HOTD: A holistic cross-layer time-delay attack detection framework for unmanned aerial vehicle networks

Zhai, Wenbin; Sun, Songlin; Liu, Liang; Ding, Yao; Lu, Wanying

doi:10.1016/j.jpdc.2023.03.001

Cited by 2 publications

(5 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, our study incorporates realistic network scenarios that account for factors such as 3D node movement, local data collection by each node, and realistic traffic patterns. To the best of our knowledge, this study represents one of the few recent studies in the field of FANET security [18] [20] where data is based on an actual FANET dataset, but with more realistic settings specifically tailored to suit the dynamics and requirements of FANETs. In previous studies [39], the application of federated learning was often demonstrated using synthetic data that mimicked IoT data federations.…”

Section: Discussionmentioning

confidence: 99%

“…Another attack dataset is introduced in [20]. This study is noteworthy as it is the first to address time delay attacks in FANETs, where delays are intentionally introduced in packet transmissions to the destination.…”

Section: Related Workmentioning

confidence: 99%

“…As shown in the table, the majority of these studies train and evaluate their models on datasets not suitable for FANETs. Even in cases where new attack dataset for FANETs are created, their parameters are not very realistic due to simulating networks with a small number of nodes [31], 2D mobility models [20][29], or nodes with low speeds suitable for MANETs and VANETs but not FANETs [18] [20]. Hence, such parameters may not accurately reflect the reality of FANETs.…”

Section: Related Workmentioning

confidence: 99%

“…-it is evaluated on a small area with nodes having low speeds (10-20 m/s) -high false positive rate [20] 2023 FANETs a FANET dataset Time Delay ML + a new dataset is created by using 4 different routing protocols (13, 24 nodes and 2D MapRouteMovement) -2D mobility is considered -use of pre-planned route for ... applications [24] 2021 FANETs KDDCup'99 [25] DoS, DDoS, Probe, R2L, U2R DL + both local and central IDSs participate in detection NSL-KDD [26] Fuzzer, Analysis, Backdoors, Exploits -the datasets are not suitable for FANETs UNSW-NB15 [42] Worms, Shell Code, Reconnaissance WSN-DS [43] Password, XSS, Injection, Scanning CICIDS2017 [28] TON IoT [44] [29] 2019 FANETs a FANET dataset collected from nodes Spoofing, Jamming DL + it is claimed to be lightweight (20 nodes, Random Way Point Mobility Model )…”

Section: A Federated Learningmentioning

confidence: 99%

See 3 more Smart Citations

Analysis of Routing Attacks in FANETs

Ozlem

Pinar

Şen

2022

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Unmanned aerial vehicles (UAVs) in flying ad-hoc networks (FANETs) face security challenges due to the dynamic and distributed nature of these networks. This paper presents the Federated Learning-based Intrusion Detection System (FL-IDS), an innovative approach designed to improve FANET security. FL-IDS leverages federated learning to address privacy concerns of centralized intrusion detection systems. FL-IDS operates in a decentralized manner, enabling UAVs to collaboratively train a global intrusion detection model without sharing raw data. Local models are assigned to each UAV, using client-specific data, and only updated model weights are shared with a central server. This preserves privacy while utilizing collective intelligence for effective intrusion detection. Experimental results show FL-IDS's competitive performance with Central IDS (C-IDS) while mitigating privacy concerns. The Bias Towards Specific Clients (BTSC) method further enhances FL-IDS performance, surpassing C-IDS even at lower attacker ratios. A comparative analysis with traditional intrusion detection methods, including Local IDS (L-IDS), provides insights into FL-IDS's strengths. This study significantly contributes to FANET security by introducing a privacy-aware, decentralized intrusion detection approach tailored to the unique challenges of UAV networks.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: A Federated Learningmentioning

confidence: 99%

See 2 more Smart Citations

Analysis of Routing Attacks in FANETs

Ozlem

Pinar

Şen

2022

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

show abstract

“…The second, by Tax and Duin, restricts training data to a hypersphere [28]. One-class classification problems commonly exist in novelty and outlier detection [29][30][31][32]. Successful application of one-class classifiers depends on whether the feature space is well constructed.…”

Section: One-class Classification Problemsmentioning

confidence: 99%

Detecting Generated Images by Real Images

Liu¹,

Yang²,

Bi³

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

As deep learning technology continues to evolve, the images yielded by generative models are becoming more and more realistic, triggering people to question the authenticity of images. Existing generated image detection methods detect visual artifacts in generated images or learn discriminative features from both real and generated images by massive training. This learning paradigm will result in efficiency and generalization issues, making detection methods always lag behind generation methods. This paper approaches the generated image detection problem from a new perspective: Start from real images. By finding the commonality of real images and mapping them to a dense subspace in feature space, the goal is that generated images, regardless of their generative model, are then projected outside the subspace. As a result, images from different generative models can be detected, solving some long-existing problems in the field. Experimental results show that although our method was trained only by real images and uses 99.9% less training data than other deep learning-based methods, it can compete with state-of-the-art methods and shows excellent performance in detecting emerging generative models with high inference efficiency. Moreover, the proposed method shows robustness against various post-processing. These advantages allow the method to be used in real-world scenarios.

show abstract

HOTD: A holistic cross-layer time-delay attack detection framework for unmanned aerial vehicle networks

Cited by 2 publications

References 58 publications

Analysis of Routing Attacks in FANETs

Analysis of Routing Attacks in FANETs

Detecting Generated Images by Real Images

Contact Info

Product

Resources

About