Recent developments in Artificial Intelligence (AI) and their applications in critical industries such as healthcare, fin-tech and cybersecurity have led to a surge in research in explainability in AI. Innovative research methods are being explored to extract meaningful insight from blackbox AI systems to make the decision-making technology transparent and interpretable. Explainability becomes all the more critical when AI is used in decision making in domains like fintech, healthcare and safety critical systems such as cybersecurity and autonomous vehicles. However, there is still ambiguity lingering on the reliable evaluations for the users and nature of transparency in the explanations provided for the decisions made by black-boxed AI. To solve the blackbox nature of Machine Learning based Intrusion Detection Systems, a framework is proposed in this paper to give an explanation for IDSs decision making. This framework uses Local Interpretable Model-Agnostic Explanations (LIME) coupled with Explain Like I'm five (ELI5) and Decision Tree algorithms to provide local and global explanations and improve the interpretation of IDSs. The local explanations provide the justification for the decision made on a specific input. Whereas, the global explanations provides the list of significant features and their relationship with attack traffic. In addition, this framework brings transparency in the field of ML driven IDS that might be highly significant for wide scale adoption of eXplainable AI in cyber-critical systems. Our framework is able to achieve 85 percent accuracy in classifying attack behaviour on UNSW-NB15 dataset, while at the same time displaying the feature significance ranking of the top 10 features used in the classification.

Out-of-distribution (OOD) detection ensures safe and reliable model deployment. Contemporary OOD algorithms using geometry projection can detect OOD or adversarial samples from clean in-distribution (ID) samples. However, this setting regards adversarial ID samples as OOD, leading to incorrect OOD predictions. Existing efforts on OOD detection with ID and OOD data under attacks are minimal. In this paper, we develop a robust OOD detection method that distinguishes adversarial ID samples from OOD ones. The sharp loss landscape created by adversarial training hinders model convergence, impacting the latent embedding quality for OOD score calculation. Therefore, we introduce a {\bf Sharpness-aware Geometric Defense (SaGD)} framework to smooth out the rugged adversarial loss landscape in the projected latent geometry. Enhanced geometric embedding convergence enables accurate ID data characterization, benefiting OOD detection against adversarial attacks. We use Jitter-based perturbation in adversarial training to extend the defense ability against unseen attacks. Our SaGD framework significantly improves FPR and AUC over the state-of-the-art defense approaches in differentiating CIFAR-100 from six other OOD datasets under various attacks. We further examine the effects of perturbations at various adversarial training levels, revealing the relationship between the sharp loss landscape and adversarial OOD detection.

Large language model fine-tuning APIs enable widespread model customization, yet pose significant safety risks. Recent work shows that adversaries can exploit access to these APIs to bypass model safety mechanisms by encoding harmful content in seemingly harmless fine-tuning data, evading both human monitoring and standard content filters. We formalize the fine-tuning API defense problem, and introduce the Cipher Fine-tuning Robustness benchmark (CIFR), a benchmark for evaluating defense strategies' ability to retain model safety in the face of cipher-enabled attackers while achieving the desired level of fine-tuning functionality. We include diverse cipher encodings and families, with some kept exclusively in the test set to evaluate for generalization across unseen ciphers and cipher families. We then evaluate different defenses on the benchmark and train probe monitors on model internal activations from multiple fine-tunes. We show that probe monitors achieve over 99% detection accuracy, generalize to unseen cipher variants and families, and compare favorably to state-of-the-art monitoring approaches. We open-source CIFR and the code to reproduce our experiments to facilitate further research in this critical area. Code and data are available online https://github.com/JackYoustra/safe-finetuning-api

