Canary exposure, introduced in Carlini et al. is frequently used to empirically evaluate, or audit, the privacy of machine learning model training. The goal of this note is to provide some intuition on how to interpret canary exposure, including by relating it to membership inference attacks and differential privacy.

Financial forecasting has been an important and active area of machine learning research, as even the most modest advantage in predictive accuracy can be parlayed into significant financial gains. Recent advances in natural language processing (NLP) bring the opportunity to leverage textual data, such as earnings reports of publicly traded companies, to predict the return rate for an asset. However, when dealing with such a sensitive task, the consistency of models -- their invariance under meaning-preserving alternations in input -- is a crucial property for building user trust. Despite this, current financial forecasting methods do not consider consistency. To address this problem, we propose FinTrust, an evaluation tool that assesses logical consistency in financial text. Using FinTrust, we show that the consistency of state-of-the-art NLP models for financial forecasting is poor. Our analysis of the performance degradation caused by meaning-preserving alternations suggests that current text-based methods are not suitable for robustly predicting market information. All resources are available at https://github.com/yingpengma/fintrust.

Labeling a large number of electronic health records is expensive and time consuming, and having a labeling assistant tool can significantly reduce medical experts' workload. Nevertheless, to gain the experts' trust, the tool must be able to explain the reasons behind its outputs. Motivated by this, we introduce Explainable Labeling Assistant (XLabel) a new visual-interactive tool for data labeling. At a high level, XLabel uses Explainable Boosting Machine (EBM) to classify the labels of each data point and visualizes heatmaps of EBM's explanations. As a case study, we use XLabel to help medical experts label electronic health records with four common non-communicable diseases (NCDs). Our experiments show that 1) XLabel helps reduce the number of labeling actions, 2) EBM as an explainable classifier is as accurate as other well-known machine learning models outperforms a rule-based model used by NCD experts, and 3) even when more than 40% of the records were intentionally mislabeled, EBM could recall the correct labels of more than 90% of these records.

Algorithmic fairness has attracted increasing attention in the machine learning community. Various definitions are proposed in the literature, but the differences and connections among them are not clearly addressed. In this paper, we review and reflect on various fairness notions previously proposed in machine learning literature, and make an attempt to draw connections to arguments in moral and political philosophy, especially theories of justice. We also consider fairness inquiries from a dynamic perspective, and further consider the long-term impact that is induced by current prediction and decision. In light of the differences in the characterized fairness, we present a flowchart that encompasses implicit assumptions and expected outcomes of different types of fairness inquiries on the data generating process, on the predicted outcome, and on the induced impact, respectively. This paper demonstrates the importance of matching the mission (which kind of fairness one would like to enforce) and the means (which spectrum of fairness analysis is of interest, what is the appropriate analyzing scheme) to fulfill the intended purpose.

As industrial applications are increasingly automated by machine learning models, enforcing personal data ownership and intellectual property rights requires tracing training data back to their rightful owners. Membership inference algorithms approach this problem by using statistical techniques to discern whether a target sample was included in a model's training set. However, existing methods only utilize the unaltered target sample or simple augmentations of the target to compute statistics. Such a sparse sampling of the model's behavior carries little information, leading to poor inference capabilities. In this work, we use adversarial tools to directly optimize for queries that are discriminative and diverse. Our improvements achieve significantly more accurate membership inference than existing methods, especially in offline scenarios and in the low false-positive regime which is critical in legal settings. Membership inference algorithms are designed to determine whether a target data point was present in the training set of a model. Membership inference is often studied in the context of ML privacy, as there are situations where belonging to a dataset is itself sensitive information (e.g. a model trained on a group of people with a rare disease).

