Quantization index modulation (QIM) steganography makes it possible to hide secret information in voice-over IP (VoIP) streams, which could be utilized by unauthorized entities to set up covert channels for malicious purposes. Detecting short QIM steganography samples, as is required by real circumstances, remains an unsolved challenge. In this paper, we propose an effective online steganalysis method to detect QIM steganography. We find four strong codeword correlation patterns in VoIP streams, which will be distorted after embedding with hidden data. To extract those correlation features, we propose the codeword correlation model, which is based on recurrent neural network (RNN). Furthermore, we propose the feature classification model to classify those correlation features into cover speech and stego speech categories. The whole RNN-based steganalysis model (RNN-SM) is trained in a supervised learning framework. Experiments show that on full embedding rate samples, RNN-SM is of high detection accuracy, which remains over 90% even when the sample is as short as 0.1 s, and is significantly higher than other state-of-the-art methods. For the challenging task of conducting steganalysis towards low embedding rate samples, RNN-SM also achieves a high accuracy. The average testing time for each sample is below 0.15% of sample length. These clues show that RNN-SM meets the short sample detection demand and is a state-of-the-art algorithm for online VoIP steganalysis.
Frequency selective scheduling is an attractive feature in the 3GPP LTE system that allows optimum usage of the allocated spectrum. In order to support frequency selective scheduling in the downlink, the mobile user needs to feedback channel quality indication (CQI) of the downlink channel to the base station. Several CQI feedback scheme have been proposed for 3GPP LTE systems. We propose to apply Haar compression to distributed subband groups to reduce the CQI feedback overhead. The simulation results indicate that the distributed- Haar scheme achieves the best trade-off between the throughput performance and overhead reduction compared with other CQI feedback schemes. We also observe that the sensitivity in sector throughput performance to user mobility is approximately the same for all feedback methods considered in the paper.
The privacy implications of generative adversarial networks (GANs) are a topic of great interest, leading to several recent algorithms for training GANs with privacy guarantees. By drawing connections to the generalization properties of GANs, we prove that under some assumptions, GAN-generated samples inherently satisfy some (weak) privacy guarantees. First, we show that if a GAN is trained on m samples and used to generate n samples, the generated samples are (epsilon, delta)-differentially-private for (epsilon, delta) pairs where delta scales as O(n/m). We show that under some special conditions, this upper bound is tight. Next, we study the robustness of GAN-generated samples to membership inference attacks. We model membership inference as a hypothesis test in which the adversary must determine whether a given sample was drawn from the training dataset or from the underlying data distribution. We show that this adversary can achieve an area under the ROC curve that scales no better than O(m^{-1/4}).