Recent advances in generative models have led to their application in password guessing, with the aim of replicating the complexity, structure, and patterns of human-created passwords. Despite their potential, inconsistencies and inadequate evaluation methodologies in prior research have hindered meaningful comparisons and a comprehensive, unbiased understanding of their capabilities. This paper introduces MAYA, a unified, customizable, plug-and-play benchmarking framework designed to facilitate the systematic characterization and benchmarking of generative password-guessing models in the context of trawling attacks. Using MAYA, we conduct a comprehensive assessment of six state-of-the-art approaches, which we re-implemented and adapted to ensure standardization. Our evaluation spans eight real-world password datasets and covers an exhaustive set of advanced testing scenarios, totaling over 15,000 compute hours. Our findings indicate that these models effectively capture different aspects of human password distribution and exhibit strong generalization capabilities. However, their effectiveness varies significantly with long and complex passwords. Through our evaluation, sequential models consistently outperform other generative architectures and traditional password-guessing tools, demonstrating unique capabilities in generating accurate and complex guesses. Moreover, the diverse password distributions learned by the models enable a multi-model attack that outperforms the best individual model. By releasing MAYA, we aim to foster further research, providing the community with a new tool to consistently and reliably benchmark generative password-guessing models. Our framework is publicly available at https://github.com/williamcorrias/MAYA-Password-Benchmarking.

Ransomware attacks have caused billions of dollars in damages in recent years, and are expected to cause billions more in the future. Consequently, significant effort has been devoted to ransomware detection and mitigation. Behavioral-based ransomware detection approaches have garnered considerable attention recently. These behavioral detectors typically rely on process-based behavioral profiles to identify malicious behaviors. However, with an increasing body of literature highlighting the vulnerability of such approaches to evasion attacks, a comprehensive solution to the ransomware problem remains elusive. This paper presents Minerva, a novel robust approach to ransomware detection. Minerva is engineered to be robust by design against evasion attacks, with architectural and feature selection choices informed by their resilience to adversarial manipulation. We conduct a comprehensive analysis of Minerva across a diverse spectrum of ransomware types, encompassing unseen ransomware as well as variants designed specifically to evade Minerva. Our evaluation showcases the ability of Minerva to accurately identify ransomware, generalize to unseen threats, and withstand evasion attacks. Furthermore, over of detected ransomware are identified within 0.52sec of activity, enabling the adoption of data loss prevention techniques with near-zero overhead.

Network traffic analysis attacks represent a significant threat to information security and user privacy. Leveraging machine learning, these attacks can infer sensitive information even when encryption and anonymization techniques are in place. This paper proposes TravelingTogether, a novel framework that leverages packet aggregation from multiple source hosts to defend users against network traffic analysis. TravelingTogether works at the network level, providing transparent and seamless protection to any hosts connected to the network. We evaluate our defense across different scenarios through a comprehensive set of experiments, demonstrating its effectiveness in thwarting website fingerprinting attacks as a representative use case, and its efficiency in terms of low time and bandwidth overhead.

Training high-quality deep learning models is a challenging task due to computational and technical requirements. A growing number of individuals, institutions, and companies increasingly rely on pre-trained, third-party models made available in public repositories. These models are often used directly or integrated in product pipelines with no particular precautions, since they are effectively just data in tensor form and considered safe. In this paper, we raise awareness of a new machine learning supply chain threat targeting neural networks. We introduce MaleficNet 2.0, a novel technique to embed self-extracting, self-executing malware in neural networks. MaleficNet 2.0 uses spread-spectrum channel coding combined with error correction techniques to inject malicious payloads in the parameters of deep neural networks. MaleficNet 2.0 injection technique is stealthy, does not degrade the performance of the model, and is robust against removal techniques. We design our approach to work both in traditional and distributed learning settings such as Federated Learning, and demonstrate that it is effective even when a reduced number of bits is used for the model parameters. Finally, we implement a proof-of-concept self-extracting neural network malware using MaleficNet 2.0, demonstrating the practicality of the attack against a widely adopted machine learning framework. Our aim with this work is to raise awareness against these new, dangerous attacks both in the research community and industry, and we hope to encourage further research in mitigation techniques against such threats.

