We propose an audio-visual person identification approach based on a joint deep Boltzmann machine (jDBM) model. The proposed jDBM model is trained in three steps: 1) learning the unimodal DBM models corresponding to the speech and facial image modalities, 2) learning the shared layer parameters using a joint restricted Boltzmann machine (jRBM) model, and 3) the fine-tuning of the jDBM model after the initialization with the parameters of the unimodal DBMs and the shared layer. The activation probabilities of the units of the shared layer are used as the joint features and a logistic regression classifier is used for the combined speech and facial image recognition. We show that by learning the shared layer parameters using a jRBM, a higher accuracy can be achieved compared to the greedy layer-wise initialization. The performance of our proposed model is also compared with a state-of-the art support vector machine (SVM), deep belief network (DBN), and the deep auto-encoder (DAE) models. In addition, our experimental results show that the joint representations obtained from the proposed jDBM model are robust to noise and missing information. Experiments were carried out on the challenging MOBIO database, which includes audio-visual data captured using mobile phones.

A multibiometric identification system establishes the identity of a person based on the input biometric data presented to its sub-systems. Each sub-system compares the features extracted from the input against the templates of all identities stored in gallery. The best matched identity is ranked highest in the ranked list. In rank-level fusion, the ranked lists from different sub-systems are combined to reach a final decision. However, the state-of-the-art rank-level fusion methods consider that all sub-systems are equally reliable in terms of classifying the probe data. In practice, the probe data may be affected by different sources of degradation (e.g., illumination and pose variation on the face image, environmental noise) and thus affecting the overall recognition accuracy. In this paper, robust rank-level fusion methods (e.g., confidence based highest rank and Borda count) are proposed by using confidence measures for each sub-system in the decision making process. Experimental results show that the proposed confidence based rank-level fusion achieved higher recognition rates than state-of-the-art rank-level fusion methods.

There are many forms of Byzantine attacks, including byzantine black hole attack, Byzantine flood rushing attack, and byzantine wormhole attack. Among all these attacks, Byzantine wormhole attack is considered one of the most complicated and severe attack in mobile ad hoc networks (MANET). In Byzantine wormhole attack, a compromised attacker actively participates in all network functions, and at the same time records packets at one location, tunnels them to another location, and then retransmits them there into the network. Most of the existing solutions targeting Byzantine wormhole attack rely on encryption and authentication which tries to detect packet dropping or modification. In this paper, we propose to detect some abnormal topological features introduced by Byzantine wormhole tunnel to detect Byzantine wormhole attack. Our scheme is easy to implement. The simulation results also show that our scheme can achieve both high Byzantine wormhole detection rate and detection accuracy.