Detection of Malicious Intent in Non-cooperative Drone Surveillance

Liang, Jiaming; Ahmad, Bashar I.; Jahangir, Mohammed; Godsill, Simon

doi:10.1109/sspd51364.2021.9541485

Cited by 19 publications

(14 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The three recurring keywords in studies related to intention estimation (that is, Task-3 in Figure 1a) are anomaly detection [5][6][7], threat assessment [8], and intent inference [9][10][11][12][13]. Among references dealing with intent inference, we review [9][10][11] first in which the targets considered are drones.…”

Section: Related Workmentioning

confidence: 99%

Estimation of drone intention using trajectory frequency defined in radar's measurement phase planes

Yun

Anderson

Fioranelli

2023

IET Radar Sonar & Navi

View full text Add to dashboard Cite

This paper presents a radar‐based algorithm for autonomous estimation of drone intention. The algorithm is based on radar's kinematic measurements, providing fast and robust intention estimation for multiple targets. The core idea of the proposed algorithm is to build intention‐specific features for each intention in advance and use them in actual drone surveillance situations. To effectively depict the trajectory characteristics of various intentions, the trajectory frequency is computed on multiple phase planes through Monte Carlo Simulations. Finally, a naive Bayes classifier is applied to integrate the trajectory likelihood in different phases and ultimately compute the intention likelihood of all intentions concerned. Numerical simulations for the three candidate intentions of image acquisition, smuggling, and kamikaze attack demonstrated the performance of the presented method. The simulation results show that one can estimate the true intention of a specific drone by comparing the value of each intention likelihood.

show abstract

Section: Related Workmentioning

confidence: 99%

Estimation of drone intention using trajectory frequency defined in radar's measurement phase planes

Yun

Anderson

Fioranelli

2023

IET Radar Sonar & Navi

View full text Add to dashboard Cite

show abstract

“…Another example for miscellaneous radars is Aveillant's Gamekeeper radar used in [218]. The Bayesian approach is used to determine the intent of a UAV around a given geographical location using the radar data in [218]. In [219], a performance analysis of twin radars is provided for civilian air traffic control.…”

Section: B Miscellaneous Types Of Radar Systemsmentioning

confidence: 99%

“…The Bayesian approach is used to determine the intent of a UAV around a given geographical location using the radar data [218] Twin radars A higher detection probability of small UAVs is possible using twin radars. Moreover, better angular resolution and increased update plot frequency can be achieved [219] Omega360 A 2D omnidirectional radar that generates multiple staring beams simultaneously to cover the 360 • azimuth plane.…”

Section: Hybrid Radarmentioning

confidence: 99%

A Survey on Radar Techniques for Detection,Tracking, and Classification of Aerial Threats

Khawaja¹

2022

Preprint

View full text Add to dashboard Cite

<p> The use of unmanned aerial vehicles (UAVs) for different applications has increased many folds in recent years. The UAVs are expected to change the future air operations. However, there are instances where the UAVs can be used for malicious purposes. The detection, tracking, and classification of UAVs is challenging compared to manned aerial vehicles (MAVs) mainly due to small size, complex shapes, and ability to fly close to the terrain and in autonomous flight patterns in swarms. In this survey, we will discuss current and future aerial threats, and provide an overview of radar systems to counter such threats. We also study the performance parameters of radar systems for the detection, tracking, and classification of UAVs compared to MAVs. Finally, limitations of radar systems and comparison with other techniques that do not rely on radars for detection, tracking, and classification of aerial threats are also provided. </p>

show abstract

“…This creates either too many false positives (e.g., constantly suspecting anomalies) or over trusting autonomous systems.Many efforts have been made to classify intention from observational data using expertsknowledge methods [4]. These methods define low-dimensional behavioural features [5,6,7,8] for relatively simple motion dynamics. However, the challenge of predicting intention is exasperated by an inherent cognitive bias problem caused by the low scalability of these simplistic features to complex and diverse classification of drone intention.…”

mentioning

confidence: 99%

“…learning models that use snap-shot data to cluster together drone attributes [6] to predict the trajectory in several time steps in the future [13]. However, the continuous flight physics has been left aside despite providing crucial information about the mission profile and intention.…”

mentioning

confidence: 99%

Uncovering Drone Intentions using Control Physics Informed Machine Learning

Perrusquía

Guo

Fraser

et al. 2023

Preprint

View full text Add to dashboard Cite

Fully autonomous aerial platforms or drones are increasingly used across diverse application areas. Uncooperative drones do not announce their identity nor file flight plans and can pose a potential risk to a variety of critical infrastructures. Understanding an uncooperative drone's intention is important to assigning risk and executing countermeasures. Drones have rapidly changing design, flexible capabilities, and diverse underpinning algorithms. This makes distinguishing malicious from naive intentions across platforms difficult. Intentions are often intangible and unobservable, and a variety of tangible intention classes are often inferred as a proxy. However, inference of drone intention classes (e.g., via inverse learning) using observational data alone is inherently unreliable due to observational and learning bias. Here we develop a novel control-physics informed machine learning (CPhy-ML) that can robustly infer across intention classes, out performing over expert-defined anomaly detection and inverse learning approaches. Our CPhy-ML complementary learning couples the representation power of deep learning with the conservation laws of aerospace control models, reducing bias and instability. The results in simulation and experimentation demonstrate that we can find common intention patterns across the inferred intention classes, ranging from trajectory to reward goals. We believe that this framework can provide deeper insight into the complex nature of intention and a firm step towards to its smooth integration in current counter drone technologies. The techniques developed here can aid the enforcement of drone incursions in a time where geo-fencing is no-longer efficiently enforceable. As transport and operational autonomy is increasingly used, enforcement algorithms can also inform the design of better criminal justice system and safer autonomous systems themselves.

show abstract

Detection of Malicious Intent in Non-cooperative Drone Surveillance

Cited by 19 publications

References 22 publications

Estimation of drone intention using trajectory frequency defined in radar's measurement phase planes

Estimation of drone intention using trajectory frequency defined in radar's measurement phase planes

A Survey on Radar Techniques for Detection,Tracking, and Classification of Aerial Threats

Uncovering Drone Intentions using Control Physics Informed Machine Learning

Contact Info

Product

Resources

About