Most research on replay detection has focused on developing a stand-alone countermeasure that runs independently of a speaker verification system by training a single spoofed model and a single genuine model for all speakers. In this paper, we explore the potential benefits of adapting the back-end of a spoofing detection system towards the claimed target speaker. Specifically, we characterize and quantify speaker variability by comparing speaker-dependent and speaker-independent (SI) models of feature distributions for both genuine and spoofed speech. Following this, we develop an approach for implementing speaker-dependent spoofing detection using a Gaussian mixture model (GMM) back-end, where both the genuine and spoofed models are adapted to the claimed speaker. Finally, we also develop and evaluate a speaker-specific neural network-based spoofing detection system in addition to the GMM based back-end. Evaluations of the proposed approaches on replay corpora BTAS2016 and ASVspoof2017 v2.0 reveal that the proposed speaker-dependent spoofing detection outperforms equivalent SI replay detection baselines on both datasets. Our experimental results show that the use of speaker-specific genuine models leads to a significant improvement (around 4% in terms of equal error rate (EER)) as previously shown and the addition of speaker-specific spoofed models adds a small improvement on top (less than 1% in terms of EER).

With electronic warfare increasingly complicated and military confrontations increasingly intense, the potential security threat to satellite navigation has become a difficult issue to deal with. Traditional satellite navigation anti-interference technology generally refers to jamming, but less consideration has been given to spoofing. It should be noted that the potential risk induced by spoofing interference is worse than that caused by jamming as the loss of positioning integrity may not be immediately obvious. This paper introduces a spoofing detection method based on a two-antenna structure using fraction parts of double-difference carrier phase observables. If all spoofing signals are transmitted by one single antenna, a spoofing detection hypothesis test can be carried out through the normalisation of double-difference carrier phase observables, without need to consider the integer ambiguity problem, measure the baseline vector and estimate the real directions of signals. The detection scheme adopts an M of N algorithm (if M or more of the test values exceed the threshold, the algorithm declares the presence of a spoofing signal), integrating carrier phase measurements of all the available satellites. Finally, the proposed method is verified by real experiments. This spoofing detection method can easily be applied to GNSS anti-spoofing receivers without changing their architecture and has simple and effective characteristics.

The importance of the Global Positioning System (GPS) and related electronic systems continues to increase in a range of environmental, engineering and navigation applications. However, civilian GPS signals are vulnerable to Radio Frequency (RF) interference. Spoofing is an intentional intervention that aims to force a GPS receiver to acquire and track invalid navigation data. Analysis of spoofing and authentic signal patterns represents the differences as phase, energy and imaginary components of the signal. In this paper, early-late phase, delta, and signal level as the three main features are extracted from the correlation output of the tracking loop. Using these features, spoofing detection can be performed by exploiting conventional machine learning algorithms such as K-Nearest Neighbourhood (KNN) and naive Bayesian classifier. A Neural Network (NN) as a learning machine is a modern computational method for collecting the required knowledge and predicting the output values in complicated systems. This paper presents a new approach for GPS spoofing detection based on multi-layer NN whose inputs are indices of features. Simulation results on a software GPS receiver showed adequate detection accuracy was obtained from NN with a short detection time.