SpecGuard: Spectrum Misuse Detection in Dynamic Spectrum Access Systems

Mobile Information Systems

Xia

Shao

et al. 2020

Self Cite

Smart Home brings a new people-oriented home life experience. However, the edge devices in this system are facing severe threats such as data security and equipment safety. To solve the above problems, this paper proposes an intrusion detection scheme based on repeated game. We first use the K-Nearest Neighbors (KNN) algorithm to classify edge devices and equip the intrusion detection system to cluster heads. Secondly, we use the regret minimization algorithm to determine the mixed strategy Nash equilibrium of the one-order game and then take a severe punishment strategy to domesticate malicious attackers. Thirdly, the intrusion detection system can detect malicious attackers by reduction of payoff. Finally, the detailed experimental results show that the proposed scheme can reduce the loss of attacked intrusion detection system and then achieve the purpose of defending against the attacker.

Section: Related Workmentioning

confidence: 99%

An Intrusion Detection Scheme Based on Repeated Game in Smart Home

Mobile Information Systems

Xia

Shao

et al. 2020

Self Cite

Proceedings of the Twenty-First International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Netw

“…Learning-based radios are envisioned to be able to automatically infer the current spectrum status in terms of occupancy [27], interference [28] and malicious activities [29]. Most of the existing work is based on low-dimensional machine learning [18][19][20]30], which requires the cumbersome manual extraction of very complex, ad hoc features from the waveforms.…”

Section: Related Workmentioning

confidence: 99%

PolymoRF

Restuccia

Melodia

2020

Today's wireless technologies are largely based on inflexible designs, which makes them inefficient and prone to a variety of wireless attacks. To address this key issue, wireless receivers will need to (i) infer on-the-fly the physical-layer parameters currently used by transmitters; and if needed, (ii) change their hardware and software structures to demodulate the incoming waveform. In this paper, we introduce PolymoRF, a deep learning-based polymorphic receiver able to reconfigure itself in real time based on the inferred waveform parameters. Our key technical innovations are (i) a novel embedded deep learning architecture, called RFNet, which enables the solution of key waveform inference problems; (ii) a generalized hardware/software architecture that integrates RFNet with radio components and signal processing. We prototype PolymoRF on a custom software-defined radio platform, and show through extensive over-the-air experiments that PolymoRF achieves throughput within 87% of a perfect-knowledge Oracle system, thus demonstrating for the first time that polymorphic receivers are feasible. CCS CONCEPTS • Hardware → Wireless devices.

“…For CRN security, [35] propose authentication of CR device with signal at the physical layer and [36] propose detecting and preventing malicious CR at device level. Although authentication can verify the identity of a CR device and device level security protects a CR device from being compromised, they cannot ensure authority that every connected CR device is benign and complies to transmission permissions at runtime in our case.…”

Section: Related Workmentioning

confidence: 99%

PriRoster: Privacy-preserving Radio Context Attestation in Cognitive Radio Networks

Wang

2019 IEEE International Symposium on Dynamic Spectrum Access Networks (DySPAN)

et al. 2019

Spectrum shortage is becoming a global concern and cognitive radio network (CRN) is envisioned to be one of the key technologies for overcoming this challenge. However, proper operation of CRN heavily depends on compliance of cognitive radios (CRs). Although Remote attestation of CRs' radio context is a promising solution, delegating appraisal tasks to local base stations has serious privacy concerns. Conducting appraisal tasks only on global appraiser brings an easy solution, nevertheless, scalability remains an unsolved issue. In this paper, we propose PriRoster, a privacy-preserving radio context attestation framework for cognitive radio network. The proposed framework takes advantage of recent advancement in trusted hardware, Intel SGX, and incorporate it in a secure and scalable way. First, we propose a privacy-preserving design for single device remote attestation. Second, we design a secure trust transfer scheme to delegate power consuming process of trust establishment between local appraiser (LA) enclave and CR nodes to global appraiser (GA). Through this design, we construct a scalable framework with low computation burden for resource constraint low-end CR devices. Furthermore, special considerations are given in adopting Intel SGX. We consider known memory access side channel of Intel SGX and propose oblivious appraisal functions to prevent this kind of information exposure. At last, we build a prototype of the proposed system using Raspberry Pi, USRP, Intel NUC and AWS cloud. The feasibility of our proposed framework is measured by system benchmark and the effectiveness of proposed oblivious appraisal functions are verified by dynamic code instrumentation.