While deep learning has revolutionized computer-aided drug discovery, the AI community has predominantly focused on model innovation and placed less emphasis on establishing best benchmarking practices. We posit that without a sound model evaluation framework, the AI community's efforts cannot reach their full potential, thereby slowing the progress and transfer of innovation into real-world drug discovery. Thus, in this paper, we seek to establish a new gold standard for small molecule drug discovery benchmarking, WelQrate. Specifically, our contributions are threefold: WelQrate Dataset Collection - we introduce a meticulously curated collection of 9 datasets spanning 5 therapeutic target classes. Our hierarchical curation pipelines, designed by drug discovery experts, go beyond the primary high-throughput screen by leveraging additional confirmatory and counter screens along with rigorous domain-driven preprocessing, such as Pan-Assay Interference Compounds (PAINS) filtering, to ensure the high-quality data in the datasets; WelQrate Evaluation Framework - we propose a standardized model evaluation framework considering high-quality datasets, featurization, 3D conformation generation, evaluation metrics, and data splits, which provides a reliable benchmarking for drug discovery experts conducting real-world virtual screening; Benchmarking - we evaluate model performance through various research questions using the WelQrate dataset collection, exploring the effects of different models, dataset quality, featurization methods, and data splitting strategies on the results. In summary, we recommend adopting our proposed WelQrate as the gold standard in small molecule drug discovery benchmarking. The WelQrate dataset collection, along with the curation codes, and experimental scripts are all publicly available at WelQrate.org.

Disaggregated evaluation -- estimation of performance of a machine learning model on different subpopulations -- is a core task when assessing performance and group-fairness of AI systems. A key challenge is that evaluation data is scarce, and subpopulations arising from intersections of attributes (e.g., race, sex, age) are often tiny. Today, it is common for multiple clients to procure the same AI model from a model developer, and the task of disaggregated evaluation is faced by each customer individually. This gives rise to what we call the multi-task disaggregated evaluation problem, wherein multiple clients seek to conduct a disaggregated evaluation of a given model in their own data setting (task). In this work we develop a disaggregated evaluation method called SureMap that has high estimation accuracy for both multi-task and single-task disaggregated evaluations of blackbox models. SureMap's efficiency gains come from (1) transforming the problem into structured simultaneous Gaussian mean estimation and (2) incorporating external data, e.g., from the AI system creator or from their other clients. Our method combines maximum a posteriori (MAP) estimation using a well-chosen prior together with cross-validation-free tuning via Stein's unbiased risk estimate (SURE). We evaluate SureMap on disaggregated evaluation tasks in multiple domains, observing significant accuracy improvements over several strong competitors.

Predicting stroke risk is a complex challenge that can be enhanced by integrating diverse clinically available data modalities. This study introduces a self-supervised multimodal framework that combines 3D brain imaging, clinical data, and image-derived features to improve stroke risk prediction prior to onset. By leveraging large unannotated clinical datasets, the framework captures complementary and synergistic information across image and tabular data modalities. Our approach is based on a contrastive learning framework that couples contrastive language-image pretraining with an image-tabular matching module, to better align multimodal data representations in a shared latent space. The model is trained on the UK Biobank, which includes structural brain MRI and clinical data. We benchmark its performance against state-of-the-art unimodal and multimodal methods using tabular, image, and image-tabular combinations under diverse frozen and trainable model settings. The proposed model outperformed self-supervised tabular (image) methods by 2.6% (2.6%) in ROC-AUC and by 3.3% (5.6%) in balanced accuracy. Additionally, it showed a 7.6% increase in balanced accuracy compared to the best multimodal supervised model. Through interpretable tools, our approach demonstrated better integration of tabular and image data, providing richer and more aligned embeddings. Gradient-weighted Class Activation Mapping heatmaps further revealed activated brain regions commonly associated in the literature with brain aging, stroke risk, and clinical outcomes. This robust self-supervised multimodal framework surpasses state-of-the-art methods for stroke risk prediction and offers a strong foundation for future studies integrating diverse data modalities to advance clinical predictive modelling.

