In this paper, we develop a new criterion, "insufficiently justified disparate impact" (IJDI), for assessing whether recommendations (binarized predictions) made by an algorithmic decision support tool are fair. Our novel, utility-based IJDI criterion evaluates false positive and false negative error rate imbalances, identifying statistically significant disparities between groups which are present even when adjusting for group-level differences in base rates. We describe a novel IJDI-Scan approach which can efficiently identify the intersectional subpopulations, defined across multiple observed attributes of the data, with the most significant IJDI. To evaluate IJDI-Scan's performance, we conduct experiments on both simulated and real-world data, including recidivism risk assessment and credit scoring. Further, we implement and evaluate approaches to mitigating IJDI for the detected subpopulations in these domains.

This paper presents a large-scale analysis of L2 Korean pronunciation error patterns from five different language backgrounds, Chinese, Vietnamese, Japanese, Thai, and English, by using automatic phonetic transcription. For the analysis, confusion matrices are generated for each L1, by aligning canonical phone sequences and automatically transcribed phone sequences obtained from fine-tuned Wav2Vec2 XLS-R phone recognizer. Each value in the confusion matrices is compared to capture frequent common error patterns and to specify patterns unique to a certain language background. Using the Foreign Speakers' Voice Data of Korean for Artificial Intelligence Learning dataset, common error pattern types are found to be (1) substitutions of aspirated or tense consonants with plain consonants, (2) deletions of syllable-final consonants, and (3) substitutions of diphthongs with monophthongs. On the other hand, thirty-nine patterns including (1) syllable-final /l/ substitutions with /n/ for Vietnamese and (2) /\textturnm/ insertions for Japanese are discovered as language-dependent.

Ensuring diagnostic performance of AI models before clinical use is key to the safe and successful adoption of these technologies. Studies reporting AI applied to digital pathology images for diagnostic purposes have rapidly increased in number in recent years. The aim of this work is to provide an overview of the diagnostic accuracy of AI in digital pathology images from all areas of pathology. This systematic review and meta-analysis included diagnostic accuracy studies using any type of artificial intelligence applied to whole slide images (WSIs) in any disease type. The reference standard was diagnosis through histopathological assessment and / or immunohistochemistry. Searches were conducted in PubMed, EMBASE and CENTRAL in June 2022. We identified 2976 studies, of which 100 were included in the review and 48 in the full meta-analysis. Risk of bias and concerns of applicability were assessed using the QUADAS-2 tool. Data extraction was conducted by two investigators and meta-analysis was performed using a bivariate random effects model. 100 studies were identified for inclusion, equating to over 152,000 whole slide images (WSIs) and representing many disease types. Of these, 48 studies were included in the meta-analysis. These studies reported a mean sensitivity of 96.3% (CI 94.1-97.7) and mean specificity of 93.3% (CI 90.5-95.4) for AI. There was substantial heterogeneity in study design and all 100 studies identified for inclusion had at least one area at high or unclear risk of bias. This review provides a broad overview of AI performance across applications in whole slide imaging. However, there is huge variability in study design and available performance data, with details around the conduct of the study and make up of the datasets frequently missing. Overall, AI offers good accuracy when applied to WSIs but requires more rigorous evaluation of its performance.

Machine learning (ML) models are costly to train as they can require a significant amount of data, computational resources and technical expertise. Thus, they constitute valuable intellectual property that needs protection from adversaries wanting to steal them. Ownership verification techniques allow the victims of model stealing attacks to demonstrate that a suspect model was in fact stolen from theirs. Although a number of ownership verification techniques based on watermarking or fingerprinting have been proposed, most of them fall short either in terms of security guarantees (well-equipped adversaries can evade verification) or computational cost. A fingerprinting technique, Dataset Inference (DI), has been shown to offer better robustness and efficiency than prior methods. The authors of DI provided a correctness proof for linear (suspect) models. However, in a subspace of the same setting, we prove that DI suffers from high false positives (FPs) -- it can incorrectly identify an independent model trained with non-overlapping data from the same distribution as stolen. We further prove that DI also triggers FPs in realistic, non-linear suspect models. We then confirm empirically that DI in the black-box setting leads to FPs, with high confidence. Second, we show that DI also suffers from false negatives (FNs) -- an adversary can fool DI (at the cost of incurring some accuracy loss) by regularising a stolen model's decision boundaries using adversarial training, thereby leading to an FN. To this end, we demonstrate that black-box DI fails to identify a model adversarially trained from a stolen dataset -- the setting where DI is the hardest to evade. Finally, we discuss the implications of our findings, the viability of fingerprinting-based ownership verification in general, and suggest directions for future work.

Automated decision systems are increasingly used to take consequential decisions in problems such as job hiring and loan granting with the hope of replacing subjective human decisions with objective machine learning (ML) algorithms. However, ML-based decision systems are prone to bias, which results in yet unfair decisions. Several notions of fairness have been defined in the literature to capture the different subtleties of this ethical and social concept (e.g., statistical parity, equal opportunity, etc.). Fairness requirements to be satisfied while learning models created several types of tensions among the different notions of fairness and other desirable properties such as privacy and classification accuracy. This paper surveys the commonly used fairness notions and discusses the tensions among them with privacy and accuracy. Different methods to address the fairness-accuracy trade-off (classified into four approaches, namely, pre-processing, in-processing, post-processing, and hybrid) are reviewed. The survey is consolidated with experimental analysis carried out on fairness benchmark datasets to illustrate the relationship between fairness measures and accuracy in real-world scenarios.

