Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Giovanni Apruzzese"'
Publikováno v:
Data in Brief, Vol 34, Iss , Pp 106631- (2021)
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 Reinf
Externí odkaz:
https://doaj.org/article/3c4d66ff7b094394a7e8aea6f6cbc2df
Autor:
Giovanni Apruzzese, Mauro Andreolini, Mirco Marchetti, Vincenzo Giuseppe Colacino, Giacomo Russo
Publikováno v:
Symmetry, Vol 12, Iss 4, p 653 (2020)
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 malici
Externí odkaz:
https://doaj.org/article/5ac914a6c0844dd29d2087386e3dd4f7
Autor:
Giovanni Apruzzese, V. S. Subrahmanian
Publikováno v:
IEEE Transactions on Dependable and Secure Computing. :1-19
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 G
Autor:
Johannes Schneider, Giovanni Apruzzese
Publikováno v:
Journal of Information Security and Applications. 75:103502
Autor:
Johannes Schneider, Giovanni Apruzzese
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 t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95cd72288a96603819e33c30cae496ce
http://arxiv.org/abs/2203.10166
http://arxiv.org/abs/2203.10166
Publikováno v:
Apruzzese, G, Pierazzi, F, Colajanni, M & Marchetti, M 2017, ' Detection and Threat Prioritization of Pivoting Attacks in Large Networks ', IEEE Transactions on Emerging Topics in Computing . https://doi.org/10.1109/TETC.2017.2764885
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 toug
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,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::77f87d3cb29f30655ad2fe77fe7aa97b
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 labeled. Such labels demand costly ex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::37479bec65bc7ce1264b4b0e33e8f75b
https://hdl.handle.net/11577/3462401
https://hdl.handle.net/11577/3462401
Publikováno v:
Proceedings-38th Annual Computer Security Applications Conference, ACSAC 2022
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 t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5c631ac8686819cbe10579a33447a8f2
https://doi.org/10.1145/3564625.3567980
https://doi.org/10.1145/3564625.3567980
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
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15b0b5316150311bab6632c331b09f26