the semantics to their binary equivalent.In this work, we introduce a complete capabilityaware compiler toolchain for such secure architectures. We illustrate the compiler construction with a RISC-V capability-based architecture, called Zeno. As a securityfocused, large-scale, global shared memory architecture, Zeno implements a Namespace-based capability model for accesses. Namespace IDs (NSID) are encoded with an extended addressing model to associate them with access permission metadata elsewhere in the system. The NSID extended addressing model requires custom compiler support to fully leverage the protections offered by Namespaces. The Zeno compiler produces code transparently to the programmer that is aware of Namespaces and maintains their integrity. The Zeno assembler enables custom Zeno instructions which support secure memory operations. Our results show that our custom toolchain moderately increases the binary size compared to nonZeno compilation. We find the minimal overhead incurred by the additional NSID management instructions to be an acceptable trade-off for the memory safety and security offered by Zeno Namespaces.

We study semantic security for classical-quantum channels. Our security functions are functional forms of mosaics of combinatorial designs. We extend methods in [25] from classical channels to classical-quantum channels to demonstrate that mosaics of designs ensure semantic security for classical-quantum channels, and are also capacity achieving coding schemes. An advantage of these modular wiretap codes is that we provide explicit code constructions that can be implemented in practice for every channel, given an arbitrary public code.

Recent studies show that the state-of-the-art deep neural networks are vulnerable to model inversion attacks, in which access to a model is abused to reconstruct private training data of any given target class. Existing attacks rely on having access to either the complete target model (whitebox) or the model's soft-labels (blackbox). However, no prior work has been done in the harder but more practical scenario, in which the attacker only has access to the model's predicted label, without a confidence measure. In this paper, we introduce an algorithm, Boundary-Repelling Model Inversion (BREP-MI), to invert private training data using only the target model's predicted labels. The key idea of our algorithm is to evaluate the model's predicted labels over a sphere and then estimate the direction to reach the target class's centroid. Using the example of face recognition, we show that the images reconstructed by BREP-MI successfully reproduce the semantics of the private training data for various datasets and target model architectures. We compare BREP-MI with the state-of-the-art white-box and blackbox model inversion attacks, and the results show that despite assuming less knowledge about the target model, BREP-MI outperforms the blackbox attack and achieves comparable results to the whitebox attack. Our code is available online.11https://github.com/m-kahla/Label-Only-Model-Inversion-Attacks-via-Boundary-Repulsion

Deep learning-based semantic communications (DLSC) significantly improve communication efficiency by only transmitting the meaning of the data rather than a raw message. Such a novel paradigm can brace the high-demand applications with massive data transmission and connectivities, such as automatic driving and internet-of-things. However, DLSC are also highly vulnerable to various attacks, such as eavesdropping, surveillance, and spoofing, due to the openness of wireless channels and the fragility of neural models. To tackle this problem, we present SemKey, a novel physical layer key generation (PKG) scheme that aims to secure the DLSC by exploring the underlying randomness of deep learning-based semantic communication systems. To boost the generation rate of the secret key, we introduce a reconfigurable intelligent surface (RIS) and tune its elements with the randomness of semantic drifts between a transmitter and a receiver. Precisely, we first extract the random features of the semantic communication system to form the randomly varying switch sequence of the RIS-assisted channel and then employ the parallel factor-based channel detection method to perform the channel detection under RIS assistance. Experimental results show that our proposed SemKey significantly improves the secret key generation rate, potentially paving the way for physical layer security for DLSC.

Since deep learning (DL) can automatically learn features from source code, it has been widely used to detect source code vulnerability. To achieve scalable vulnerability scanning, some prior studies intend to process the source code directly by treating them as text. To achieve accurate vulnerability detection, other approaches consider distilling the program semantics into graph representations and using them to detect vulnerability. In practice, text-based techniques are scalable but not accurate due to the lack of program semantics. Graph-based methods are accurate but not scalable since graph analysis is typically time-consuming. In this paper, we aim to achieve both scalability and accuracy on scanning large-scale source code vulnerabilities. Inspired by existing DL-based image classification which has the ability to analyze millions of images accurately, we prefer to use these techniques to accomplish our purpose. Specifically, we propose a novel idea that can efficiently convert the source code of a function into an image while preserving the program details. We implement Vul-CNN and evaluate it on a dataset of 13,687 vulnerable functions and 26,970 non-vulnerable functions. Experimental results report that VulCNN can achieve better accuracy than eight state-of-the-art vul-nerability detectors (i.e., Checkmarx, FlawFinder, RATS, TokenCNN, VulDeePecker, SySeVR, VulDeeLocator, and Devign). As for scalability, VulCNN is about four times faster than VulDeePecker and SySeVR, about 15 times faster than VulDeeLocator, and about six times faster than Devign. Furthermore, we conduct a case study on more than 25 million lines of code and the result indicates that VulCNN can detect large-scale vulnerability. Through the scanning reports, we finally discover 73 vulnerabilities that are not reported in NVD.