Visual prompting (VP) is a new technique that adapts well-trained frozen models for source domain tasks to target domain tasks. This study examines VP's benefits for black-box model-level backdoor detection. The visual prompt in VP maps class subspaces between source and target domains. We identify a misalignment, termed class subspace inconsistency, between clean and poisoned datasets. Deep neural networks (DNNs) are commonly used in complex applications but require extensive computational power, leading to significant costs. However, DNNs can include backdoors (Gu et al., 2017; Liu et al., 2018b; Tang et al., 2021; Qi et al., 2023b; Nguyen & Tran, 2021; Chen et al., 2017), which manipulate model responses to inputs with specific triggers (like certain pixel patterns) while functioning correctly on other inputs. In backdoor attacks, attackers embed these triggers in the training data, leading the model to associate the trigger with a particular outcome and misclassify inputs containing it. Black-box backdoor detection, which uses only blackbox queries to the suspicious model (i.e., the model to be inspected), is gaining attention.

In this paper, we address the critical need for interpretable and uncertainty-aware machine learning models in the context of online learning for high-risk industries, particularly cyber-security. While deep learning and other complex models have demonstrated impressive predictive capabilities, their opacity and lack of uncertainty quantification present significant questions about their trustworthiness. We propose a novel pipeline for online supervised learning problems in cyber-security, that harnesses the inherent interpretability and uncertainty awareness of Additive Gaussian Processes (AGPs) models. Our approach aims to balance predictive performance with transparency while improving the scalability of AGPs, which represents their main drawback, potentially enabling security analysts to better validate threat detection, troubleshoot and reduce false positives, and generally make trustworthy, informed decisions. This work contributes to the growing field of interpretable AI by proposing a class of models that can be significantly beneficial for high-stake decision problems such as the ones typical of the cyber-security domain. The source code is available.

Embedding-as-a-Service (EaaS) has emerged as a successful business pattern but faces significant challenges related to various forms of copyright infringement, including API misuse and different attacks. Various studies have proposed backdoor-based watermarking schemes to protect the copyright of EaaS services. In this paper, we reveal that previous watermarking schemes possess semantic-independent characteristics and propose the Semantic Perturbation Attack (SPA). Our theoretical and experimental analyses demonstrate that this semantic-independent nature makes current watermarking schemes vulnerable to adaptive attacks that exploit semantic perturbations test to bypass watermark verification. To address this vulnerability, we propose the Semantic Aware Watermarking (SAW) scheme, a robust defense mechanism designed to resist SPA, by injecting a watermark that adapts to the text semantics. Extensive experimental results across multiple datasets demonstrate that the True Positive Rate (TPR) for detecting watermarked samples under SPA can reach up to more than 95%, rendering previous watermarks ineffective. Meanwhile, our watermarking scheme can resist such attack while ensuring the watermark verification capability. Our code is available at https://github.com/Zk4-ps/EaaS-Embedding-Watermark.

Protein language models (PLMs) have demonstrated remarkable success in protein modeling and design, yet their internal mechanisms for predicting structure and function remain poorly understood. Here we present a systematic approach to extract and analyze interpretable features from PLMs using sparse autoencoders (SAEs). By training SAEs on embeddings from the PLM ESM-2, we identify up to 2,548 human-interpretable latent features per layer that strongly correlate with up to 143 known biological concepts such as binding sites, structural motifs, and functional domains. In contrast, examining individual neurons in ESM-2 reveals up to 46 neurons per layer with clear conceptual alignment across 15 known concepts, suggesting that PLMs represent most concepts in superposition. Beyond capturing known annotations, we show that ESM-2 learns coherent concepts that do not map onto existing annotations and propose a pipeline using language models to automatically interpret novel latent features learned by the SAEs. As practical applications, we demonstrate how these latent features can fill in missing annotations in protein databases and enable targeted steering of protein sequence generation. Our results demonstrate that PLMs encode rich, interpretable representations of protein biology and we propose a systematic framework to extract and analyze these latent features. In the process, we recover both known biology and potentially new protein motifs. As community resources, we introduce InterPLM (interPLM.ai), an interactive visualization platform for exploring and analyzing learned PLM features, and release code for training and analysis at github.com/ElanaPearl/interPLM.

