恶意软件检测在网络安全中起着至关重要的作用,随着恶意软件增长的增加和网络攻击的进步。以前看不见的恶意软件不是由安全供应商确定的,这些恶意软件通常在这些攻击中使用,并且不可避免地要找到可以从未标记的样本数据中自学习的解决方案。本文介绍了Sherlock,这是一种基于自学的深度学习模型,可根据视觉变压器(VIT)体系结构检测恶意软件。 Sherlock是一种新颖的恶意软件检测方法,它可以通过使用基于图像的二进制表示形式来学习独特的功能,以区分恶意软件和良性程序。在47种类型和696个家庭的层次结构中使用120万个Android应用的实验结果表明,自我监督的学习可以达到97%的恶意软件分类,而恶意软件的二进制分类比现有的最新技术更高。我们提出的模型还能够胜过针对多级恶意软件类型和家庭的最先进技术,分别为.497和.491。
translated by 谷歌翻译
随着基于图像的二进制表示,计算机视觉在自动化恶意软件检测中起着越来越重要的作用。这些二进制图像快速生成,不需要功能工程,并且对流行的混淆方法有弹性。但是,在该领域进行了重大研究,但是它仅限于仅少数行业实验室和研究团队可以使用的小型或私人数据集。这种缺乏可用性阻碍了对现有工作的研究,新研究的发展以及思想的传播。我们发布了最大的公共网络安全图像数据库Malnet-Image,比现有数据库多24倍的图像和70倍的类别(可在https://mal-net.org上获得)。 Malnet-图像包含超过120万张恶意软件图像 - 遍及47种类型和696个家庭 - 通过使研究人员和实践者能够评估以前在礼节环境中报道的技术来使基于图像的恶意软件能力民主化。我们在二进制图像上报告了第一个百万尺度的恶意软件检测结果。 MALNET-IMAGE解锁了新的独特机会,可以推进机器学习的前沿,从而使新的研究方向可以进入基于视觉的网络防御,多类不平衡分类和可解释的安全性。
translated by 谷歌翻译
恶意应用程序(尤其是针对Android平台的应用程序)对开发人员和最终用户构成了严重威胁。许多研究工作都致力于开发有效的方法来防御Android恶意软件。但是,鉴于Android恶意软件的爆炸性增长以及恶意逃避技术(如混淆和反思)的持续发展,基于手动规则或传统机器学习的Android恶意软件防御方法可能无效。近年来,具有强大功能抽象能力的主要研究领域称为“深度学习”(DL),在各个领域表现出了令人信服和有希望的表现,例如自然语言处理和计算机视觉。为此,采用深度学习技术来阻止Android恶意软件攻击,最近引起了广泛的研究关注。然而,没有系统的文献综述着重于针对Android恶意软件防御的深度学习方法。在本文中,我们进行了系统的文献综述,以搜索和分析在Android环境中恶意软件防御的背景下采用了如何应用的。结果,确定了涵盖2014 - 2021年期间的132项研究。我们的调查表明,尽管大多数这些来源主要考虑基于Android恶意软件检测的基于DL,但基于其他方案的53项主要研究(40.1%)设计防御方法。这篇综述还讨论了基于DL的Android恶意软件防御措施中的研究趋势,研究重点,挑战和未来的研究方向。
translated by 谷歌翻译
恶意软件系列的分类对于全面了解他们如何感染设备,计算机或系统的全面了解至关重要。因此,恶意软件识别使安全研究人员和事件响应者能够采取防止恶意软件的预防措施并加速缓解。由于这些序列代表恶意软件的行为,恶意软件由恶意软件制作的API呼叫序列是广泛利用的机器和深度学习模型的特征。但是,传统的机器和深度学习模型仍然无法捕获API呼叫之间的序列关系。另一方面,基于变压器的模型作为整体过程序列,并且由于多针注意机制和位置嵌入而学习API调用之间的关系。我们的实验表明,具有一个变压器块层的变压器模型超越了广泛使用的基础架构,LSTM。此外,伯特或犬,预先训练的变压器模型,在根据评估指标,F1分数和AUC分数分类高度不平衡恶意软件系列方面表现优于分类高度不平衡的恶意软件系列。此外,拟议的基于袋的随机变压器森林(RTF),伯特或犬的集合,已经达到了四个数据集中的三个,特别是最先进的F1 - 在一个常用的基准数据集中得分为0.6149。
translated by 谷歌翻译
The automation of an increasingly large number of software engineering tasks is becoming possible thanks to Machine Learning (ML). One foundational building block in the application of ML to software artifacts is the representation of these artifacts (e.g., source code or executable code) into a form that is suitable for learning. Many studies have leveraged representation learning, delegating to ML itself the job of automatically devising suitable representations. Yet, in the context of Android problems, existing models are either limited to