In recent years, we have seen a significant interest in data-driven deep learning approaches for video anomaly detection, where an algorithm must determine if specific frames of a video contain abnormal behaviors. However, video anomaly detection is particularly context-specific, and the availability of representative datasets heavily limits real-world accuracy. Additionally, the metrics currently reported by most state-of-the-art methods often do not reflect how well the model will perform in real-world scenarios. In this article, we present the Charlotte Anomaly Dataset (CHAD). CHAD is a high-resolution, multi-camera anomaly dataset in a commercial parking lot setting. In addition to frame-level anomaly labels, CHAD is the first anomaly dataset to include bounding box, identity, and pose annotations for each actor. This is especially beneficial for skeleton-based anomaly detection, which is useful for its lower computational demand in real-world settings. CHAD is also the first anomaly dataset to contain multiple views of the same scene. With four camera views and over 1.15 million frames, CHAD is the largest fully annotated anomaly detection dataset including person annotations, collected from continuous video streams from stationary cameras for smart video surveillance applications. To demonstrate the efficacy of CHAD for training and evaluation, we benchmark two state-of-the-art skeleton-based anomaly detection algorithms on CHAD and provide comprehensive analysis, including both quantitative results and qualitative examination. The dataset is available at https://github.com/TeCSAR-UNCC/CHAD.

Disk scrubbing is a process aimed at resolving read errors on disks by reading data from the disk. However, scrubbing the entire storage array at once can adversely impact system performance, particularly during periods of high input/output operations. Additionally, the continuous reading of data from disks when scrubbing can result in wear and tear, especially on larger capacity disks, due to the significant time and energy consumption involved. To address these issues, we propose a selective disk scrubbing method that enhances the overall reliability and power efficiency in data centers. Our method employs a Machine Learning model based on Mondrian Conformal prediction to identify specific disks for scrubbing, by proactively predicting the health status of each disk in the storage pool, forecasting n-days in advance, and using an open-source dataset. For disks predicted as non-healthy, we mark them for replacement without further action. For healthy drives, we create a set and quantify their relative health across the entire storage pool based on the predictor's confidence. This enables us to prioritize selective scrubbing for drives with established scrubbing frequency based on the scrub cycle. The method we propose provides an efficient and dependable solution for managing enterprise disk drives. By scrubbing just 22.7% of the total storage disks, we can achieve optimized energy consumption and reduce the carbon footprint of the data center.

Transfer learning has become an increasingly popular technique in machine learning as a way to leverage a pretrained model trained for one task to assist with building a finetuned model for a related task. This paradigm has been especially popular for privacy in machine learning, where the pretrained model is considered public, and only the data for finetuning is considered sensitive. However, there are reasons to believe that the data used for pretraining is still sensitive, making it essential to understand how much information the finetuned model leaks about the pretraining data. In this work we propose a new membership-inference threat model where the adversary only has access to the finetuned model and would like to infer the membership of the pretraining data. To realize this threat model, we implement a novel metaclassifier-based attack, TMI, that leverages the influence of memorized pretraining samples on predictions in the downstream task. We evaluate TMI on both vision and natural language tasks across multiple transfer learning settings, including finetuning with differential privacy. Through our evaluation, we find that TMI can successfully infer membership of pretraining examples using query access to the finetuned model.

Artificial Intelligence (AI) has received an increasing amount of attention in multiple areas. The uncertainties and risks in AI-powered systems have created reluctance in their wild adoption. As an economic solution to compensate for potential damages, AI liability insurance is a promising market to enhance the integration of AI into daily life. In this work, we use an AI-powered E-diagnosis system as an example to study AI liability insurance. We provide a quantitative risk assessment model with evidence-based numerical analysis. We discuss the insurability criteria for AI technologies and suggest necessary adjustments to accommodate the features of AI products. We show that AI liability insurance can act as a regulatory mechanism to incentivize compliant behaviors and serve as a certificate of high-quality AI systems. Furthermore, we suggest premium adjustment to reflect the dynamic evolution of the inherent uncertainty in AI. Moral hazard problems are discussed and suggestions for AI liability insurance are provided.

The field of machine learning (ML) has witnessed significant advancements in recent years. However, many existing algorithms lack interpretability and struggle with high-dimensional and imbalanced data. This paper proposes SPINEX, a novel similarity-based interpretable neighbor exploration algorithm designed to address these limitations. This algorithm combines ensemble learning and feature interaction analysis to achieve accurate predictions and meaningful insights by quantifying each feature's contribution to predictions and identifying interactions between features, thereby enhancing the interpretability of the algorithm. To evaluate the performance of SPINEX, extensive experiments on 59 synthetic and real datasets were conducted for both regression and classification tasks. The results demonstrate that SPINEX achieves comparative performance and, in some scenarios, may outperform commonly adopted ML algorithms. The same findings demonstrate the effectiveness and competitiveness of SPINEX, making it a promising approach for various real-world applications.