About
60
Publications
24,099
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
1,650
Citations
Introduction
My research combines Cybersecurity and Big Data Analytics with the goal of detecting traces of illicit or anomalous activities. In my research efforts, I strive to find the most appropriate answers by leveraging and combining state-of-the-art techniques and algorithms, especially those within the fields of Time Series analysis and Machine Learning. My expertise lies in analyzing network-related data (such as Network Intrusion Detection System logs, network Flows and Packet Captures), and have recently started focusing on Phishing webpage identification. During the second half of my PhD course, I explored the topic of Adversarial Attacks against machine learning cyber-detectors.
Current institution
Additional affiliations
Education
January 2019 - August 2019
November 2016 - February 2020
December 2013 - July 2016
Publications
Publications (60)
Several advanced cyber attacks adopt the technique of "pivoting" through which attackers create a command propagation tunnel through two or more hosts in order to reach their final target. Identifying such malicious activities is one of the most tough research problems because of several challenges: command propagation is a rare event that cannot b...
Machine learning is adopted in a wide range of domains where it shows its superiority over traditional rule-based algorithms. These methods are being integrated in cyber detection systems with the goal of supporting or even replacing the first level of security analysts. Although the complete automation of detection and analysis is an enticing goal...
As cybersecurity detectors increasingly rely on machine learning mechanisms, attacks to these defenses escalate as well. Supervised classifiers are prone to adver-sarial evasion, and existing countermeasures suffer from many limitations. Most solutions degrade performance in the absence of adversarial perturbations; they are unable to face novel at...
Machine learning algorithms are effective in several applications, but they are not as much successful when applied to intrusion detection in cyber security. Due to the high sensitivity to their training data, cyber detectors based on machine learning are vulnerable to targeted adversarial attacks that involve the perturbation of initial samples. E...
Billions of individuals engage with Online Social Networks (OSN) daily. The owners of OSN try to meet the demands of their end-users while complying with business necessities. Such necessities may, however, lead to the adoption of restrictive data access policies that hinder research activities from "external"' scientists---who may, in turn, resort...
Modern organizations are persistently targeted by phishing emails. Despite advances in detection systems and widespread employee training, attackers continue to innovate, posing ongoing threats. Two emerging vectors stand out in the current landscape: QR-code baits and LLM-enabled pretexting. Yet, little is known about the effectiveness of current...
We study the security of stock price forecasting using Deep Learning (DL) in computational finance. Despite abundant prior research on the vulnerability of DL to adversarial perturbations, such work has hitherto hardly addressed practical adversarial threat models in the context of DL-powered algorithmic trading systems (ATS). Specifically, we inve...
Critical infrastructures like the power grid are at risk from increasing cyber threats due to high penetration of interconnected distributed energy resources (DER). Compromised DER endpoints can cause events, data breaches, communication loss, intentional device failures, and even cascading outages. To address these challenges, this paper explores...
Our society increasingly benefits from Artificial Intelligence (AI). Unfortunately, more and more evidence shows that AI is also used for offensive purposes. Prior works have revealed various examples of use cases in which the deployment of AI can lead to violation of security and privacy objectives. No extant work, however, has been able to draw a...
Billions of individuals engage with Online Social Networks (OSN) daily. The owners of OSN try to meet the demands of their end-users while complying with business necessities. Such necessities may, however, lead to the adoption of restrictive data access policies that hinder research activities from "external" scientists -- who may, in turn, resort...
We investigate the potential of using Large Language Models (LLM) to support process model creation in organizational contexts. Specifically, we carry out a case study wherein we develop and test an LLM-based chatbot, PRODIGY (PROcess moDellIng Guidance for You), in a multinational company, the Hilti Group. We are particularly interested in underst...
Recent times have witnessed the rise of anti-phishing schemes powered by deep learning (DL). In particular, logo-based phishing detectors rely on DL models from Computer Vision to identify logos of well-known brands on webpages, to detect malicious webpages that imitate a given brand. For instance, Siamese networks have demonstrated notable perform...
Existing literature on adversarial Machine Learning (ML) focuses either on showing attacks that break every ML model, or defenses that withstand most attacks. Unfortunately, little consideration is given to the actual feasibility of the attack or the defense. Moreover, adversarial samples are often crafted in the “feature-space”, making the corresp...
Artificial intelligence (AI) is increasingly used in an ever larger number of industries. Alongside this development, however, abundant works argue that AI-driven systems are lacking in terms of safety, ethics and transparency. As a direct consequence, the European Commission is working on the AI Act—a regulation designed to ensure a trustworthy de...
Recent times have witnessed the rise of anti-phishing schemes powered by deep learning (DL). In particular, logo-based phishing detectors rely on DL models from Computer Vision to identify logos of well-known brands on webpages, to detect malicious webpages that imitate a given brand. For instance, Siamese networks have demonstrated notable perform...
Adversarial samples mostly aim at fooling machine learning (ML) models. They often involve minor pixel-based perturbations that are imperceptible to human observers. In this work, adversarial samples should fool both humans and ML models, which is important in two-stage decision processes. We perform changes on a higher abstraction level so that a...
Machine Learning (ML) has become a valuable asset to solve many real-world tasks. For Network Intrusion Detection (NID), however, scientific advances in ML are still seen with skepticism by practitioners. This disconnection is due to the intrinsically limited scope of research papers, many of which primarily aim to demonstrate new methods ``outperf...
