Deep learning models are known to be vulnerable to various adversarial manipulations of the training data, model parameters, and input data. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model, so the model behaves according to the adversary's objective if the input contains the backdoor features (e.g., a stamp on an image). The poisoned model's behavior on clean data, however, remains unchanged. Many detection algorithms are designed to detect backdoors on input samples or model activation functions, in order to remove the backdoor. These algorithms rely on the statistical difference between the latent representations of backdoor-enabled and clean input data in the poisoned model. In this paper, we design an adversarial backdoor embedding algorithm that can bypass the existing detection algorithms including the state-of-the-art techniques (published in IEEE S\&P 2019 and NeurIPS 2018). We design a strategic adversarial training that optimizes the original loss function of the model, and also maximizes the indistinguishability of the hidden representations of poisoned data and clean data. We show the effectiveness of our attack on multiple datasets and model architectures. This work calls for designing adversary-aware defense mechanisms for backdoor detection algorithms.

Several deep models, esp. the generative, compare the samples from two distributions (e.g. WAE like AutoEncoder models, set-processing deep networks, etc) in their cost functions. Using all these methods one cannot train the model directly taking small size (in extreme -- one element) batches, due to the fact that samples are to be compared. We propose a generic approach to training such models using one-element mini-batches. The idea is based on splitting the batch in latent into parts: previous, i.e. historical, elements used for latent space distribution matching and the current ones, used both for latent distribution computation and the minimization process. Due to the smaller memory requirements, this allows to train networks on higher resolution images then in the classical approach.

Connectivity between different brain regions is one of the most important properties for classification of brain signals including electroencephalography (EEG). However, how to define the connectivity structure for a given task is still an open problem, because there is no ground truth about how the connectivity structure should be in order to maximize the performance. In this paper, we propose an end-to-end neural network model for EEG classification, which can extract an appropriate multi-layer graph structure and signal features directly from a set of raw EEG signals and perform classification. Experimental results demonstrate that our method yields improved performance in comparison to the existing approaches where manually defined connectivity structures and signal features are used. Furthermore, we show that the graph structure extraction process is reliable in terms of consistency, and the learned graph structures make much sense in the neuroscientific viewpoint.

Data-driven approaches which aim to identify and predict player engagement are becoming increasingly popular in games industry contexts. This is due to the growing practice of tracking and storing large volumes of in-game telemetries coupled with a desire to tailor the gaming experience to the end-user's needs. These approaches are particularly useful not just for companies adopting Game-as-a-Service (GaaS) models (e.g. for re-engagement strategies) but also for those working under persistent content-delivery regimes (e.g. for better audience targeting). A major challenge for the latter is to build engagement models of the user which are data-efficient, holistic and can generalize across multiple game titles and genres with minimal adjustments. This work leverages a theoretical framework rooted in engagement and behavioural science research for building a model able to estimate engagement-related behaviours employing only a minimal set of game-agnostic metrics. Through a series of experiments we show how, by modelling early user-game interactions, this approach can make joint estimates of long-term survival time and churn probability across several single-player games in a range of genres. The model proposed is very suitable for industry applications since it relies on a minimal set of metrics and observations, scales well with the number of users and is explicitly designed to work across a diverse range of titles.

Existing deep neural networks (DNNs), say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose "shock-absorbing" robust features such as binarization (e.g., rounding) and group extraction (e.g., color or shape) to augment the classification pipeline, resulting in more robust classifiers. Experimentally, we show that augmenting ML models with these techniques leads to improved overall robustness on adversarial inputs as well as significant improvements in training time. On the MNIST dataset, we achieved 14x speedup in training time to obtain 90% adversarial accuracy compared to the state-of-the-art adversarial training method of Madry et al. [12], as well as retained higher adversarial accuracy over a broader range of attacks. We also find robustness improvements on traffic sign classification using robust feature augmentation. Finally, we give theoretical insights for why one can expect robust feature augmentation to reduce adversarial input space.

The detection of cell shape changes in 3D time-lapse images of complex tissues is an important task. However, it is a challenging and tedious task to establish a comprehensive dataset to improve the performance of deep learning models. In the paper, we present a deep learning approach to augment 3D live images of the Caenorhabditis elegans embryo, so that we can further speed up the specific structural pattern recognition. We use an unsupervised training over unlabeled images to generate supplementary datasets for further pattern recognition. Technically, we used Alex-style neural networks in a generative adversarial network framework to generate new datasets that have common features of the C. elegans membrane structure. We also made the dataset available for a broad scientific community.

