Deep learning methods have shown state of the art performance in a range of tasks from computer vision to natural language processing. However, it is well known that such systems are vulnerable to attackers who craft inputs in order to cause misclassification. The level of perturbation an attacker needs to introduce in order to cause such a misclassification can be extremely small, and often imperceptible. This is of significant security concern, particularly where misclassification can cause harm to humans. We thus propose Deep Latent Defence, an architecture which seeks to combine adversarial training with a detection system. At its core Deep Latent Defence has a adversarially trained neural network. A series of encoders take the intermediate layer representation of data as it passes though the network and project it to a latent space which we use for detecting adversarial samples via a $k$-nn classifier. We present results using both grey and white box attackers, as well as an adaptive $L_{\infty}$ bounded attack which was constructed specifically to try and evade our defence. We find that even under the strongest attacker model that we have investigated our defence is able to offer significant defensive benefits.

Machine learning models, especially neural networks (NNs), have achieved outstanding performance on diverse and complex applications. However, recent work has found that they are vulnerable to Trojan attacks where an adversary trains a corrupted model with poisoned data or directly manipulates its parameters in a stealthy way. Such Trojaned models can obtain good performance on normal data during test time while predicting incorrectly on the adversarially manipulated data samples. This paper aims to develop ways to detect Trojaned models. We mainly explore the idea of meta neural analysis, a technique involving training a meta NN model that can be used to predict whether or not a target NN model has certain properties. We develop a novel pipeline Meta Neural Trojaned model Detection (MNTD) system to predict if a given NN is Trojaned via meta neural analysis on a set of trained shadow models. We propose two ways to train the meta-classifier without knowing the Trojan attacker's strategies. The first one, one-class learning, will fit a novel detection meta-classifier using only benign neural networks. The second one, called jumbo learning, will approximate a general distribution of Trojaned models and sample a "jumbo" set of Trojaned models to train the meta-classifier and evaluate on the unseen Trojan strategies. Extensive experiments demonstrate the effectiveness of MNTD in detecting different Trojan attacks in diverse areas such as vision, speech, tabular data, and natural language processing. We show that MNTD reaches an average of 97% detection AUC (Area Under the ROC Curve) score and outperforms existing approaches. Furthermore, we design and evaluate MNTD system to defend against strong adaptive attackers who have exactly the knowledge of the detection, which demonstrates the robustness of MNTD.

Determining the extent to which different cognitive modalities (understood here as the set of cognitive processes underlying the elaboration of a stimulus by the brain) rely on overlapping neural representations is a fundamental issue in cognitive neuroscience. In the last decade, the identification of shared activity patterns has been mostly framed as a supervised learning problem. For instance, a classifier is trained to discriminate categories (e.g. faces vs. houses) in modality I (e.g. perception) and tested on the same categories in modality II (e.g. imagery). This type of analysis is often referred to as cross-modal decoding. In this paper we take a different approach and instead formulate the problem of assessing shared patterns across modalities within the framework of statistical hypothesis testing. We propose both an appropriate test statistic and a scheme based on permutation testing to compute the significance of this test while making only minimal distributional assumption. We denote this test cross-modal permutation test (CMPT). We also provide empirical evidence on synthetic datasets that our approach has greater statistical power than the cross-modal decoding method while maintaining low Type I errors (rejecting a true null hypothesis). We compare both approaches on an fMRI dataset with three different cognitive modalities (perception, imagery, visual search). Finally, we show how CMPT can be combined with Searchlight analysis to explore spatial distribution of shared activity patterns.

We design a classifier for transactional datasets with application in malware detection. We build the classifier based on the minimum description length (MDL) principle. This involves selecting a model that best compresses the training dataset for each class considering the MDL criterion. To select a model for a dataset, we first use clustering followed by closed frequent pattern mining to extract a subset of closed frequent patterns (CFPs). We show that this method acts as a pattern summarization method to avoid pattern explosion; this is done by giving priority to longer CFPs, and without requiring to extract all CFPs. We then use the MDL criterion to further summarize extracted patterns, and construct a code table of patterns. This code table is considered as the selected model for the compression of the dataset. We evaluate our classifier for the problem of static malware detection in portable executable (PE) files. We consider API calls of PE files as their distinguishing features. The presence-absence of API calls forms a transactional dataset. Using our proposed method, we construct two code tables, one for the benign training dataset, and one for the malware training dataset. Our dataset consists of 19696 benign, and 19696 malware samples, each a binary sequence of size 22761. We compare our classifier with deep neural networks providing us with the state-of-the-art performance. The comparison shows that our classifier performs very close to deep neural networks. We also discuss that our classifier is an interpretable classifier. This provides the motivation to use this type of classifiers where some degree of explanation is required as to why a sample is classified under one class rather than the other class.

