We introduce a new attack against face verification systems based on Deep Neural Networks (DNN). The attack relies on the introduction into the network of a hidden backdoor, whose activation at test time induces a verification error allowing the attacker to impersonate any user. The new attack, named Master Key backdoor attack, operates by interfering with the training phase, so to instruct the DNN to always output a positive verification answer when the face of the attacker is presented at its input. With respect to existing attacks, the new backdoor attack offers much more flexibility, since the attacker does not need to know the identity of the victim beforehand. In this way, he can deploy a Universal Impersonation attack in an open-set framework, allowing him to impersonate any enrolled users, even those that were not yet enrolled in the system when the attack was conceived. We present a practical implementation of the attack targeting a Siamese-DNN face verification system, and show its effectiveness when the system is trained on VGGFace2 dataset and tested on LFW and YTF datasets. According to our experiments, the Master Key backdoor attack provides a high attack success rate even when the ratio of poisoned training data is as small as 0.01, thus raising a new alarm regarding the use of DNN-based face verification systems in security-critical applications.

Over the past two decades, CNN architectures have produced compelling models of sound perception and cognition, learning hierarchical organizations of features. Analogous to successes in computer vision, audio feature classification can be optimized for a particular task of interest, over a wide variety of datasets and labels. In fact similar architectures designed for image understanding have proven effective for acoustic scene analysis. Here we propose applying Transformer based architectures without convolutional layers to raw audio signals. On a standard dataset of Free Sound 50K,comprising of 200 categories, our model outperforms convolutional models to produce state of the art results. This is significant as unlike in natural language processing and computer vision, we do not perform unsupervised pre-training for outperforming convolutional architectures. On the same training set, with respect mean aver-age precision benchmarks, we show a significant improvement. We further improve the performance of Transformer architectures by using techniques such as pooling inspired from convolutional net-work designed in the past few years. In addition, we also show how multi-rate signal processing ideas inspired from wavelets, can be applied to the Transformer embeddings to improve the results. We also show how our models learns a non-linear non constant band-width filter-bank, which shows an adaptable time frequency front end representation for the task of audio understanding, different from other tasks e.g. pitch estimation.

Current computational-emotion research has focused on applying acoustic properties to analyze how emotions are perceived mathematically or used in natural language processing machine learning models. With most recent interest being in analyzing emotions from the spoken voice, little experimentation has been performed to discover how emotions are recognized in the singing voice -- both in noiseless and noisy data (i.e., data that is either inaccurate, difficult to interpret, has corrupted/distorted/nonsense information like actual noise sounds in this case, or has a low ratio of usable/unusable information). Not only does this ignore the challenges of training machine learning models on more subjective data and testing them with much noisier data, but there is also a clear disconnect in progress between advancing the development of convolutional neural networks and the goal of emotionally cognizant artificial intelligence. By training a new model to include this type of information with a rich comprehension of psycho-acoustic properties, not only can models be trained to recognize information within extremely noisy data, but advancement can be made toward more complex biofeedback applications -- including creating a model which could recognize emotions given any human information (language, breath, voice, body, posture) and be used in any performance medium (music, speech, acting) or psychological assistance for patients with disorders such as BPD, alexithymia, autism, among others. This paper seeks to reflect and expand upon the findings of related research and present a stepping-stone toward this end goal.

Recently, machine learning approaches on Graph data have become very popular. It was observed that significant results were obtained by including implicit or explicit logical connections between data samples that make up the data to the model. In this context, the developing GCN model has made significant experimental contributions with Convolution filters applied to graph data. This model follows Transductive and Semi-Supervised Learning approach. Due to its transductive property, all of the data samples, which is partially labeled, are given as input to the model. Labeling, which is a cost, is very important. Within the scope of this study, the following research question is tried to be answered: If at least how many samples are labeled, the optimum model success is achieved? In addition, some experimental contributions have been made on the accuracy of the model, whichever sampling approach is used with fixed labeling effort. According to the experiments, the success of the model can be increased by using the local centrality metric.

To assess generalization, machine learning scientists typically either (i) bound the generalization gap and then (after training) plug in the empirical risk to obtain a bound on the true risk; or (ii) validate empirically on holdout data. However, (i) typically yields vacuous guarantees for overparameterized models. Furthermore, (ii) shrinks the training set and its guarantee erodes with each re-use of the holdout set. In this paper, we introduce a method that leverages unlabeled data to produce generalization bounds. After augmenting our (labeled) training set with randomly labeled fresh examples, we train in the standard fashion. Whenever classifiers achieve low error on clean data and high error on noisy data, our bound provides a tight upper bound on the true risk. We prove that our bound is valid for 0-1 empirical risk minimization and with linear classifiers trained by gradient descent. Our approach is especially useful in conjunction with deep learning due to the early learning phenomenon whereby networks fit true labels before noisy labels but requires one intuitive assumption. Empirically, on canonical computer vision and NLP tasks, our bound provides non-vacuous generalization guarantees that track actual performance closely. This work provides practitioners with an option for certifying the generalization of deep nets even when unseen labeled data is unavailable and provides theoretical insights into the relationship between random label noise and generalization.