Machine learning (ML) models are valuable tools for analyzing the impact of technology using patent citation information. However, existing ML-based methods often struggle to account for the dynamic nature of the technology impact over time and the interdependencies of these impacts across different periods. This study proposes a multi-task learning (MTL) approach to enhance the prediction of technology impact across various time frames by leveraging knowledge sharing and simultaneously monitoring the evolution of technology impact. First, we quantify the technology impacts and identify patterns through citation analysis over distinct time periods. Next, we develop MTL models to predict citation counts using multiple patent indicators over time. Finally, we examine the changes in key input indicators and their patterns over different periods using the SHapley Additive exPlanation method. We also offer guidelines for validating and interpreting the results by employing statistical methods and natural language processing techniques. A case study on battery technologies demonstrates that our approach not only deepens the understanding of 1 technology impact, but also improves prediction accuracy, yielding valuable insights for both academia and industry.

Differential privacy (DP) [13] has become a widely adopted standard for quantifying privacy of algorithms that process statistical data. In simple terms, differential privacy bounds the influence a single data-point may have on the outcome probabilities. Being a statistical property, the design of differentially private algorithms involves a pen-and-paper analysis of any randomness internal to the processing that obscures the influence a data-point might have on its output. A clear understanding of the nature of differential privacy notions is therefore tantamount to study and design of privacy-preserving algorithms. Throughout its exploration, various functional interpretations of the concept of differential privacy have emerged over the years. These include the privacy-profile curve δ(ϵ) [5] that traces the (ϵ, δ)-DP point guarantees, the f-DP [11] view of worst-case trade-off curve between type I and type II errors for hypothesis testing membership [19, 6], the Rényi DP [23] function of order q that admits a natural analytical composition [1, 23], the view of the privacy loss distribution (PLD) [29] that allows for approximate numerical composition [20, 18], and the recent characteristic function formulation of the dominating privacy loss random variables Zhu et al. [32]. Each of these formalisms have their own properties and use-cases, and none of them seem to be superior in all aspects. Regardless of their differences, they all have some shared difficulties--certain types of manipulations on them are harder to perform in the time-domain, but considerably simpler to do in the frequency-domain. For instance, Koskela et al. [20] noted that composing PLDs of two mechanisms involve convolving their probability densities, which can be numerically approximated efficiently

Ensuring fairness has emerged as one of the primary concerns in AI and its related algorithms. Over time, the field of machine learning fairness has evolved to address these issues. This paper provides an extensive overview of this field and introduces two formal frameworks to tackle open questions in machine learning fairness. In one framework, operator-valued optimisation and min-max objectives are employed to address unfairness in time-series problems. This approach showcases state-of-the-art performance on the notorious COMPAS benchmark dataset, demonstrating its effectiveness in real-world scenarios. In the second framework, the challenge of lacking sensitive attributes, such as gender and race, in commonly used datasets is addressed. This issue is particularly pressing because existing algorithms in this field predominantly rely on the availability or estimations of such attributes to assess and mitigate unfairness. Here, a framework for a group-blind bias-repair is introduced, aiming to mitigate bias without relying on sensitive attributes. The efficacy of this approach is showcased through analyses conducted on the Adult Census Income dataset. Additionally, detailed algorithmic analyses for both frameworks are provided, accompanied by convergence guarantees, ensuring the robustness and reliability of the proposed methodologies.