Search

Federated Learning (FL) heavily depends on label quality for its performance. However, the label distribution among individual clients is always both noisy and heterogeneous. The high loss incurred by client-specific samples in heterogeneous label noise poses challenges for distinguishing between client-specific and noisy label samples, impacting the effectiveness of existing label noise learning approaches. To tackle this issue, we propose FedFixer, where the personalized model is introduced to cooperate with the global model to effectively select clean client-specific samples. In the dual models, updating the personalized model solely at a local level can lead to overfitting on noisy data due to limited samples, consequently affecting both the local and global models' performance. To mitigate overfitting, we address this concern from two perspectives. Firstly, we employ a confidence regularizer to alleviate the impact of unconfident predictions caused by label noise. Secondly, a distance regularizer is implemented to constrain the disparity between the personalized and global models. We validate the effectiveness of FedFixer through extensive experiments on benchmark datasets. The results demonstrate that FedFixer can perform well in filtering noisy label samples on different clients, especially in highly heterogeneous label noise scenarios., Comment: accepted by AAA24

This article addresses the problem of automatically generating attack trees that soundly and clearly describe the ways the system can be attacked. Soundness means that the attacks displayed by the attack tree are indeed attacks in the system; clarity means that the tree is efficient in communicating the attack scenario. To pursue clarity, we introduce an attack-tree generation algorithm that minimises the tree size and the information length of its labels without sacrificing correctness. We achieve this by i) introducing a system model that allows to reason about attacks and goals in an efficient manner, and ii) by establishing a connection between the problem of factorising algebraic expressions and the problem of minimising the tree size. To the best of our knowledge, we introduce the first attack-tree generation framework that optimises the labelling and shape of the generated trees, while guaranteeing their soundness with respect to a system specification.

Multi-task reinforcement learning and meta-reinforcement learning have been developed to quickly adapt to new tasks, but they tend to focus on tasks with higher rewards and more frequent occurrences, leading to poor performance on tasks with sparse rewards. To address this issue, GFlowNets can be integrated into meta-learning algorithms (GFlowMeta) by leveraging the advantages of GFlowNets on tasks with sparse rewards. However, GFlowMeta suffers from performance degradation when encountering heterogeneous transitions from distinct tasks. To overcome this challenge, this paper proposes a personalized approach named pGFlowMeta, which combines task-specific personalized policies with a meta policy. Each personalized policy balances the loss on its personalized task and the difference from the meta policy, while the meta policy aims to minimize the average loss of all tasks. The theoretical analysis shows that the algorithm converges at a sublinear rate. Extensive experiments demonstrate that the proposed algorithm outperforms state-of-the-art reinforcement learning algorithms in discrete environments., Comment: journal

In recent years, the number of cyber attacks has grown rapidly. An effective way to reduce the attack surface and protect software is adoption of methodologies that apply security at each step of the software development lifecycle. While different methodologies have been proposed to address software security, recent research shows an increase in the number of vulnerabilities in software and data breaches. Therefore, the security practices incorporated in secure software development methodologies require investigation. This paper provides an overview of security practices involved in 28 secure software development methodologies from industry, government, and academia. To achieve this goal, we distributed the security practices among the software development lifecycle stages. We also investigated auxiliary (non-technical) practices, such as organizational, behavioral, legal, policy, and governance aspects that are incorporated in the secure software development methodologies. Furthermore, we explored methods used to provide evidence of the effectiveness of the methodologies. Finally, we present the gaps that require attention in the scientific community. The results of our survey may assist researchers and organizations to better understand the existing security practices integrated into the secure software development methodologies. In addition, our bridge between "technical" and "non-technical" worlds may be useful for non-technical specialists who investigate software security. Moreover, exploring the gaps that we found in current research may help improve security in software development and produce software with fewer number of vulnerabilities., Comment: 27 pages, 2 figures

Exploit proof-of-concepts (PoCs) for known vulnerabilities are widely shared in the security community. They help security analysts to learn from each other and they facilitate security assessments and red teaming tasks. In the recent years, PoCs have been widely distributed, e.g., via dedicated websites and platforms, and public code repositories such as GitHub. However, there is no guarantee that PoCs in public code repositories come from trustworthy sources or even that they do what they are supposed to do. In this work we investigate GitHub-hosted PoCs for known vulnerabilities discovered in 2017--2021. We discovered that not all PoCs are trustworthy. Some proof-of-concepts are malicious, e.g., they attempt to exfiltrate data from the system they are being run on, or they try to install malware on this system, and in some cases they have hard-coded reverse shell listener. To measure the prevalence of this threat, we propose an approach to detecting malicious PoCs. Our approach relies on the maliciousness symptoms we have observed in our PoC dataset: calls to malicious IP addresses, encoded malicious code, and included Trojanized binaries. With this approach, we have discovered 899 malicious repositories out of 47,285 repositories that have been downloaded and checked (i.e., 1.9% of the studied repositories have indicators of malicious intent). This figure shows a worrying prevalence of dangerous malicious PoCs among the exploit code distributed on GitHub.