coarse-grained whole-app level (e.g., apk2vec) or conducted for one specific downstream task (e.g., smali2vec). Our work is part of a new line of research that investigates effective, task-agnostic, and fine-grained universal representations of bytecode to mitigate both of these two limitations. Such representations aim to capture information relevant to various low-level downstream tasks (e.g., at the class-level). We are inspired by the field of Natural Language Processing, where the problem of universal representation was addressed by building Universal Language Models, such as BERT, whose goal is to capture abstract semantic information about sentences, in a way that is reusable for a variety of tasks. We propose DexBERT, a BERT-like Language Model dedicated to representing chunks of DEX bytecode, the main binary format used in Android applications. We empirically assess whether DexBERT is able to model the DEX language and evaluate the suitability of our model in two distinct class-level software engineering tasks: Malicious Code Localization and Defect Prediction. We also experiment with strategies to deal with the problem of catering to apps having vastly different sizes, and we demonstrate one example of using our technique to investigate what information is relevant to a given task.
translated by 谷歌翻译
哥内克人Sentinel Imagery的纯粹卷的可用性为使用深度学习的大尺度创造了新的土地利用陆地覆盖(Lulc)映射的机会。虽然在这种大型数据集上培训是一个非琐碎的任务。在这项工作中,我们试验Lulc Image分类和基准不同最先进模型的Bigearthnet数据集,包括卷积神经网络,多层感知,视觉变压器,高效导通和宽残余网络(WRN)架构。我们的目标是利用分类准确性,培训时间和推理率。我们提出了一种基于用于网络深度,宽度和输入数据分辨率的WRNS复合缩放的高效导通的框架,以有效地训练和测试不同的模型设置。我们设计一种新颖的缩放WRN架构,增强了有效的通道注意力机制。我们提出的轻量级模型具有较小的培训参数,实现所有19个LULC类的平均F分类准确度达到4.5%,并且验证了我们使用的resnet50最先进的模型速度快两倍作为基线。我们提供超过50种培训的型号,以及我们在多个GPU节点上分布式培训的代码。
translated by 谷歌翻译
使用计算机视觉对间接费用的分析是一个问题,在学术文献中受到了很大的关注。在这个领域运行的大多数技术都非常专业,需要大型数据集的昂贵手动注释。这些问题通过开发更通用的框架来解决这些问题,并结合了表示学习的进步,该框架可以更灵活地分析具有有限标记数据的新图像类别。首先,根据动量对比机制创建了未标记的空中图像数据集的强大表示。随后,通过构建5个标记图像的准确分类器来专门用于不同的任务。从6000万个未标记的图像中,成功的低水平检测城市基础设施进化,体现了我们推进定量城市研究的巨大潜力。
translated by 谷歌翻译
恶意软件开发人员使用诸如压缩,加密和混淆等技术的组合来绕过反病毒软件。使用抗分析技术的恶意软件可以绕过基于AI的防病毒软件和恶意软件分析工具。因此,对包装文件进行分类是最大的挑战之一。如果恶意软件分类器学习包装工的功能,而不是恶意软件的功能,就会出现问题。用意外错误的数据训练模型变成中毒攻击,对抗攻击和逃避攻击。因此,研究人员应考虑包装以构建适当的恶意软件分类器模型。在本文中,我们提出了一个多步框架,用于分类和识别包装样本,其中包括伪最佳的功能选择,基于机器学习的分类器和Packer识别步骤。在第一步中,我们使用购物车算法和置换重要性来预选重要的20个功能。在第二步中,每个模型都会学习20个预选功能,以分类具有最高性能的包装文件。结果,XGBoost以置换重要性了解了XGBoost预先选择的功能,其精度为99.67%,F1得分为99.46%,并且在曲线下的F1分数表现出最高的性能(f1)。 AUC)为99.98%。在第三步中,我们提出了一种新方法,该方法只能识别包装工,仅针对被分类为众所周知的包装的样品。
