We study the adaptation of convolutional neural networks to the complex-valued temporal radio signal domain. We compare the efficacy of radio modulation classification using naively learned features against using expert feature based methods which are widely used today and e show significant performance improvements. We show that blind temporal learning on large and densely encoded time series using deep convolutional neural networks is viable and a strong candidate approach for this task especially at low signal to noise ratio.

We conduct an in depth study on the performance of deep learning based radio signal classification for radio communications signals. We consider a rigorous baseline method using higher order moments and strong boosted gradient tree classification and compare performance between the two approaches across a range of configurations and channel impairments. We consider the effects of carrier frequency offset, symbol rate, and multi-path fading in simulation and conduct over-the-air measurement of radio classification performance in the lab using software radios and compare performance and training strategies for both. Finally we conclude with a discussion of remaining problems, and design considerations for using such techniques.

In this paper, the fundamental insecurities hampering a scalable, wide-spread deployment of biometric authentication are examined, and a cryptosystem capable of using flngerprint data as its key is presented. For our application, we focus on situations where a private key stored on a smartcard is used for authentication in a networked environment, and we assume an attacker can launch ofi-line attacks against a stolen card.Juels and Sudan's fuzzy vault is used as a starting point for building and analyzing a secure authentication scheme using flngerprints and smartcards called a fingerprint vault. Fingerprint minutiae coordinates mi are encoded as elements in a flnite fleld F and the secret key is encoded in a polynomial f (x) over F [x]. The polynomial is evaluated at the minutiae locations, and the pairs (mi, f (mi)) are stored along with random (ci, di) chafi points such that di = f (ci). Given a matching flngerprint, a valid user can seperate out enough true points from the chafi points to reconstruct f (x), and hence the original secret key.The parameters of the vault are selected such that the attacker's vault unlocking complexity is maximized, subject to zero unlocking complexity with a matching flngerprint and a reasonable amount of error. For a feature location measurement variance of 9 pixels, the optimal vault is 2 69 times more di-cult to unlock for an attacker compared to a user posessing a matching flngerprint, along with approximately a 30% chance of unlocking failure.

Abstract-Various spectrum management schemes have been proposed in recent years to improve the spectrum utilization in cognitive radio networks. However, few of them have considered the existence of cognitive attackers who can adapt their attacking strategy to the time-varying spectrum environment and the secondary users' strategy. In this paper, we investigate the security mechanism when secondary users are facing the jamming attack, and propose a stochastic game framework for anti-jamming defense. At each stage of the game, secondary users observe the spectrum availability, the channel quality, and the attackers' strategy from the status of jammed channels. According to this observation, they will decide how many channels they should reserve for transmitting control and data messages and how to switch between the different channels. Using the minimax-Q learning, secondary users can gradually learn the optimal policy, which maximizes the expected sum of discounted payoffs defined as the spectrum-efficient throughput. The proposed stationary policy in the anti-jamming game is shown to achieve much better performance than the policy obtained from myopic learning, which only maximizes each stage's payoff, and a random defense strategy, since it successfully accommodates the environment dynamics and the strategic behavior of the cognitive attackers.

No abstract