Attack trees and attack graphs are both common graphical threat models used by organizations to better understand possible cybersecurity threats. These models have been primarily seen as separate entities, to be used and researched in entirely different contexts, but recently there has emerged a new interest in combining the strengths of these models and in transforming models from one notation into the other. The existing works in this area focus on transforming attack graphs into attack trees. In this paper, we propose an approach to transform attack trees into attack graphs based on the fundamental understanding of how actions are represented in both structures. From this, we hope to enable more versatility in both structures., Comment: 20 pages, 7 figures, Shortened version to be published CRiSIS 2021

Cryptojacking applications pose a serious threat to mobile devices. Due to the extensive computations, they deplete the battery fast and can even damage the device. In this work we make a step towards combating this threat. We collected and manually verified a large dataset of Android mining apps. In this paper, we analyze the gathered miners and identify how they work, what are the most popular libraries and APIs used to facilitate their development, and what static features are typical for this class of applications. Further, we analyzed our dataset using VirusTotal. The majority of our samples is considered malicious by at least one VirusTotal scanner, but 16 apps are not detected by any engine; and at least 5 apks were not seen previously by the service. Mining code could be obfuscated or fetched at runtime, and there are many confusing miner-related apps that actually do not mine. Thus, static features alone are not sufficient for miner detection. We have collected a feature set of dynamic metrics both for miners and unrelated benign apps, and built a machine learning-based tool for dynamic detection. Our BrenntDroid tool is able to detect miners with 95% of accuracy on our dataset. This preprint is a technical report accompanying the paper "Dissecting Android Cryptocurrency Miners" published in ACM CODASPY 2020.

Today, there are millions of third-party Android applications. Some of these applications are buggy or even malicious. To identify such applications, novel frameworks for automated black-box testing and dynamic analysis are being developed by the Android community, including Google. Code coverage is one of the most common metrics for evaluating effectiveness of these frameworks. Furthermore, code coverage is used as a fitness function for guiding evolutionary and fuzzy testing techniques. However, there are no reliable tools for measuring fine-grained code coverage in black-box Android app testing. We present the Android Code coVerage Tool, ACVTool for short, that instruments Android apps and measures the code coverage in the black-box setting at the class, method and instruction granularities. ACVTool has successfully instrumented 96.9% of apps in our experiments. It introduces a negligible instrumentation time overhead, and its runtime overhead is acceptable for automated testing tools. We show in a large-scale experiment with Sapienz, a state-of-art testing tool, that the fine-grained instruction-level code coverage provided by ACVTool helps to uncover a larger amount of faults than coarser-grained code coverage metrics.

Attack trees are considered a useful tool for security modelling because they support qualitative as well as quantitative analysis. The quantitative approach is based on values associated to each node in the tree, expressing, for instance, the minimal cost or probability of an attack. Current quantitative methods for attack trees allow the analyst to, based on an initial assignment of values to the leaf nodes, derive the values of the higher nodes in the tree. In practice, however, it shows to be very difficult to obtain reliable values for all leaf nodes. The main reasons are that data is only available for some of the nodes, that data is available for intermediate nodes rather than for the leaf nodes, or even that the available data is inconsistent. We address these problems by developing a generalisation of the standard bottom-up calculation method in three ways. First, we allow initial attributions of non-leaf nodes. Second, we admit additional relations between attack steps beyond those provided by the underlying attack tree semantics. Third, we support the calculation of an approximative solution in case of inconsistencies. We illustrate our method, which is based on constraint programming, by a comprehensive case study.

Recently security researchers have started to look into automated generation of attack trees from socio-technical system models. The obvious next step in this trend of automated risk analysis is automating the selection of security controls to treat the detected threats. However, the existing socio-technical models are too abstract to represent all security controls recommended by practitioners and standards. In this paper we propose an attack-defence model, consisting of a set of attack-defence bundles, to be generated and maintained with the socio-technical model. The attack-defence bundles can be used to synthesise attack-defence trees directly from the model to offer basic attack-defence analysis, but also they can be used to select and maintain the security controls that cannot be handled by the model itself., Comment: GraMSec 2015, 16 pages

We propose a flexible framework that can be easily customized to enforce a large variety of information flow properties. Our framework combines the ideas of secure multi-execution and map-reduce computations. The information flow property of choice can be obtained by simply changes to a map (or reduce) program that control parallel executions. We present the architecture of the enforcement mechanism and its customizations for non-interference (NI) (from Devriese and Piessens) and some properties proposed by Mantel, such as removal of inputs (RI) and deletion of inputs (DI), and demonstrate formally soundness and precision of enforcement for these properties., Comment: 40 pages