Opin vísindi

 

Nýlega bætt við

Verk
Evaluating the effectiveness of Adversarial Attacks against Botnet Detectors
(Institute of Electrical and Electronics Engineers Inc., 2019-09) Apruzzese, Giovanni; Colajanni, Michele; Marchetti, Mirco; Gkoulalas-Divanis, Aris; Marchetti, Mirco; Avresky, Dimiter R.; Department of Computer Science
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-detectors are being increasingly integrated with machine learning methods, making them suitable targets for skilled attackers leveraging adversarial samples to evade detection. In this paper, we propose a thorough analysis of realistic adversarial attacks performed against network intrusion detection systems that focus on identifying botnet traffic through machine learning classifiers. Our large campaign of experiments involves the most recent public datasets, representing multiple realistic network scenarios. Moreover, we evaluate the impact of these attacks against state-of-the-art detectors relying on different machine learning algorithms, providing a clear overview of this problem. The results outline the fragility of these methods. Our study represent a stepping stone for devising suitable countermeasures to the menace of adversarial attacks against cyber-detectors.
Verk
Evading botnet detectors based on flows and random forest with adversarial samples
(Institute of Electrical and Electronics Engineers Inc., 2018-11-26) Apruzzese, Giovanni; Colajanni, Michele; Department of Computer Science
Machine learning is increasingly adopted for a wide array of applications, due to its promising results and autonomous capabilities. However, recent research efforts have shown that, especially within the image processing field, these novel techniques are susceptible to adversarial perturbations. In this paper, we present an analysis that highlights and evaluates experimentally the fragility of network intrusion detection systems based on machine learning algorithms against adversarial attacks. In particular, our study involves a random forest classifier that utilizes network flows to distinguish between botnet and benign samples. Our results, derived from experiments performed on a public real dataset of labelled network flows, show that attackers can easily evade such defensive mechanisms by applying slight and targeted modifications to the network activity generated by their controlled bots. These findings pave the way for future techniques that aim to strengthen the performance of machine learning-based network intrusion detection systems.
Verk
E-PhishGEN : Unlocking Novel Research in Phishing Email Detection
(Association for Computing Machinery, Inc, 2025-12-30) Pajola, Luca; Caripoti, Eugenio; Banzer, Stefan; Pizzi, Simeone; Conti, Mauro; Apruzzese, Giovanni; Department of Computer Science
Every day, our inboxes are flooded with unsolicited emails, ranging between annoying spam to more subtle phishing scams. Unfortunately, despite abundant prior efforts proposing solutions achieving near-perfect accuracy, the reality is that countering malicious emails still remains an unsolved dilemma. This "open problem"paper carries out a critical assessment of scientific works in the context of phishing email detection. First, we focus on the benchmark datasets that have been used to assess the methods proposed in research. We find that most prior work relied on datasets containing emails that - we argue - are not representative of current trends, and mostly encompass the English language. Based on this finding, we then re-implement and re-assess a variety of detection methods reliant on machine learning (ML), including large-language models (LLM), and release all of our codebase - an (unfortunately) uncommon practice in related research. We show that most such methods achieve near-perfect performance when trained and tested on the same dataset - a result which intrinsically hinders development (how can future research outperform methods that are already near perfect?). To foster the creation of "more challenging benchmarks"that reflect current phishing trends, we propose E-PhishGEN, an LLM-based (and privacy-savvy) framework to generate novel phishing-email datasets. We use our E-PhishGEN to create E-PhishLLM, a novel phishing-email detection dataset containing 16616 emails in three languages. We use E-PhishLLM to test the detectors we considered, showing a much lower performance than that achieved on existing benchmarks - indicating a larger room for improvement. We also validate the quality of E-PhishLLM with a user study (n=30). To sum up, we show that phishing email detection is still an open problem - and provide the means to tackle such a problem by future research.
Verk
Dynamic Current Distribution in the Electrodes of Submerged Arc Furnace Using Scalar and Vector Potentials
(Springer Verlag, 2018) Tesfahunegn, Yonatan Afework; Magnusson, Thordur; Tangstad, Merete; Saevarsdottir, Gudrun; Krzhizhanovskaya, Valeria V.; Lees, Michael Harold; Sloot, Peter M.; Dongarra, Jack; Shi, Yong; Tian, Yingjie; Fu, Haohuan; Department of Engineering
This work presents computations of electric current distributions inside an industrial submerged arc furnace. A 3D model has been developed in ANSYS Fluent that solves Maxwell’s equations based on scalar and vector potentials approach that are treated as transport equations. In this paper, the approach is described in detail and numerical simulations are performed on an industrial three-phase submerged arc furnace. The current distributions within electrodes due to skin and proximity effects are presented. The results show that the proposed method adequately models these phenomena.
Verk
Distributed large independent sets in one round on bounded-independence graphs
(Springer Verlag, 2015) Halldórsson, Magnús M.; Konrad, Christian; Moses, Yoram; Department of Computer Science
We present a randomized one-round, single-bit messages, distributed algorithm for the maximum independent set problem in polynomially bounded-independence graphs with poly-logarithmic approximation factor. Bounded-independence graphs capture various models of wireless networks such as the unit disc graphs model and the quasi unit disc graphs model. For instance, on unit disc graphs, our achieved approximation ratio is (Formula presented.). A starting point of our work is an extension of Turán’s bound for independent sets by Caro and Wei which states that every graph G = (V,E) contains an independent set of size at least (Formula presented.), where degG(v) denotes the degree of v in G. Alon and Spencer’s proof of the Caro-Wei bound in [1] suggests a randomized distributed oneround algorithm that outputs an independent set of expected size equal to β(G), using messages of sizes O(log n), where n is the number of vertices of the input graph. To achieve our main result, we show that β(G) gives poly-logarithmic approximation ratios for polynomially boundedindependence graphs. Then, for O(1)-claw free graphs (which include graphs of bounded-independence), we show that using a different algorithm, an independent set of expected size Θ(β(G)) can be computed in one round using single bit messages, thus reducing the communication cost to an absolute minimum. Last, in general graphs, β(G) may only give an Ω(n)-approximation. We show, however, that this is best possible for one-round algorithms: We show that each such distributed algorithm (possibly randomized) has an approximation ratio of Ω(n) on general graphs.

Flokkar í Opnum vísindum

Veldu flokk til að skoða.

Niðurstöður 1 - 9 af 9

Öll gögn í Opnum vísindum eru vernduð af ákvæðum höfundalaga og með öllum réttindum áskildum, nema annað sé tekið fram.