Graph anomaly detection (GAD) is a vital task since even a few anomalies can pose huge threats to benign users. Recent semi-supervised GAD methods, which can effectively leverage the available labels as prior knowledge, have achieved superior performances than unsupervised methods. In practice, people usually need to identify anomalies on new (sub)graphs to secure their business, but they may lack labels to train an effective detection model. One natural idea is to directly adopt a trained GAD model to the new (sub)graph for testing. However, we find that existing semi-supervised GAD methods suffer from poor generalization issue, i.e., well-trained models could not perform well on an unseen area (i.e., not accessible in training) of the same graph. It may cause great troubles. In this paper, we base on the phenomenon and propose a general and novel research problem of generalized graph anomaly detection that aims to effectively identify anomalies on both the training-domain graph and unseen testing graph to eliminate potential dangers. Nevertheless, it is a challenging task since only limited labels are available, and the normal background may differ between training and testing data. Accordingly, we propose a data augmentation method named \textit{AugAN} (\uline{Aug}mentation for \uline{A}nomaly and \uline{N}ormal distributions) to enrich training data and boost the generalizability of GAD models. Experiments verify the effectiveness of our method in improving model generalizability.

For several cancer patients, operative resection with curative intent can end up in early recurrence of the cancer. Current limitations in peri-operative cancer staging and especially intra-operative misidentification of visible metastases is likely the main reason leading to unnecessary operative interventions in the affected individuals. Here, we evaluate whether an artificial intelligence (AI) system can improve recognition of peritoneal surface metastases on routine staging laparoscopy images from patients with gastrointestinal malignancies. In a simulated setting evaluating biopsied peritoneal lesions, a prototype deep learning surgical guidance system outperformed oncologic surgeons in identifying peritoneal surface metastases. In this environment the developed AI model would have improved the identification of metastases by 5% while reducing the number of unnecessary biopsies by 28% compared to current standard practice. Evaluating non-biopsied peritoneal lesions, the findings support the possibility that the AI system could identify peritoneal surface metastases that were falsely deemed benign in clinical practice. Our findings demonstrate the technical feasibility of an AI system for intra-operative identification of peritoneal surface metastases, but require future assessment in a multi-institutional clinical setting.

Pre-trained language models based on general text enable huge success in the NLP scenario. But the intrinsical difference of linguistic patterns between general text and task-oriented dialogues makes existing pre-trained language models less useful in practice. Current dialogue pre-training methods rely on a contrastive framework and face the challenges of both selecting true positives and hard negatives. In this paper, we propose a novel dialogue pre-training model, FutureTOD, which distills future knowledge to the representation of the previous dialogue context using a self-training framework. Our intuition is that a good dialogue representation both learns local context information and predicts future information. Extensive experiments on diverse downstream dialogue tasks demonstrate the effectiveness of our model, especially the generalization, robustness, and learning discriminative dialogue representations capabilities.

Deep Neural Networks (DNNs), from AlexNet to ResNet to ChatGPT, have made revolutionary progress in recent years, and are widely used in various fields. The high performance of DNNs requires a huge amount of high-quality data, expensive computing hardware, and excellent DNN architectures that are costly to obtain. Therefore, trained DNNs are becoming valuable assets and must be considered the Intellectual Property (IP) of the legitimate owner who created them, in order to protect trained DNN models from illegal reproduction, stealing, redistribution, or abuse. Although being a new emerging and interdisciplinary field, numerous DNN model IP protection methods have been proposed. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of two mainstream DNN IP protection methods: deep watermarking and deep fingerprinting, with a proposed taxonomy. More than 190 research contributions are included in this survey, covering many aspects of Deep IP Protection: problem definition, main threats and challenges, merits and demerits of deep watermarking and deep fingerprinting methods, evaluation metrics, and performance discussion. We finish the survey by identifying promising directions for future research.

Machine learning methods are commonly evaluated and compared by their performance on data sets from public repositories. This allows for multiple methods, oftentimes several thousands, to be evaluated under identical conditions and across time. The highest ranked performance on a problem is referred to as state-of-the-art (SOTA) performance, and is used, among other things, as a reference point for publication of new methods. Using the highest-ranked performance as an estimate for SOTA is a biased estimator, giving overly optimistic results. The mechanisms at play are those of multiplicity, a topic that is well-studied in the context of multiple comparisons and multiple testing, but has, as far as the authors are aware of, been nearly absent from the discussion regarding SOTA estimates. The optimistic state-of-the-art estimate is used as a standard for evaluating new methods, and methods with substantial inferior results are easily overlooked. In this article, we provide a probability distribution for the case of multiple classifiers so that known analyses methods can be engaged and a better SOTA estimate can be provided. We demonstrate the impact of multiplicity through a simulated example with independent classifiers. We show how classifier dependency impacts the variance, but also that the impact is limited when the accuracy is high. Finally, we discuss a real-world example; a Kaggle competition from 2020.