Did you know that over 70 million of Dota2 players have their in-game data freely accessible? What if such data is used in malicious ways? This paper is the first to investigate such a problem. Motivated by the widespread popularity of video games, we propose the first threat model for Attribute Inference Attacks (AIA) in the Dota2 context. We expl...
Recent years have seen a proliferation of research on adversarial machine learning. Numerous papers demonstrate powerful algorithmic attacks against a wide variety of machine learning (ML) models, and numerous other papers propose defenses that can withstand most attacks. However, abundant real-world evidence suggests that actual attackers use simp...
Although machine learning based algorithms have been extensively used for detecting phishing websites, there has been relatively little work on how adversaries may attack such "phishing detectors" (PDs for short). In this paper, we propose a set of Gray-Box attacks on PDs that an adversary may use which vary depending on the knowledge that he has a...
The Smart Grid (SG) is a cornerstone of modern society, providing the energy required to sustain billions of lives and thousands of industries. Unfortunately, as one of the most critical infrastructures of our World, the SG is an attractive target for attackers. The problem is aggravated by the increasing adoption of digitalisation, which further i...
Existing literature on adversarial Machine Learning (ML) focuses either on showing attacks that break every ML model, or defenses that withstand most attacks. Unfortunately, little consideration is given to the actual \textit{cost} of the attack or the defense. Moreover, adversarial samples are often crafted in the "feature-space", making the corre...
Did you know that over 70 million of Dota2 players have their in-game data freely accessible? What if such data is used in malicious ways? This paper is the first to investigate such a problem. Motivated by the widespread popularity of video games, we propose the first threat model for Attribute Inference Attacks (AIA) in the Dota2 context. We expl...
Machine Learning (ML) represents a pivotal technology for current and future information systems, and many domains already leverage the capabilities of ML. However, deployment of ML in cybersecurity is still at an early stage, revealing a significant discrepancy between research and practice. Such discrepancy has its root cause in the current state...
Fifth Generation (5G) networks must support billions of heterogeneous devices while guaranteeing optimal Quality of Service (QoS). Such requirements are impossible to meet with human effort alone, and Machine Learning (ML) represents a core asset in 5G. ML, however, is known to be vulnerable to adversarial examples; moreover, as our paper will show...
Machine Learning (ML) represents a pivotal technology for current and future information systems, and many domains already leverage the capabilities of ML. However, deployment of ML in cybersecurity is still at an early stage, revealing a significant discrepancy between research and practice. Such discrepancy has its root cause in the current state...
Machine learning (ML) has become an important paradigm for cyberthreat detection (CTD) in the recent years. A substantial research effort has been invested in the development of specialized algorithms for CTD tasks. From the operational perspective, however, the progress of ML-based CTD is hindered by the difficulty in obtaining the large sets of l...
We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sample, yielding an adversarial sample, by using the modified activations to reconstruct the original sample. A human might (and possibly should) notice differences between th...
Enhancing Network Intrusion Detection Systems (NIDS) with supervised Machine Learning (ML) is tough. ML-NIDS must be trained and evaluated, operations requiring data where benign and malicious samples are clearly labelled. Such labels demand costly expert knowledge, resulting in a lack of real deployments, as well as on papers always relying on the...
Although machine learning based algorithms have been extensively used for detecting phishing websites, there has been relatively little work on how adversaries may attack such “phishing detectors” (PDs for short). In this paper, we propose a set of Gray-Box attacks on PDs that an adversary may use which vary depending on the knowledge that he has a...
The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to adversarial attacks that create tiny perturbations aimed at decreasing the effectiveness of detecting threats. We o...
The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to adversarial attacks that create tiny perturbations aimed at decreasing the effectiveness of detecting threats. We o...
Recent advances in deep learning renewed the research interests in machine learning for Network Intrusion Detection Systems (NIDS). Specifically, attention has been given to sequential learning models, due to their ability to extract the temporal characteristics of Network traffic Flows (NetFlows), and use them for NIDS tasks. However, the applicat...
Pivoting is a technique used by cyber attackers to exploit the privileges of compromised hosts in order to reach their final target. Existing research on countering this menace is only effective for pivoting activities spanning within the internal network perimeter. When applying existing methods to include external traffic, the detection algorithm...
We present the first dataset that aims to serve as a benchmark to validate the resilience of botnet detectors against adversarial attacks. This dataset includes realistic adversarial samples that are generated by leveraging two widely used Deep Reinforcement Learning (DRL) techniques. These adversarial samples are proved to evade state of the art d...
Adversarial attacks represent a critical issue that prevents the reliable integration of machine learning methods into cyber defense systems. Past work has shown that even proficient detectors are highly affected just by small perturbations to malicious samples, and that existing countermeasures are immature. We address this problem by presenting A...
Machine learning algorithms are effective in several applications, but they are not as much successful when applied to intrusion detection in cyber security. Due to the high sensitivity to their training data, cyber detectors based on machine learning are vulnerable to targeted adversarial attacks that involve the perturbation of initial samples. E...
Classifiers based on Machine Learning are vulnerable to adversarial attacks, which involve the creation of malicious samples that are not classified correctly. While this phenomenon has been extensively studied within the image processing domain, comprehensive analyses are scarce in the cybersecurity field. This is a critical problem because cyber-...