Deep neural networks (DNNs) are notorious for their vulnerability to adversarial attacks, which are small perturbations added to their input images to mislead their prediction. Detection of adversarial examples is, therefore, a fundamental requirement for robust classification frameworks. In this work, we present a method for detecting such adversarial attacks, which is suitable for any pre-trained neural network classifier. We use influence functions to measure the impact of every training sample on the validation set data. From the influence scores, we find the most supportive training samples for any given validation example. A k-nearest neighbor (k-NN) model fitted on the DNN's activation layers is employed to search for the ranking of these supporting training samples. We observe that these samples are highly correlated with the nearest neighbors of the normal inputs, while this correlation is much weaker for adversarial inputs. We train an adversarial detector using the k-NN ranks and distances and show that it successfully distinguishes adversarial examples, getting state-of-the-art results on four attack methods with three datasets.

This article investigates the eigenspectrum of the inner product-type kernel matrix $\sqrt{p} \mathbf{K}=\{f( \mathbf{x}_i^{\sf T} \mathbf{x}_j/\sqrt{p})\}_{i,j=1}^n $ under a binary mixture model in the high dimensional regime where the number of data $n$ and their dimension $p$ are both large and comparable. Based on recent advances in random matrix theory, we show that, for a wide range of nonlinear functions $f$, the eigenspectrum behavior is asymptotically equivalent to that of an (at most) cubic function. This sheds new light on the understanding of nonlinearity in large dimensional problems. As a byproduct, we propose a simple function prototype valued in $ (-1,0,1) $ that, while reducing both storage memory and running time, achieves the same (asymptotic) classification performance as any arbitrary function $f$.

The goal of imitation learning (IL) is to learn a good policy from high-quality demonstrations. However, the quality of demonstrations in reality can be diverse, since it is easier and cheaper to collect demonstrations from a mix of experts and amateurs. IL in such situations can be challenging, especially when the level of demonstrators' expertise is unknown. We propose a new IL method called \underline{v}ariational \underline{i}mitation \underline{l}earning with \underline{d}iverse-quality demonstrations (VILD), where we explicitly model the level of demonstrators' expertise with a probabilistic graphical model and estimate it along with a reward function. We show that a naive approach to estimation is not suitable to large state and action spaces, and fix its issues by using a variational approach which can be easily implemented using existing reinforcement learning methods. Experiments on continuous-control benchmarks demonstrate that VILD outperforms state-of-the-art methods. Our work enables scalable and data-efficient IL under more realistic settings than before.

The study presents a general framework for discovering underlying Partial Differential Equations (PDEs) using measured spatiotemporal data. The method, called Sparse Spatiotemporal System Discovery ($\text{S}^3\text{d}$), decides which physical terms are necessary and which can be removed (because they are physically negligible in the sense that they do not affect the dynamics too much) from a pool of candidate functions. The method is built on the recent development of Sparse Bayesian Learning; which enforces the sparsity in the to-be-identified PDEs, and therefore can balance the model complexity and fitting error with theoretical guarantees. Without leveraging prior knowledge or assumptions in the discovery process, we use an automated approach to discover ten types of PDEs, including the famous Navier-Stokes and sine-Gordon equations, from simulation data alone. Moreover, we demonstrate our data-driven discovery process with the Complex Ginzburg-Landau Equation (CGLE) using data measured from a traveling-wave convection experiment. Our machine discovery approach presents solutions that has the potential to inspire, support and assist physicists for the establishment of physical laws from measured spatiotemporal data, especially in notorious fields that are often too complex to allow a straightforward establishment of physical law, such as biophysics, fluid dynamics, neuroscience or nonlinear optics.

The performance of land surface models (LSMs) strongly depends on their unknown parameter variables so that it is necessary to optimize them. Here I present a globally applicable and computationally efficient method for parameter optimization and uncertainty assessment of the LSM by combining Markov Chain Monte Carlo (MCMC) with machine learning. First, I performed the long-term ensemble simulation of the LSM, in which each ensemble member has different parameters' variables, and calculated the gap between simulation and observation, or the cost function, for each ensemble member. Second, I developed the statistical machine learning based surrogate model, which is computationally cheap but accurately mimics the relationship between parameters and the cost function, by applying the Gaussian process regression to learn the model simulation. Third, we applied MCMC by repeatedly driving the surrogate model to get the posterior probabilistic distribution of parameters.

Next week at AI Research Week, hosted by the MIT-IBM Watson AI Lab in Cambridge, MA, we will publish the first major release of the Adversarial Robustness 360 Toolbox (ART). Initially released in April 2018, ART is an open-source library for adversarial machine learning that provides researchers and developers with state-of-the-art tools to defend and verify AI models against adversarial attacks. ART v1.0 marks a milestone in AI security, introducing new features that extend ART to conventional machine learning models and a variety of data types beyond images: The number of reports on real-world exploitations using adversarial attacks against AI is growing, as in the case of anti-virus software, highlighting the importance of understanding, improving and monitoring the adversarial robustness of AI models. ART provides a comprehensive and growing set of tools to systematically assess and improve the robustness of AI models against adversarial attacks, including evasion and poisoning. In evasion attacks, the adversary crafts small changes to the original input to an AI model in order to influence its behaviour.

Many such'literary' quandaries are inspected by expert linguists as analysing and categorising discourses is fairly complex, domain-specific and highly multi-dimensional. One of latest research areas in Natural Language Processing is Authorship Analysis which is trying to leverage the computational power of big-data and artificial intelligence combined with linguistics and cognitive psychology to encode automatic classification of texts, identification of author profiles and resolution of authorship conflicts. This article is an attempt to introduce the concept of authorship analysis, its application areas and the major sub-tasks associated with it. The art and science of discriminating between writing styles of authors by identifying the characteristics of the persona of the authors and examining articles authored by them is called Authorship Analysis. Consequentially, it also aims to determine biographic characteristics of an individual like age, gender, native language and cognitive psychological traits based on "available information" pertaining to that individual. In this article, "available information" refers to textual data only in the context of authorship analysis, however, information in this context could go beyond textual format as it might also involve usage of multi-modal observations.

A Gaussian Process is a non-parametric model that can be used to represent a distribution over functions. Lets break this definition down. Parametric models assume that the data distribution (set of input points, images etc.) can be entirely defined in terms of a finite set of parameters theta. For example in simple linear regression the parameters are the m and c in the equation y mx c. Such that if the model is given the parameters, a future prediction is independent of the data.

What is a genetic algorithm? Bayesian inference ([1] links to particle methods in Bayesian statistics and hidden Markov chain models and [2] a tutorial on genetic particle models) Bioinformatics multiple sequence alignment.[1] SAGA is available on:.[4] Bioinformatics: Motif Discovery.[5] Calculation of bound states and local-density approximations. Code-breaking, using the GA to search large solution spaces of ciphers for the one correct decryption.[8]

Drug repositioning is an attractive cost-efficient strategy for the development of treatments for human diseases. Here, we propose an interpretable model that learns disease self-representations for drug repositioning. Our self-representation model represents each disease as a linear combination of a few other diseases. We enforce the proximity between diseases to preserve the geometric structure of the human phenome network - a domain-specific knowledge that naturally adds relational inductive bias to the disease self-representations. We prove that our method is globally optimal and show results outperforming state-of-the-art drug repositioning approaches. We further show that the disease self-representations are biologically interpretable.