Identifying patient characteristics that influence the rate of colorectal polyp recurrence can provide important insights into which patients are at higher risk for recurrence. We used natural language processing to extract polyp morphological characteristics from 953 polyp-presenting patients' electronic medical records. We used subsequent colonoscopy reports to examine how the time to polyp recurrence (731 patients experienced recurrence) is influenced by these characteristics as well as anthropometric features using Kaplan-Meier curves, Cox proportional hazards modeling, and random survival forest models. We found that the rate of recurrence differed significantly by polyp size, number, and location and patient smoking status. Additionally, right-sided colon polyps increased recurrence risk by 30% compared to left-sided polyps. History of tobacco use increased polyp recurrence risk by 20% compared to never-users. A random survival forest model showed an AUC of 0.65 and identified several other predictive variables, which can inform development of personalized polyp surveillance plans.

Existing deep active learning algorithms achieve impressive sampling efficiency on natural language processing tasks. However, they exhibit several weaknesses in practice, including (a) inability to use uncertainty sampling with black-box models, (b) lack of robustness to noise in labeling, (c) lack of transparency. In response, we propose a transparent batch active sampling framework by estimating the error decay curves of multiple feature-defined subsets of the data. Experiments on four named entity recognition (NER) tasks demonstrate that the proposed methods significantly outperform diversification-based methods for black-box NER taggers and can make the sampling process more robust to labeling noise when combined with uncertainty-based methods. Furthermore, the analysis of experimental results sheds light on the weaknesses of different active sampling strategies, and when traditional uncertainty-based or diversification-based methods can be expected to work well.

Deep Neural Networks (DNNs) are susceptible to model stealing attacks, which allows a data-limited adversary with no knowledge of the training dataset to clone the functionality of a target model, just by using black-box query access. Such attacks are typically carried out by querying the target model using inputs that are synthetically generated or sampled from a surrogate dataset to construct a labeled dataset. The adversary can use this labeled dataset to train a clone model, which achieves a classification accuracy comparable to that of the target model. We propose "Adaptive Misinformation" to defend against such model stealing attacks. We identify that all existing model stealing attacks invariably query the target model with Out-Of-Distribution (OOD) inputs. By selectively sending incorrect predictions for OOD queries, our defense substantially degrades the accuracy of the attacker's clone model (by up to 40%), while minimally impacting the accuracy (<0.5%) for benign users. Compared to existing defenses, our defense has a significantly better security vs accuracy trade-off and incurs minimal computational overhead.

A common problem of the real-world data sets is the class imbalance, which can significantly affect the classification abilities of classifiers. Numerous methods have been proposed to cope with this problem; however, even state-of-the-art methods offer a limited improvement (if any) for data sets with critically under-represented minority classes. For such problematic cases, an "outside the box" solution is required. Therefore, we propose a novel technique, called enrichment, which uses the information (observations) from the external data set(s). We present three approaches to implement enrichment technique: (1) selecting observations randomly, (2) iteratively choosing observations that improve the classification result, (3) adding observations that help the classifier to determine the border between classes better. We then thoroughly analyze developed solutions on ten real-world data sets to experimentally validate their usefulness. On average, our best approach improves the classification quality by 27\%, and in the best case, by outstanding 66\%. We also compare our technique with the universally applicable state-of-the-art methods. We find that our technique surpasses the existing methods performing, on average, 21\% better. The advantage is especially noticeable for the smallest data sets, for which existing methods failed, while our solutions achieved the best results. Additionally, our technique applies to both the multi-class and binary classification tasks. It can also be combined with other techniques dealing with the class imbalance problem.

Feature selection is a crucial preprocessing step in data analytics and machine learning. Classical feature selection algorithms select features based on the correlations between predictive features and the class variable and do not attempt to capture causal relationships between them. It has been shown that the knowledge about the causal relationships between features and the class variable has potential benefits for building interpretable and robust prediction models, since causal relationships imply the underlying mechanism of a system. Consequently, causality-based feature selection has gradually attracted greater attentions and many algorithms have been proposed. In this paper, we present a comprehensive review of recent advances in causality-based feature selection. To facilitate the development of new algorithms in the research area and make it easy for the comparisons between new methods and existing ones, we develop the first open-source package, called CausalFS, which consists of most of the representative causality-based feature selection algorithms (available at https://github.com/kuiy/CausalFS). Using CausalFS, we conduct extensive experiments to compare the representative algorithms with both synthetic and real-world data sets. Finally, we discuss some challenging problems to be tackled in future causality-based feature selection research.