translated by 谷歌翻译
监督学习已被广​​泛用于攻击分类,需要高质量的数据和标签。但是,数据通常是不平衡的,很难获得足够的注释。此外,有监督的模型应遵守现实世界的部署问题,例如防御看不见的人造攻击。为了应对挑战,我们提出了一个半监督的细粒攻击分类框架,该框架由编码器和两个分支机构结构组成,并且该框架可以推广到不同的监督模型。具有残留连接的多层感知器用作提取特征并降低复杂性的编码器。提出了复发原型模块(RPM)以半监督的方式有效地训练编码器。为了减轻数据不平衡问题,我们将重量任务一致性(WTC)引入RPM的迭代过程中,通过将较大的权重分配给损失函数中较少样本的类别。此外,为了应对现实世界部署中的新攻击,我们提出了一种主动调整重新采样(AAR)方法,该方法可以更好地发现看不见的样本数据的分布并调整编码器的参数。实验结果表明,我们的模型优于最先进的半监督攻击检测方法,分类精度提高了3%,训练时间降低了90%。
translated by 谷歌翻译
我们提出“ AITLAS:基准竞技场” - 一个开源基准测试框架,用于评估地球观察中图像分类的最新深度学习方法(EO)。为此,我们介绍了从九种不同的最先进的体系结构得出的400多个模型的全面比较分析,并将它们与来自22个具有不同尺寸的数据集的各种多级和多标签分类任务进行比较和属性。除了完全在这些数据集上训练的模型外,我们还基于在转移学习的背景下训练的模型,利用预训练的模型变体,因为通常在实践中执行。所有提出的方法都是一般的,可以轻松地扩展到本研究中未考虑的许多其他遥感图像分类任务。为了确保可重复性并促进更好的可用性和进一步的开发,所有实验资源在内的所有实验资源,包括训练的模型,模型配置和数据集的处理详细信息(以及用于培训和评估模型的相应拆分)都在存储库上公开可用:HTTPS ://github.com/biasvariancelabs/aitlas-arena。
translated by 谷歌翻译
在深度学习研究中,自学学习(SSL)引起了极大的关注,引起了计算机视觉和遥感社区的兴趣。尽管计算机视觉取得了很大的成功,但SSL在地球观测领域的大部分潜力仍然锁定。在本文中,我们对在遥感的背景下为计算机视觉的SSL概念和最新发展提供了介绍,并回顾了SSL中的概念和最新发展。此外,我们在流行的遥感数据集上提供了现代SSL算法的初步基准,从而验证了SSL在遥感中的潜力,并提供了有关数据增强的扩展研究。最后,我们确定了SSL未来研究的有希望的方向的地球观察(SSL4EO),以铺平了两个领域的富有成效的相互作用。
translated by 谷歌翻译
X-ray imaging technology has been used for decades in clinical tasks to reveal the internal condition of different organs, and in recent years, it has become more common in other areas such as industry, security, and geography. The recent development of computer vision and machine learning techniques has also made it easier to automatically process X-ray images and several machine learning-based object (anomaly) detection, classification, and segmentation methods have been recently employed in X-ray image analysis. Due to the high potential of deep learning in related image processing applications, it has been used in most of the studies. This survey reviews the recent research on using computer vision and machine learning for X-ray analysis in industrial production and security applications and covers the applications, techniques, evaluation metrics, datasets, and performance comparison of those techniques on publicly available datasets. We also highlight some drawbacks in the published research and give recommendations for future research in computer vision-based X-ray analysis.