Smart metering is a mechanism through which fine-grained electricity usage data of consumers is collected periodically in a smart grid. However, a growing concern in this regard is that the leakage of consumers' consumption data may reveal their daily life patterns as the state-of-the-art metering strategies lack adequate security and privacy measures. Many proposed solutions have demonstrated how the aggregated metering information can be transformed to obscure individual consumption patterns without affecting the intended semantics of smart grid operations. In this paper, we expose a complete break of such an existing privacy preserving metering scheme [10] by determining individual consumption patterns efficiently, thus compromising its privacy guarantees. The underlying methodol-ogy of this scheme allows us to - i) retrieve the lower bounds of the privacy parameters and ii) establish a relationship between the privacy preserved output readings and the initial input readings. Subsequently, we present a rigorous experimental validation of our proposed attacking methodology using real-life dataset to highlight its efficacy. In summary, the present paper queries: Is the Whole lesser than its Parts? for such privacy aware metering algorithms which attempt to reduce the information leakage of aggregated consumption patterns of the individuals.

A formal modeling language MCD for concurrent systems is proposed, and its syntax, semantics and formal definitions are given. MCD uses modules as basic components, and that the detection rules are not perfect, resulting in packets that do not belong to intrusion attacks being misjudged as attacks, respectively. Then the data detection algorithm based on MCD concurrency model protects hidden computer viruses and security threats, and the efficiency is increased by 7.5% Finally, the computer network security protection system is researched based on security modeling.

In recent years, the security of AI systems has drawn increasing research attention, especially in the medical imaging realm. To develop a secure medical image analysis (MIA) system, it is a must to study possible backdoor attacks (BAs), which can embed hidden malicious behaviors into the system. However, designing a unified BA method that can be applied to various MIA systems is challenging due to the diversity of imaging modalities (e.g., X-Ray, CT, and MRI) and analysis tasks (e.g., classification, detection, and segmentation). Most existing BA methods are designed to attack natural image classification models, which apply spatial triggers to training images and inevitably corrupt the semantics of poisoned pixels, leading to the failures of attacking dense prediction models. To address this issue, we propose a novel Frequency-Injection based Backdoor Attack method (FIBA) that is capable of delivering attacks in various MIA tasks. Specifically, FIBA leverages a trigger function in the frequency domain that can inject the low-frequency information of a trigger image into the poisoned image by linearly combining the spectral amplitude of both images. Since it preserves the semantics of the poisoned image pixels, FIBA can perform attacks on both classification and dense prediction models. Experiments on three benchmarks in MIA (i.e., ISIC-2019 [4] for skin lesion classification, KiTS-19 [17] for kidney tumor segmentation, and EAD-2019 [1] for endoscopic artifact detection), validate the effectiveness of FIBA and its superiority over stateof-the-art methods in attacking MIA models and bypassing backdoor defense. Source code will be available at code.

In the recent years, we have witnessed quite notable cyber-attacks targeting industrial automation control systems. Upgrading their cyber security is a challenge, not only due to long equipment lifetimes and legacy protocols originally designed to run in air-gapped networks. Even where multiple data sources are available and collection established, data interpretation usable across the different data sources remains a challenge. A modern hydro power plant contains the data sources that range from the classical distributed control systems to newer IoT- based data sources, embedded directly within the plant equipment and deeply integrated in the process. Even abundant collected data does not solve the security problems by itself. The interpretation of data semantics is limited as the data is effectively siloed. In this paper, the relevance of semantic integration of diverse data sources is presented in the context of a hydro power plant. The proposed semantic integration would increase the data interoperability, unlocking the data siloes and thus allowing ingestion of complementary data sources. The principal target of the data interoperability is to support the data-enhanced cyber security in an operational hydro power plant context. Furthermore, the opening of the data siloes would enable additional usage of the existing data sources in a structured semantically enriched form.

Obfuscation refers to changing the structure of code in a way that original semantics can be hidden. These techniques are often used by application developers for code hardening but it has been found that obfuscation techniques are widely used by malware developers in order to hide the work flow and semantics of malicious code. Class Encryption, Code Re-Ordering, Junk Code insertion and Control Flow modifications are Code Obfuscation techniques. In these techniques, code of the application is changed. These techniques change the signature of the application and also affect the systems that use sequence of instructions in order to detect maliciousness of an application. In this paper an ’Opcode sequence’ based detection system is designed and tested against obfuscated samples. It has been found that the system works efficiently for the detection of non obfuscated samples but the performance is effected significantly against obfuscated samples. The study tests different code obfuscation schemes and reports the effect of each on sequential opcode based analytic system.