Moving Target Defense and Cyber Deception emerged in recent years as two key proactive cyber defense approaches, contrasting with the static nature of the traditional reactive cyber defense. The key insight behind these approaches is to impose an asymmetric disadvantage for the attacker by using deception and randomization techniques to create a dynamic attack surface. Moving Target Defense (MTD) typically relies on system randomization and diversification, while Cyber Deception is based on decoy nodes and fake systems to deceive attackers. However, current Moving Target Defense techniques are complex to manage and can introduce high overheads, while Cyber Deception nodes are easily recognized and avoided by adversaries. This paper presents DOLOS, a novel architecture that unifies Cyber Deception and Moving Target Defense approaches. DOLOS is motivated by the insight that deceptive techniques are much more powerful when integrated into production systems rather than deployed alongside them. DOLOS combines typical Moving Target Defense techniques, such as randomization, diversity, and redundancy, with cyber deception and seamlessly integrates them into production systems through multiple layers of isolation. We extensively evaluate DOLOS against a wide range of attackers, ranging from automated malware to professional penetration testers, and show that DOLOS is effective in slowing down attacks and protecting the integrity of production systems. We also provide valuable insights and considerations for the future development of MTD techniques based on our findings.

Recent advances in generative machine learning models rekindled research interest in the area of password guessing. Data-driven password guessing approaches based on GANs, language models, and deep latent variable models have shown impressive generalization performance and offer compelling properties for the task of password guessing.This paper proposes PassFlow, a flow-based generative model approach to password guessing. Flow-based models allow for precise log-likelihood computation and optimization, which enables exact latent variable inference. Additionally, flow-based models provide meaningful latent space representation, which enables operations such as exploration of specific subspaces of the latent space and interpolation. We demonstrate the applicability of generative flows to the context of password guessing, departing from previous applications of flow-networks which are mainly limited to the continuous space of image generation. We show that PassFlow is able to outperform prior state-of-the-art GAN-based approaches in the password guessing task while using a training set that is orders of magnitudes smaller than that of prior art. Furthermore, a qualitative analysis of the generated samples shows that PassFlow can accurately model the distribution of the original passwords, with even non-matched samples closely resembling human-like passwords.

Abstract Recent progress in machine learning has led to promising results in behavioral malware detection. Behavioral modeling identifies malicious processes via features derived by their runtime behavior. Behavioral features hold great promise as they are intrinsically related to the functioning of each malware, and are therefore considered difficult to evade. Indeed, while a significant amount of results exists on evasion of static malware features, evasion of dynamic features has seen limited work. This paper examines the robustness of behavioral ransomware detectors to evasion and proposes multiple novel techniques to evade them. Ransomware behavior differs significantly from that of benign processes, making it an ideal best case for behavioral detectors, and a difficult candidate for evasion. We identify and propose a set of novel attacks that distribute the overall malware workload across a small set of independent, cooperating processes in order to avoid the generation of significant behavioral features. Our most effective attack decreases the accuracy of a state-of-the-art classifier from 98.6 to 0% using only 18 cooperating processes. Furthermore, we show our attacks to be effective against commercial ransomware detectors in a black-box setting. Finally, we evaluate a detector designed to identify our most effective attack, as well as discuss potential directions to mitigate our most advanced attack.

Abstract Several cybersecurity domains, such as ransomware detection, forensics and data analysis, require methods to reliably identify encrypted data fragments. Typically, current approaches employ statistics derived from byte-level distribution, such as entropy estimation, to identify encrypted fragments. However, modern content types use compression techniques which alter data distribution pushing it closer to the uniform distribution. The result is that current approaches exhibit unreliable encryption detection performance when compressed data appear in the dataset. Furthermore, proposed approaches are typically evaluated over few data types and fragment sizes, making it hard to assess their practical applicability. This paper compares existing statistical tests on a large, standardized dataset and shows that current approaches consistently fail to distinguish encrypted and compressed data on both small and large fragment sizes. We address these shortcomings and design EnCoD, a learning-based classifier which can reliably distinguish compressed and encrypted data. We evaluate EnCoD on a dataset of 16 different file types and fragment sizes ranging from 512B to 8KB. Our results highlight that EnCoD outperforms current approaches by a wide margin, with accuracy ranging from $$\sim 82\%$$ ∼ 82 % for 512B fragments up to $$\sim 92\%$$ ∼ 92 % for 8KB data fragments. Moreover, EnCoD can pinpoint the exact format of a given data fragment, rather than performing only binary classification like previous approaches.

