Published in IEEE European Symposium on Security and Privacy (Euro S&P 25), 2025
This paper presents OMINE, a system that leverges lightweight in-network ML models that collaboratively contribute on a per-packet decision for DDoS attack detection. We tackle mainly two challenges: (a) lowering the FPR for DDoS detection and (b) feature collection feasibility for in-network solutions.
Published in 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24), 2024
This paper presents CARAVAN, a practical online learning system for in-network ML models. We tackle two primary challenges in facilitating online learning for networking: (a) the automatic labeling of evolving traffic and (b) the efficient monitoring and detection of model performance degradation to trigger retraining.
Recommended citation: Qizheng Zhang, Ali Imran, Enkeleda Bardhi, Tushar Swamy, Nathan Zhang, Muhammad Shahbaz, Kunle Olukotun (2024). "Caravan: Practical Online Learning of {In-Network}{ML} Models with Labeling Agents." 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 2024.
Download Paper
Published in 2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P), 2023
In the context of Information-Centric Networking, Interest Flooding Attacks (IFAs) represent a new and dangerous sort of distributed denial of service. Since existing proposals targeting IFAs mainly focus on local information, in this paper we propose GNN4IFA as the first mechanism exploiting complex non-local knowledge for IFA detection by leveraging Graph Neural Networks (GNNs) handling the overall network topology.
Recommended citation: Andrea Agiollo, Enkeleda Bardhi, Mauro Conti, Riccardo Lazzeretti, Eleonora Losiouk, Andrea Omicini (2023) "GNN4IFA: Interest flooding attack detection with graph neural networks." 2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P). IEEE, 2023.
Download Paper
Published in Proceedings of the 17th International Conference on Availability, Reliability and Security, 2022
The paper proposes a setup of an NDN testbed composed of Raspberry Pi devices. After that, we conduct performance analysis for crucial NDN features such as name-based forwarding, in-network caching, and data packet signing.
Recommended citation: Enkeleda Bardhi, Mauro Conti, Riccardo Lazzeretti, Eleonora Losiouk, Ahmed Taffal (2022). "Sim2Testbed Transfer: NDN Performance Evaluation." Proceedings of the 17th International Conference on Availability, Reliability and Security. 2022.
Download Paper
Published in 2021 IEEE 46th Conference on Local Computer Networks (LCN), 2021
PATTA is the first privacy attack based on network traffic analysis in Information-Centric Networking. PATTA aims to automatically identify the category of requested content by sniffing the communication towards the first hop router. PATTA applies text processing and machine learning techniques to content names in content-oriented architectures.
Recommended citation: Enkeleda Bardhi, Mauro Conti, Riccardo Lazzeretti, Eleonora Losiouk (2021). "ICN PATTA: ICN privacy attack through traffic analysis." 2021 IEEE 46th Conference on Local Computer Networks (LCN). IEEE, 2021.
Download Paper
Published in IEEE Network Magazine, 2024
This article discusses AI-based security solutions in programmable networks, focusing on the explored modalities of integrating AI models in programmable constrained network devices. Moreover, we elaborate on the challenges and risks of relying on AI for such mechanisms. Lastly, the article brings a visionary glimpse for future trends in this regard, raising some essential questions on the indispensability of AI for security functionalities and providing some alternative solutions.
Recommended citation: Enkeleda Bardhi, Mauro Conti, and Riccardo Lazzeretti. "Is AI a Trick or T (h) reat for Securing Programmable Data Planes?." IEEE Network (2024).
Download Paper
Published in Future Generation Computer Systems, 2024
This paper contributes with a novel anonymous-by-design FL framework with a customised communication protocol leveraging NDN. The proposed communication scheme encompasses an ad-hoc FL-oriented naming convention and anonymity-driven forwarding and enrollment procedures.
Recommended citation: Andrea Agiollo, Enkeleda Bardhi, Mauro Conti, Nicolò Dal Fabbro, Riccardo Lazzeretti (2024). "Anonymous Federated Learning via Named-Data Networking." Future Gener. Comput. Syst. 152: 288-303 (2024)
Download Paper
Published in IEEE Communications Surveys & Tutorials, 2023
This article provides the first comprehensive Security and Privacy (SP) analysis of the state-of-the-art IP-ICN coexistence architectures by horizontally comparing the SP features among three deployment approaches – i.e., overlay, underlay, and hybrid – and vertically comparing among the ten considered SP features.
Recommended citation: Enkeleda Bardhi, Mauro Conti, Riccardo Lazzeretti, Eleonora Losiouk (2023). "Security and Privacy of IP-ICN Coexistence: A Comprehensive Survey." IEEE Commun. Surv. Tutorials 25(4): 2427-2455 (2023)
Download Paper