Jamming signals classification using convolutional neural network

Wu, Zhilu; Zhao, Yanlong; Yin, Zhendong; Luo, Haochen

doi:10.1109/isspit.2017.8388320

Cited by 41 publications

(21 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wireless security finds rich applications of deep learning. Deep learning was applied to authenticate signals [37], detect and classify jammers of different types [38], [39], [40], and control communications to mitigate jamming effects [41], [42], [47]. Using wireless sensors, deep learning was also used to infer private information in analogy to exploratory attacks [43].…”

Section: Related Workmentioning

confidence: 99%

Adversarial Deep Learning for Over-the-Air Spectrum Poisoning Attacks

Sagduyu

Shi

Erpek

2021

IEEE Trans. on Mobile Comput.

100

View full text Add to dashboard Cite

An adversarial deep learning approach is presented to launch over-the-air spectrum poisoning attacks. A transmitter applies deep learning on its spectrum sensing results to predict idle time slots for data transmission. In the meantime, an adversary learns the transmitter's behavior (exploratory attack) by building another deep neural network to predict when transmissions will succeed. The adversary falsifies (poisons) the transmitter's spectrum sensing data over the air by transmitting during the short spectrum sensing period of the transmitter. Depending on whether the transmitter uses the sensing results as test data to make transmit decisions or as training data to retrain its deep neural network, either it is fooled into making incorrect decisions (evasion attack), or the transmitter's algorithm is retrained incorrectly for future decisions (causative attack). Both attacks are energy efficient and hard to detect (stealth) compared to jamming the long data transmission period, and substantially reduce the throughput. A dynamic defense is designed for the transmitter that deliberately makes a small number of incorrect transmissions (selected by the confidence score on channel classification) to manipulate the adversary's training data. This defense effectively fools the adversary (if any) and helps the transmitter sustain its throughput with or without an adversary present.

show abstract

Section: Related Workmentioning

confidence: 99%

Adversarial Deep Learning for Over-the-Air Spectrum Poisoning Attacks

Sagduyu

Shi

Erpek

2021

IEEE Trans. on Mobile Comput.

100

View full text Add to dashboard Cite

show abstract

“…Over the last years, Deep learning techniques have shown remarkable performance in various fields such as computer vision, natural language processing, speech recognition and localization [25]. In localization field, Deep Convolution Neural Network is one of the most employed models for environment classification [26], GNSS jamming detection [27], traffic prediction [28], etc. What makes this network more attractive than other types of networks such as DNNs, is its potential to exploit spatial or temporal correlation by extracting useful information from input data (2D images, voice signal, sensors measurements...) and learn distinctive features in order to match as precisely as possible the inputs with the outputs.…”

Section: Adaptive Decision and Fault Management Based On Dcnnmentioning

confidence: 99%

Navigation Context Adaptive Fault Detection and Exclusion Strategy based On Deep Learning & Information Theory: Application to a GNSS/IMU Integration

Harbaoui¹,

Tmazirte²,

Makkawi³

et al. 2021

Proceedings of the 34th International Technical Meeting of the Satellite Division of the Institute of Navigation (ION GNSS+ 202

View full text Add to dashboard Cite

His research interests include multi-sensor fault tolerant fusion for localization and integrity assessment. Khoder Makkawi Lecturer at Polytech Lille and Researcher at CRIStAL laboratory. Received the Ph.D. degree in 2020, in collaboration between Lille University and Lebanese University. He is a member of the TOSyMA (Tolérance aux fautes des Systèmes Mobiles Autonomes) team of the CRIStAL laboratory UMR CNRS 9189.

show abstract

“…The waveforms designed by the proposed technique can clearly be employed within periods the TV-STJ. When the variation of the TV-STJ is very fast, the problem could possibly be modeled and solved with the methods of signal detection and classification, widely developed by utilizing energy detectors, higher-order statistical features, and statistical tests [27]: They can also be achieved by using learning methods based on techniques of neural networks as shown in [28], [29].…”

Section: Challenges and Possible Solutions In Other Jamming Scenariosmentioning

confidence: 99%

Design of Anti-Jamming Waveforms for Time-Hopping Spread Spectrum Systems in Tone Jamming Environments

Jung

Nguyen

Song

et al. 2020

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

We consider the problem of designing waveforms for mitigating single tone jamming (STJ) signals with an estimated jamming frequency in time-hopping spread spectrum (TH SS) systems. The proposed design of waveforms optimizes the antijamming (AJ) performance of TH SS systems by minimizing the correlation between the template and STJ signals, in which the problem of waveform optimization is simplified by employing a finite number of rectangular pulses. The simplification eventually makes the design of waveforms be converted into a problem of finding eigenvalues and eigenvectors of a matrix. Simulation results show that the waveforms designed by the proposed scheme provide us with performance superior not only to the conventional waveforms but also to the clipper receiver in the mitigation of STJ. The waveforms from the proposed design also exhibit a desirable AJ capability even when the estimated frequency of the STJ is not perfect.

show abstract

Jamming signals classification using convolutional neural network

Cited by 41 publications

References 11 publications

Adversarial Deep Learning for Over-the-Air Spectrum Poisoning Attacks

Adversarial Deep Learning for Over-the-Air Spectrum Poisoning Attacks

Navigation Context Adaptive Fault Detection and Exclusion Strategy based On Deep Learning & Information Theory: Application to a GNSS/IMU Integration

Design of Anti-Jamming Waveforms for Time-Hopping Spread Spectrum Systems in Tone Jamming Environments

Contact Info

Product

Resources

About