Economic incentives encourage malware authors to constantly develop new, increasingly complex malware to steal sensitive data or blackmail individuals and companies into paying large ransoms. In 2017, the worldwide economic impact of cyberattacks is estimated to be between 445 and 600 billion USD, or 0.8% of global GDP. Traditionally, one of the approaches used to defend against malware is network traffic analysis, which relies on network data to detect the presence of potentially malicious software. However, to keep up with increasing network speeds and amount of traffic, network analysis is generally limited to work on aggregated network data, which is traditionally challenging and yields mixed results. In this paper we present MalPhase, a system that was designed to cope with the limitations of aggregated flows. MalPhase features a multi-phase pipeline for malware detection, type and family classification. The use of an extended set of network flow features and a simultaneous multi-tier architecture facilitates a performance improvement for deep learning models, making them able to detect malicious flows (>98% F1) and categorize them to a respective malware type (>93% F1) and family (>91% F1). Furthermore, the use of robust features and denoising autoencoders allows MalPhase to perform well on samples with varying amounts of benign traffic mixed in. Finally, MalPhase detects unseen malware samples with performance comparable to that of known samples, even when interlaced with benign flows to reflect realistic network environments.

Information-Centric Networking (ICN) is a novel network architecture designed to replace the current IP-based architecture. In ICN, contents are identified based on unique names and can be cached in-network in order to immediately serve subsequent requests. These characteristics are particularly important in the context of the Internet of Things (IoT), where they allow to heavily reduce loads on the things, as well as increase content availability and decrease energy consumption. In this paper we address the open problem of providing access control for IoT deployments in ICN. Our protocol takes advantage of the reliance of IoT on Infrastructure-as-a-Service and provides confidentiality, traitor tracing and revocation of an unbound number of users. At the same time, our protocol preserves both network caching and location-independent content retrieval. To the best of our knowledge, our protocol is the first access control protocol for ICN providing all these advantages. We provide an extensive analysis of the security properties of our protocol, as well as a thorough experimental evaluation. Our evaluation shows that our protocol does not pose significant over-head with respect to published content size nor computational time required. Considering a popular IoT camera, our evaluation shows that our protocol introduces 0.27% size overhead and 150ms of computational overhead for a 7 seconds stream.

Software defined networking (SDN) is a new networking paradigm that in recent years has revolutionized network architectures. At its core, SDN separates the data plane, which provides data forwarding functionalities, and the control plane, which implements the network control logic. The separation of these two components provides a virtually centralized point of control in the network, and at the same time abstracts the complexity of the underlying physical infrastructure. Unfortunately, while promising, the SDN approach also introduces new attacks and vulnerabilities. Indeed, previous research shows that, under certain traffic conditions, the required communication between the control and data plane can result in a bottleneck. An attacker can exploit this limitation to mount a new, network-wide, type of denial of service attack, known as the control plane saturation attack. This paper presents LineSwitch, an efficient and effective data plane solution to tackle the control plane saturation attack. LineSwitch employs probabilistic proxying and blacklisting of network traffic to prevent the attack from reaching the control plane, and thus preserve network functionality. We implemented LineSwitch as an extension of the reference SDN implementation, OpenFlow, and run a thorough set of experiments under different traffic and attack scenarios. We compared LineSwitch to the state of the art, and we show that it provides at the same time, the same level of protection against the control plane saturation attack, and a reduced time overhead by up to 30%.

Software Defined Networking (SDN) is a new networking architecture that aims to provide better decoupling between network control (control plane) and data forwarding functionalities (data plane). This separation introduces several benefits, such as a directly programmable and (virtually) centralized network control. However, researchers showed that the required communication channel between the control and data plane of SDN creates a potential bottleneck in the system, introducing new vulnerabilities.Indeed, this behavior could be exploited to mount powerful attacks, such as the control plane saturation attack, that can severely hinder the performance of the whole network.