Fabio De Gaspari

Machine learning has brought significant advances in cybersecurity, particularly in the development of Intrusion Detection Systems (IDS). These improvements are mainly attributed to the ability of machine learning algorithms to identify complex relationships between features and effectively generalize to unseen data. Deep neural networks, in particular, contributed to this progress by enabling the analysis of large amounts of training data, significantly enhancing detection performance. However, machine learning models remain vulnerable to adversarial attacks, where carefully crafted input data can mislead the model into making incorrect predictions. While adversarial threats in unstructured data, such as images and text, have been extensively studied, their impact on structured data like network traffic is less explored. This survey aims to address this gap by providing a comprehensive review of machine learning-based Network Intrusion Detection Systems (NIDS) and analyzing their susceptibility to adversarial attacks, with a specific focus on evasion attacks due to their prevalence and real-world relevance. We critically examine existing research in NIDS, highlighting key trends, strengths, and limitations, while identifying areas that require further exploration. We also provide practical recommendations for adapting adversarial strategies to network-specific constraints. Additionally, we discuss emerging challenges in the field and offer insights for the development of more robust and resilient NIDS. In summary, this paper not only enhances the understanding of adversarial attacks and defenses in NIDS but also connects theoretical and practical perspectives, providing actionable guidance for future research to improve the robustness of machine learning models in cybersecurity applications.

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.

The easy and accurate identification of varieties is fundamental in agriculture, especially in the olive sector, where more than 1200 olive varieties are currently known worldwide. Varietal misidentification leads to many potential problems for all the actors in the sector: farmers and nursery workers may establish the wrong variety, leading to its maladaptation in the field; olive oil and table olive producers may label and sell a non-authentic product; consumers may be misled; and breeders may commit errors during targeted crossings between different varieties. To date, the standard for varietal identification and certification consists of two methods: morphological classification and genetic analysis. The morphological classification consists of the visual pairwise comparison of different organs of the olive tree, where the most important organ is considered to be the endocarp. In contrast, different methods for genetic classification exist (RAPDs, SSR, and SNP). Both classification methods present advantages and disadvantages. Visual morphological classification requires highly specialized personnel and is prone to human error. Genetic identification methods are more accurate but incur a high cost and are difficult to implement. This paper introduces OliVaR, a novel approach to olive varietal identification. OliVaR uses a teacher-student deep learning architecture to learn the defining characteristics of the endocarp of each specific olive variety and perform classification. We construct what is, to the best of our knowledge, the largest olive variety dataset to date, comprising image data for 131 varieties from the Mediterranean basin. We thoroughly test OliVaR on this dataset and show that it correctly predicts olive varieties with over 86% accuracy.

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.

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. In this paper, we propose 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 previous 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.