translated by 谷歌翻译
In this paper, we explore the use of metric learning to embed Windows PE files in a low-dimensional vector space for downstream use in a variety of applications, including malware detection, family classification, and malware attribute tagging. Specifically, we enrich labeling on malicious and benign PE files using computationally expensive, disassembly-based malicious capabilities. Using these capabilities, we derive several different types of metric embeddings utilizing an embedding neural network trained via contrastive loss, Spearman rank correlation, and combinations thereof. We then examine performance on a variety of transfer tasks performed on the EMBER and SOREL datasets, demonstrating that for several tasks, low-dimensional, computationally efficient metric embeddings maintain performance with little decay, which offers the potential to quickly retrain for a variety of transfer tasks at significantly reduced storage overhead. We conclude with an examination of practical considerations for the use of our proposed embedding approach, such as robustness to adversarial evasion and introduction of task-specific auxiliary objectives to improve performance on mission critical tasks.
translated by 谷歌翻译
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 million training examples it was trained on. We release our code and pre-trained model weights at https://github.com/OpenAI/CLIP.
translated by 谷歌翻译
The International Workshop on Reading Music Systems (WoRMS) is a workshop that tries to connect researchers who develop systems for reading music, such as in the field of Optical Music Recognition, with other researchers and practitioners that could benefit from such systems, like librarians or musicologists. The relevant topics of interest for the workshop include, but are not limited to: Music reading systems; Optical music recognition; Datasets and performance evaluation; Image processing on music scores; Writer identification; Authoring, editing, storing and presentation systems for music scores; Multi-modal systems; Novel input-methods for music to produce written music; Web-based Music Information Retrieval services; Applications and projects; Use-cases related to written music. These are the proceedings of the 3rd International Workshop on Reading Music Systems, held in Alicante on the 23rd of July 2021.
translated by 谷歌翻译
Security issues are threatened in various types of networks, especially in the Internet of Things (IoT) environment that requires early detection. IoT is the network of real-time devices like home automation systems and can be controlled by open-source android devices, which can be an open ground for attackers. Attackers can access the network, initiate a different kind of security breach, and compromises network control. Therefore, timely detecting the increasing number of sophisticated malware attacks is the challenge to ensure the credibility of network protection. In this regard, we have developed a new malware detection framework, Deep Squeezed-Boosted and Ensemble Learning (DSBEL), comprised of novel Squeezed-Boosted Boundary-Region Split-Transform-Merge (SB-BR-STM) CNN and ensemble learning. The proposed S.T.M. block employs multi-path dilated convolutional, Boundary, and regional operations to capture the homogenous and heterogeneous global malicious patterns. Moreover, diverse feature maps are achieved using transfer learning and multi-path-based squeezing and boosting at initial and final levels to learn minute pattern variations. Finally, the boosted discriminative features are extracted from the developed deep SB-BR-STM CNN and provided to the ensemble classifiers (SVM, M.L.P., and AdaboostM1) to improve the hybrid learning generalization. The performance analysis of the proposed DSBEL framework and SB-BR-STM CNN against the existing techniques have been evaluated by the IOT_Malware dataset on standard performance measures. Evaluation results show progressive performance as 98.50% accuracy, 97.12% F1-Score, 91.91% MCC, 95.97 % Recall, and 98.42 % Precision. The proposed malware analysis framework is helpful for the timely detection of malicious activity and suggests future strategies.
translated by 谷歌翻译
To date, a large number of research papers have been written on the classification of malware, its identification, classification into different families and the distinction between malware and goodware. These works have been based on captured malware samples and have attempted to analyse malware and goodware using various techniques, including techniques from the field of artificial intelligence. For example, neural networks have played a significant role in these classification methods. Some of this work also deals with analysing malware using its visualisation. These works usually convert malware samples capturing the structure of malware into image structures, which are then the object of image processing. In this paper, we propose a very unconventional and novel approach to malware visualisation based on dynamic behaviour analysis, with the idea that the images, which are visually very interesting, are then used to classify malware concerning goodware. Our approach opens an extensive topic for future discussion and provides many new directions for research in malware analysis and classification, as discussed in conclusion. The results of the presented experiments are based on a database of 6 589 997 goodware, 827 853 potentially unwanted applications and 4 174 203 malware samples provided by ESET and selected experimental data (images, generating polynomial formulas and software generating images) are available on GitHub for interested readers. Thus, this paper is not a comprehensive compact study that reports the results obtained from comparative experiments but rather attempts to show a new direction in the field of visualisation with possible applications in malware analysis.