Outlier detection and novelty detection are two important topics for anomaly detection. Suppose the majority of a dataset are drawn from a certain distribution, outlier detection and novelty detection both aim to detect data samples that do not fit the distribution. Outliers refer to data samples within this dataset, while novelties refer to new samples. In the meantime, backdoor poisoning attacks for machine learning models are achieved through injecting poisoning samples into the training dataset, which could be regarded as "outliers" that are intentionally added by attackers. Differential privacy has been proposed to avoid leaking any individual's information, when aggregated analysis is performed on a given dataset. It is typically achieved by adding random noise, either directly to the input dataset, or to intermediate results of the aggregation mechanism. In this paper, we demonstrate that applying differential privacy can improve the utility of outlier detection and novelty detection, with an extension to detect poisoning samples in backdoor attacks. We first present a theoretical analysis on how differential privacy helps with the detection, and then conduct extensive experiments to validate the effectiveness of differential privacy in improving outlier detection, novelty detection, and backdoor attack detection.

From Equifax to Yahoo, and Facebook to Marriott, large-scale data breaches impacting hundreds of millions of consumers have received their fair share of media attention in recent years. All this ink hasn't been spilled (or pixels displayed) in vain: there's growing awareness among business leaders of the security and privacy risks their organizations face, and increasing concern that their preparedness may be inadequate. In a recent PwC survey, for example, 72% of CEOs worldwide listed cybercriminal activity as a significant threat to their businesses, yet only 35% were comfortable with their organization's digital resilience and readiness to face such threats. Especially among small and mid-sized enterprises, the growth in awareness of the severity and urgency of cybersecurity risks is driving demand for managed security services. Organizations are increasingly turning to external vendors to help them build, maintain, and monitor their security operations programs and the technologies that comprise them.

Recent studies on fairness in automated decision making systems have both investigated the potential future impact of these decisions on the population at large, and emphasized that imposing ''typical'' fairness constraints such as demographic parity or equality of opportunity does not guarantee a benefit to disadvantaged groups. However, these previous studies have focused on either simple one-step cost/benefit criteria, or on discrete underlying state spaces. In this work, we first propose a natural continuous representation of population state, governed by the Beta distribution, using a loan granting setting as a running example. Next, we apply a model of population dynamics under lending decisions, and show that when conditional payback probabilities are estimated correctly 1) ``optimal'' behavior by lenders can lead to ''Matthew Effect'' bifurcations (i.e., ''the rich get richer and the poor get poorer''), but that 2) many common fairness constraints on the allowable policies cause groups to converge to the same equilibrium point. Last, we contrast our results in the case of misspecified conditional probability estimates with prior work, and show that for this model, different levels of group misestimation guarantees that even fair policies lead to bifurcations. We illustrate some of the modeling conclusions on real data from credit scoring.

Neural network interpretability is a vital component for applications across a wide variety of domains. In such cases it is often useful to analyze a network which has already been trained for its specific purpose. In this work, we develop a method to produce explanation masks for pre-trained networks. Masks are created by a secondary network whose goal is to create as small an explanation as possible while still preserving the predictive accuracy of the original network. We demonstrate the applicability of our method for image classification with CNNs, sentiment analysis with RNNs, and chemical property prediction with mixed CNN/RNN architectures. 1 Introduction Network interpretability remains a required feature for machine learning systems in many domains.

Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on machine learning models in the visual domain, where methods for generating and detecting such examples have been most extensively studied. We explore a variety of adversarial attack methods that apply to image-space content, real world adversarial attacks, adversarial defenses, and the transferability property of adversarial examples. We also discuss strengths and weaknesses of various methods of adversarial attack and defense. Our aim is to provide an extensive coverage of the field, furnishing the reader with an intuitive understanding of the mechanics of adversarial attack and defense mechanisms and enlarging the community of researchers studying this fundamental set of problems.