Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
About me
About me
Page not in menu
This is a page not in th emain menu
Posts
Blog Post 1
Published:
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
PriRoster: Privacy-preserving Radio Context Attestation in Cognitive Radio Networks
Published in IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN), 2019
This paper proposes a privacy preserving remote attestation mechanism, to protect spectrum users’ sensitive radio configuration information from untrusted intermediate verifiers in a public network via trusted execution environment.
Recommended citation: R. Zhang, N. Zhang, N. zhang, Z. Yan, W. Lou and Y.T. Hou, “PriRoster: Privacy-preserving Radio Context Attestation in Cognitive Radio Networks,” DySPAN, Nov 11-14, 2019, Newark, USA. http://ning-wang1.github.io/files/priroster.pdf
MANDA: On Adversarial Example Detection for Network Intrusion Detection System
Published in IEEE International Conference on Computer Communications, 2021
This paper examines three recent AE attacks against ML-based IDSs. It demonstrate that the problem-space AE attacks are an effective disruption to the IDSs as it allows malicious events to escape with high probability. In this paper, we design an effective and accurate AE detector, MANDA, which exploits inconsistency between manifold evaluation and IDS model inference and evaluates model uncertainty on small perturbations to differentiate AEs from clean network traffic.
Recommended citation: N. Wang, Y. Chen, Y. Hu, W. Lou and Y.T. Hou, “MANDA: On Adversarial Example Detection for Network Intrusion Detection System,” IEEE INFOCOM 2021, May 10-13, 2021, online conference. http://ning-wang1.github.io/files/manda.pdf
MANDA: On Adversarial Example Detection for Network Intrusion Detection System
Published in IEEE Transactions on Dependable and Secure Computing, 2022
This paper is an extension of our INFOCOM 2021 paper, In this paper, we propose general guidelines of generating AEs in different problem spaces. we extend the evaluation to a multi-class IDS on a new dataset (i.e., CICIDS 2017). We demonstrate that MANDA generalizes well to a multi-class IDS.
Recommended citation: N. Wang, Y. Chen, Y. Xiao, Y. Hu, W. Lou and Y.T. Hou, “MANDA: On Adversarial Example Detection for Network Intrusion Detection System,” in IEEE Transactions on Dependable and Secure Computing, doi: 10.1109/TDSC.2022.3148990. http://ning-wang1.github.io/files/manda_journal.pdf
FeCo: Boosting Intrusion Detection Capability in IoT Networks via Contrastive Learning
Published in IEEE International Conference on Computer Communications, 2022
This paper presents a machine-learning-based IDS for IoT networks, namely FeCo. FeCo incorporates contrastive learning into FL framework to support distributed intrusion detection. FeCo obtains more representative feature vectors by contrastive learning. These feature vectors have higher discriminative power between normal and malicious traffic. This effectively enables FeCo to achieve better detection accuracy than other baselines.
Recommended citation: N. Wang, Y. Chen, Y. Hu, W. Lou and Y.T. Hou, “FeCo: Boosting Intrusion Detection Capability in IoT Networks via Contrastive Learning,” IEEE INFOCOM 2022, May 2-5, 2022, virtual conference. http://ning-wang1.github.io/files/feco.pdf
FLARE: Defending Federated Learning against Model Poisoning Attacks via Latent Space Representations
Published in 17th ACM ASIA Conference on Computer and Communications Security (ACM ASIACCS), 2022
This paper proposes a robust aggregation algorithm FLARE to protect FL against MPAs. Through analysis and experimental visualization, we demonstrate that PLR vector has high potentials in differentiating malicious/poisonous models from the benign ones. FLARE effectively minimizes the impact of malicious/poisonous models on the final aggregation by assigning low trust scores to those with diverging PLRs.
Recommended citation: N. Wang, Y. Xiao, Y. Chen, Y. Hu, W. Lou and Y.T. Hou, “FLARE: Defending Federated Learning against Model Poisoning Attacks via Latent Space Representations,” Proceedings of the 2022 ACM on Asia Conference on Computer and Communications Security, May 30–June 3, 2022, Nagasaki, Japan. ACM, 13 pages. https://doi.org/10.1145/3488932.3517395. http://ning-wang1.github.io/files/flare.pdf
Transferability of Adversarial Examples in Machine Learning-based Malware Detection
Published in IEEE Conference on Communications and Network Security (CNS), 2022
This paper improves the transferability of adversarial examples (AEs) so that the generated AEs can evade multiple types of ML-based malware detector. We study AE transferability enhancement techniques (i.e., ensemble sample (ES) and ensemble model (EM)) and how they impact AE generation and Android malware detection. Further, we develop a new transfer-based AE generation method, BATE, using a novel feature evenness metric. The idea is to spread perturbations more evenly among perturbed features by incorporating an evenness score in the objective function.
Recommended citation: Y. Hu, N. Wang, Y. Chen, W. Lou and Y.T. Hou, “Transferability of Adversarial Examples in Machine Learning-based Malware Detection,” CNS, Oct 3-5, 2022, Austin, USA. http://ning-wang1.github.io/files/CNS.pdf
Squeezing More Utility via Adaptive Clipping on Deferentially Private Gradients in Federated Meta-Learning
Published in Annual Computer Security Applications Conference (ACSAC), 2022
This paper proposes a new differentially private federated meta-learning architecture to addresses data privacy challenges in federated learning. Our proposal features an adaptive gradient clipping method and a one-pass meta-training process to improve model utility-privacy trade-off. It provides two notions of privacy protection for the trusted server and honest-but-curious central server.
Recommended citation: N. Wang, Y. Xiao, Y. Chen, N. Zhang, W. Lou and Y.T. Hou, “Squeezing More Utility via Adaptive Clipping on Deferentially Private Gradients in Federated Meta-Learning,” ACSAC, Dec 5-9, 2022, Austin, USA. http://ning-wang1.github.io/files/dp.pdf
talks
FeCo: Boosting Intrusion Detection Capability in IoT Networks via Contrastive Learning
Published:
This talk presents FeCo, a machine-learning-based IDS for IoT networks. FeCo incorporates contrastive learning into FL framework to support distributed intrusion detection. FeCo obtains more representative feature vectors by contrastive learning. These feature vectors have higher discriminative power between normal and malicious traffic. This effectively enables FeCo to achieve better detection accuracy than other baselines. Through extensive evaluations on the NSL-KDD dataset, we demonstrate the high effectiveness of FeCo in both centralized and federated learning setting.
Flare: Defensing Federated Learning against Model Poisoning Attacks via Latent Space Representations
Published:
This talk presents a robust aggregation algorithm FLARE to protect FL against MPAs. It demonstrates that PLR vector has high potentials in differentiating malicious/poisonous models from the benign ones. FLARE effectively minimizes the impact of malicious/poisonous models on the final aggregation by assigning low trust scores to those with diverging PLRs.