Knowledge distillation (KD) has been actively studied for image classification tasks in deep learning, aiming to improve the performance of a student model based on the knowledge from a teacher model. However, there have been very few efforts for applying KD in image regression with a scalar response, and there is no KD method applicable to both tasks. Moreover, existing KD methods often require a practitioner to carefully choose or adjust the teacher and student architectures, making these methods less scalable in practice. Furthermore, although KD is usually conducted in scenarios with limited labeled data, very few techniques are developed to alleviate such data insufficiency. To solve the above problems in an all-in-one manner, we propose in this paper a unified KD framework based on conditional generative adversarial networks (cGANs), termed cGAN-KD. Fundamentally different from existing KD methods, cGAN-KD distills and transfers knowledge from a teacher model to a student model via cGAN-generated samples. This unique mechanism makes cGAN-KD suitable for both classification and regression tasks, compatible with other KD methods, and insensitive to the teacher and student architectures. Also, benefiting from the recent advances in cGAN methodology and our specially designed subsampling and filtering procedures, cGAN-KD also performs well when labeled data are scarce. An error bound of a student model trained in the cGAN-KD framework is derived in this work, which theoretically explains why cGAN-KD takes effect and guides the implementation of cGAN-KD in practice. Extensive experiments on CIFAR-10 and Tiny-ImageNet show that we can incorporate state-of-the-art KD methods into the cGAN-KD framework to reach a new state of the art. Also, experiments on RC-49 and UTKFace demonstrate the effectiveness of cGAN-KD in image regression tasks, where existing KD methods are inapplicable.

Objective: Accurate evaluation of the root canal filling result in X-ray image is a significant step for the root canal therapy, which is based on the relative position between the apical area boundary of tooth root and the top of filled gutta-percha in root canal as well as the shape of the tooth root and so on to classify the result as correct-filling, under-filling or over-filling. Methods: We propose a novel anatomy-guided Transformer diagnosis network. For obtaining accurate anatomy-guided features, a polynomial curve fitting segmentation is proposed to segment the fuzzy boundary. And a Parallel Bottleneck Transformer network (PBT-Net) is introduced as the classification network for the final evaluation. Results, and conclusion: Our numerical experiments show that our anatomy-guided PBT-Net improves the accuracy from 40\% to 85\% relative to the baseline classification network. Comparing with the SOTA segmentation network indicates that the ASD is significantly reduced by 30.3\% through our fitting segmentation. Significance: Polynomial curve fitting segmentation has a great segmentation effect for extremely fuzzy boundaries. The prior knowledge guided classification network is suitable for the evaluation of root canal therapy greatly. And the new proposed Parallel Bottleneck Transformer for realizing self-attention is general in design, facilitating a broad use in most backbone networks.

Massive multiple-input multiple-output (MIMO) is one of the key techniques to achieve better spectrum and energy efficiency in 5G system. The channel state information (CSI) needs to be fed back from the user equipment to the base station in frequency division duplexing (FDD) mode. However, the overhead of the direct feedback is unacceptable due to the large antenna array in massive MIMO system. Recently, deep learning is widely adopted to the compressed CSI feedback task and proved to be effective. In this paper, a novel network named aggregated channel reconstruction network (ACRNet) is designed to boost the feedback performance with network aggregation and parametric rectified linear unit (PReLU) activation. The practical deployment of the feedback network in the communication system is also considered. Specifically, the elastic feedback scheme is proposed to flexibly adapt the network to meet different resource limitations. Besides, the network binarization technique is combined with the feature quantization for lightweight and practical deployment. Experiments show that the proposed ACRNet outperforms loads of previous state-of-the-art networks, providing a neat feedback solution with high performance, low cost and impressive flexibility. This work was supported in part by the National Key R&D Program of China under Grant 2017YFE0112300. The authors are with the Department of Electronic Engineering, Tsinghua University, and Beijing National Research Center for Information Science and Technology (BNRist), Beijing 100084, China. Massive multiple-input multiple-output (MIMO) is widely regarded as one of the key techniques in the fifth-generation wireless communication system [1]. With larger antenna array, massive MIMO is able to boost both spectrum and energy efficiency [2]. The downlink channel state information (CSI) needs to be obtained at the base station (BS) so that the MIMO system can acquire the performance gain with beamforming [3]. In frequency division duplexing (FDD) mode, downlink CSI is usually estimated at the user equipment (UE) and fed back to the BS due to the channel non-reciprocity. However, the dimension of CSI matrix is sharply increased in massive MIMO system.

In this paper, we propose Stochastic Block-ADMM as an approach to train deep neural networks in batch and online settings. Our method works by splitting neural networks into an arbitrary number of blocks and utilizes auxiliary variables to connect these blocks while optimizing with stochastic gradient descent. This allows training deep networks with non-differentiable constraints where conventional backpropagation is not applicable. An application of this is supervised feature disentangling, where our proposed DeepFacto inserts a non-negative matrix factorization (NMF) layer into the network. Since backpropagation only needs to be performed within each block, our approach alleviates vanishing gradients and provides potentials for parallelization. We prove the convergence of our proposed method and justify its capabilities through experiments in supervised and weakly-supervised settings.

The field of neuromorphic computing is in a period of active exploration. While many tools have been developed to simulate neuronal dynamics or convert deep networks to spiking models, general software libraries for learning rules remain underexplored. This is partly due to the diverse, challenging nature of efforts to design new learning rules, which range from encoding methods to gradient approximations, from population approaches that mimic the Bayesian brain to constrained learning algorithms deployed on memristor crossbars. To address this gap, we present Neko, a modular, extensible library with a focus on aiding the design of new learning algorithms. We demonstrate the utility of Neko in three exemplar cases: online local learning, probabilistic learning, and analog on-device learning. Our results show that Neko can replicate the state-of-the-art algorithms and, in one case, lead to significant outperformance in accuracy and speed. Further, it offers tools including gradient comparison that can help develop new algorithmic variants. Neko is an open source Python library that supports PyTorch and TensorFlow backends.