Knowledge-based biomedical data science (KBDS) involves the design and implementation of computer systems that act as if they knew about biomedicine. Such systems depend on formally represented knowledge in computer systems, often in the form of knowledge graphs. Here we survey the progress in the last year in systems that use formally represented knowledge to address data science problems in both clinical and biological domains, as well as on approaches for creating knowledge graphs. Major themes include the relationships between knowledge graphs and machine learning, the use of natural language processing, and the expansion of knowledge-based approaches to novel domains, such as Chinese Traditional Medicine and biodiversity.

An app uses a smart phone camera to detect leukocoria, a pale reflection from the back of the eye. It can be an early sign of disease. Here it appears light brown compared the healthy eye. An app uses a smart phone camera to detect leukocoria, a pale reflection from the back of the eye. It can be an early sign of disease.

Fraud causes substantial costs and losses for companies and clients in the finance and insurance industries. Examples are fraudulent credit card transactions or fraudulent claims. It has been estimated that roughly $10$ percent of the insurance industry's incurred losses and loss adjustment expenses each year stem from fraudulent claims. The rise and proliferation of digitization in finance and insurance have lead to big data sets, consisting in particular of text data, which can be used for fraud detection. In this paper, we propose architectures for text embeddings via deep learning, which help to improve the detection of fraudulent claims compared to other machine learning methods. We illustrate our methods using a data set from a large international health insurance company. The empirical results show that our approach outperforms other state-of-the-art methods and can help make the claims management process more efficient. As (unstructured) text data become increasingly available to economists and econometricians, our proposed methods will be valuable for many similar applications, particularly when variables have a large number of categories as is typical for example of the International Classification of Disease (ICD) codes in health economics and health services.

Deterministic neural networks (NNs) are increasingly being deployed in safety critical domains, where calibrated, robust and efficient measures of uncertainty are crucial. While it is possible to train regression networks to output the parameters of a probability distribution by maximizing a Gaussian likelihood function, the resulting model remains oblivious to the underlying confidence of its predictions. In this paper, we propose a novel method for training deterministic NNs to not only estimate the desired target but also the associated evidence in support of that target. We accomplish this by placing evidential priors over our original Gaussian likelihood function and training our NN to infer the hyperparameters of our evidential distribution. We impose priors during training such that the model is penalized when its predicted evidence is not aligned with the correct output. Thus the model estimates not only the probabilistic mean and variance of our target but also the underlying uncertainty associated with each of those parameters. We observe that our evidential regression method learns well-calibrated measures of uncertainty on various benchmarks, scales to complex computer vision tasks, and is robust to adversarial input perturbations.

Gaining more comprehensive knowledge about drug-drug interactions (DDIs) is one of the most important tasks in drug development and medical practice. Recently graph neural networks have achieved great success in this task by modeling drugs as nodes and drug-drug interactions as links and casting DDI predictions as link prediction problems. However, correlations between link labels (e.g., DDI types) were rarely considered in existing works. We propose the graph energy neural network ( GENN) to explicitly model link type correlations. We formulate the DDI prediction task as a structure prediction problem, and introduce a new energy-based model where the energy function is defined by graph neural networks. Experiments on two real world DDI datasets demonstrated that GENN is superior to many baselines without consideration of link type correlations and achieved 13. 77% and 5.01% PR-AUC improvement on the two datasets, respectively. We also present a case study in which GENN can better capture meaningful DDI correlations compared with baseline models. The use of drug combinations is common and often necessary for treating patients with complex diseases.

Traditional machine learning methods share a common hypothesis: training and testing datasets must be in a common feature space with the same distribution. However, in reality, the labeled target data may be rare, so that target space does not share the same feature space or distribution as an available training set (source domain). To address the mismatch of domains, we propose a Dual-Subspace Transfer Learning (DSTL) framework that considers both the common and specific information of the two domains. In DSTL, a latent common subspace is first learned to preserve the data properties and reduce the discrepancy of domains. Then, we propose a mapping strategy to transfer the sourcespecific information to the target subspace. The integration of the domain-common and specific information constructs the proposed DSTL framework. In comparison to the stateart-of works, the main contribution of our work is that the DSTL framework not only considers the commonalities, but also exploits the specific information. Experiments on three emotional speech corpora verify the effectiveness of our approach. The results show that the methods which include both domain-common and specific information perform better than the baseline methods which only exploit the domain commonalities.