Many of the strongest game playing programs use a combination of Monte Carlo tree search (MCTS) and deep neural networks (DNN), where the DNNs are used as policy or value evaluators. Given a limited budget, such as online playing or during the self-play phase of AlphaZero (AZ) training, a balance needs to be reached between accurate state estimation and more MCTS simulations, both of which are critical for a strong game playing agent. Typically, larger DNNs are better at generalization and accurate evaluation, while smaller DNNs are less costly, and therefore can lead to more MCTS simulations and bigger search trees with the same budget. This paper introduces a new method called the multiple policy value MCTS (MPV-MCTS), which combines multiple policy value neural networks (PV-NNs) of various sizes to retain advantages of each network, where two PV-NNs f_S and f_L are used in this paper. We show through experiments on the game NoGo that a combined f_S and f_L MPV-MCTS outperforms single PV-NN with policy value MCTS, called PV-MCTS. Additionally, MPV-MCTS also outperforms PV-MCTS for AZ training.

Current state-of-the-art approaches for spatio-temporal action detection have achieved impressive results but remain unsatisfactory for temporal extent detection. The main reason comes from that, there are some ambiguous states similar to the real actions which may be treated as target actions even by a well-trained network. In this paper, we define these ambiguous samples as "transitional states", and propose a Transition-Aware Context Network (TACNet) to distinguish transitional states. The proposed TACNet includes two main components, i.e., temporal context detector and transition-aware classifier. The temporal context detector can extract long-term context information with constant time complexity by constructing a recurrent network. The transition-aware classifier can further distinguish transitional states by classifying action and transitional states simultaneously. Therefore, the proposed TACNet can substantially improve the performance of spatio-temporal action detection. We extensively evaluate the proposed TACNet on UCF101-24 and J-HMDB datasets. The experimental results demonstrate that TACNet obtains competitive performance on JHMDB and significantly outperforms the state-of-the-art methods on the untrimmed UCF101-24 in terms of both frame-mAP and video-mAP.

Neural networks have successfully been applied to solving reasoning tasks, ranging from learning simple concepts like "close to", to intricate questions whose reasoning procedures resemble algorithms. Empirically, not all network structures work equally well for reasoning. For example, Graph Neural Networks have achieved impressive empirical results, while the less structured neural networks may fail to learn to reason. Theoretically, there is currently limited understanding of the interplay between reasoning tasks and network learning. In this paper, we develop a framework to characterize which tasks a neural network can learn well, by studying how well its structure aligns with the algorithmic structure of the relevant reasoning procedure. This suggests that Graph Neural Networks can learn dynamic programming, a powerful algorithmic strategy that solves a broad class of reasoning problems, such as relational question answering, sorting, intuitive physics, and shortest paths. Our perspective also implies strategies to design neural architectures for complex reasoning. On several abstract reasoning tasks, we see empirically that our theory aligns well with practice.

On the other hand, AM has rapidlyfrom a given document (Lippi 2016). Recent years have seen the development evolved by exploiting state-of-the-art neural architectures of a large number of techniques in this area, on coming from deep learning. So far, the wake of the advancements produced by deep these two worlds have progressed largely independently learning on the whole research field of natural of each other. Only recently, a few works language processing (NLP). Yet, it is widely recognized have taken some steps towards the integration of that the existing AM systems still have such methods, by applying techniques combining a large margin of improvement, as good results sub-symbolic classifiers with knowledge expressed have been obtained with some genres where prior in the form of rules and constraints to AM. knowledge on the structure of the text eases some Niculae et al. (2017) adopted structuredFor instance, AM tasks, but other genres such as legal cases support vector machines and recurrent neural and social media documents still require more networks to collectively classify argument components work (Cabrio and Villata, 2018). Performing and and their relations in short documents, understanding argumentation requires advanced by hard-coding contextual dependencies and constraints reasoning capabilities that are natural skills for humans, of the argument model in a factor graph. but which are difficult to learn for a machine. A joint inference approach for argument component Understanding whether a given piece of classification and relation identification was evidence supports a given claim, or whether two Persing and Ng (2016), followinginstead proposed by claims attack each other, are complex problems a pipeline scheme where integer linear programming that humans are able to address thanks to their is used to enforce mathematical constraints ability to exploit commonsense knowledge, and to on the outcomes of a first-stage set of classifiers.