translated by 谷歌翻译
COVID-19大流行刺激的快速数字化导致了更多的网络犯罪。现在,恶意软件即服务是网络犯罪分子的蓬勃发展的业务。随着恶意软件活动的激增,对于网络辩护人来说,更多地了解他们手头的恶意软件样本,因为这些信息可以极大地影响他们在违规过程中的下一步行动。最近,研究人员展示了如何通过将恶意软件二进制文件转换为灰度图像,然后通过神经网络进行分类来完成恶意软件家庭分类。但是,大多数工作着重于研究不同神经网络体系结构对分类性能的影响。在去年,研究人员表明,通过自我监督学习来增强监督学习可以提高绩效。甚至最近,Data2Vec被提议为一种训练神经网络的情态自我监督框架。在本文中,我们介绍了Binimg2Vec,这是一个培训恶意软件二进制图像分类器的框架,该框架既包含了自我监督的学习和监督学习,又可以产生一个模型,该模型始终优于仅通过监督学习而受过培训的模型。我们能够在分类性能上提高4%,并在多次运行中降低0.5%的性能差异。我们还展示了我们的框架如何产生可以很好地聚类的嵌入,从而促进模型的解释。
translated by 谷歌翻译
由于其最近在减少监督学习的差距方面取得了成功,自我监督的学习方法正在增加计算机愿景的牵引力。在自然语言处理(NLP)中,自我监督的学习和变形金刚已经是选择的方法。最近的文献表明,变压器也在计算机愿景中越来越受欢迎。到目前为止,当使用大规模监督数据或某种共同监督时,视觉变压器已被证明可以很好地工作。在教师网络方面。这些监督的普试视觉变压器在下游任务中实现了非常好的变化,变化最小。在这项工作中,我们调查自我监督学习的预用图像/视觉变压器,然后使用它们进行下游分类任务的优点。我们提出了自我监督的视觉变压器(坐在)并讨论了几种自我监督的培训机制,以获得借口模型。静坐的架构灵活性允许我们将其用作自动统计器,并无缝地使用多个自我监控任务。我们表明,可以在小规模数据集上进行预训练,以便在小型数据集上进行下游分类任务,包括几千个图像而不是数百万的图像。使用公共协议对所提出的方法进行评估标准数据集。结果展示了变压器的强度及其对自我监督学习的适用性。我们通过大边缘表现出现有的自我监督学习方法。我们还观察到坐着很好,很少有镜头学习,并且还表明它通过简单地训练从坐的学到的学习功能的线性分类器来学习有用的表示。预先训练,FineTuning和评估代码将在以下:https://github.com/sara-ahmed/sit。
translated by 谷歌翻译
基于变压器的大型语言模型在自然语言处理中表现出色。通过考虑这些模型在一个领域中获得的知识的可传递性,以及自然语言与高级编程语言(例如C/C ++)的亲密关系,这项工作研究了如何利用(大)基于变压器语言模型检测软件漏洞以及这些模型在漏洞检测任务方面的良好程度。在这方面,首先提出了一个系统的(凝聚)框架,详细介绍了源代码翻译,模型准备和推理。然后,使用具有多个漏洞的C/C ++源代码的软件漏洞数据集进行经验分析,该数据集对应于库功能调用,指针使用,数组使用情况和算术表达式。我们的经验结果证明了语言模型在脆弱性检测中的良好性能。此外,这些语言模型具有比当代模型更好的性能指标,例如F1得分,即双向长期记忆和双向封闭式复发单元。由于计算资源,平台,库和依赖项的要求,对语言模型进行实验始终是具有挑战性的。因此,本文还分析了流行的平台,以有效地微调这些模型并在选择平台时提出建议。
translated by 谷歌翻译