This thesis develops computational methods in similarity-preserving hashing, classification, and cancer genomics. Standard space partitioning-based hashing relies on Binary Search Trees (BSTs), but their exponential growth and sparsity hinder efficiency. To overcome this, we introduce Compressed BST of Inverted hash tables (ComBI), which enables fast approximate nearest-neighbor search with reduced memory. On datasets of up to one billion samples, ComBI achieves 0.90 precision with 4X-296X speed-ups over Multi-Index Hashing, and also outperforms Cellfishing.jl on single-cell RNA-seq searches with 2X-13X gains. Building on hashing structures, we propose Guided Random Forest (GRAF), a tree-based ensemble classifier that integrates global and local partitioning, bridging decision trees and boosting while reducing generalization error. Across 115 datasets, GRAF delivers competitive or superior accuracy, and its unsupervised variant (uGRAF) supports guided hashing and importance sampling. We show that GRAF and ComBI can be used to estimate per-sample classifiability, which enables scalable prediction of cancer patient survival. To address challenges in interpreting mutations, we introduce Continuous Representation of Codon Switches (CRCS), a deep learning framework that embeds genetic changes into numerical vectors. CRCS allows identification of somatic mutations without matched normals, discovery of driver genes, and scoring of tumor mutations, with survival prediction validated in bladder, liver, and brain cancers. Together, these methods provide efficient, scalable, and interpretable tools for large-scale data analysis and biomedical applications.

This paper investigates false positive constructions: grammatical structures which an LLM hallucinates as distinct constructions but which human introspection does not support. Both a behavioural probing task using contextual embeddings and a meta-linguistic probing task using prompts are included, allowing us to distinguish between implicit and explicit linguistic knowledge. Both methods reveal that models do indeed hallucinate constructions. We then simulate hypothesis testing to determine what would have happened if a linguist had falsely hypothesized that these hallucinated constructions do exist. The high accuracy obtained shows that such false hypotheses would have been overwhelmingly confirmed. This suggests that construction probing methods suffer from a confirmation bias and raises the issue of what unknown and incorrect syntactic knowledge these models also possess.

User-to-item retrieval has been an active research area in recommendation system, and two tower models are widely adopted due to model simplicity and serving efficiency. In this work, we focus on a variant called \textit{conditional retrieval}, where we expect retrieved items to be relevant to a condition (e.g. topic). We propose a method that uses the same training data as standard two tower models but incorporates item-side information as conditions in query. This allows us to bootstrap new conditional retrieval use cases and encourages feature interactions between user and condition. Experiments show that our method can retrieve highly relevant items and outperforms standard two tower models with filters on engagement metrics. The proposed model is deployed to power a topic-based notification feed at Pinterest and led to +0.26\% weekly active users.

Outlier detection holds significant importance in the realm of data mining, particularly with the growing pervasiveness of data acquisition methods. The ability to identify outliers in data streams is essential for maintaining data quality and detecting faults. However, dealing with data streams presents challenges due to the non-stationary nature of distributions and the ever-increasing data volume. While numerous methods have been proposed to tackle this challenge, a common drawback is the lack of straightforward parameterization in many of them. This article introduces two novel methods: DyCF and DyCG. DyCF leverages the Christoffel function from the theory of approximation and orthogonal polynomials. Conversely, DyCG capitalizes on the growth properties of the Christoffel function, eliminating the need for tuning parameters. Both approaches are firmly rooted in a well-defined algebraic framework, meeting crucial demands for data stream processing, with a specific focus on addressing low-dimensional aspects and maintaining data history without memory cost. A comprehensive comparison between DyCF, DyCG, and state-of-the-art methods is presented, using both synthetic and real industrial data streams. The results show that DyCF outperforms fine-tuning methods, offering superior performance in terms of execution time and memory usage. DyCG performs less well, but has the considerable advantage of requiring no tuning at all.

Hopfield networks using Hebbian learning suffer from limited storage capacity. While supervised methods like Linear Logistic Regression (LLR) offer some improvement, kernel methods like Kernel Logistic Regression (KLR) significantly enhance storage capacity and noise robustness. However, KLR requires computationally expensive iterative learning. We propose Kernel Ridge Regression (KRR) as an efficient kernel-based alternative for learning high-capacity Hopfield networks. KRR utilizes the kernel trick and predicts bipolar states via regression, crucially offering a non-iterative, closed-form solution for learning dual variables. We evaluate KRR and compare its performance against Hebbian, LLR, and KLR. Our results demonstrate that KRR achieves state-of-the-art storage capacity (reaching a storage load of 1.5) and noise robustness, comparable to KLR. Crucially, KRR drastically reduces training time, being orders of magnitude faster than LLR and significantly faster than KLR, especially at higher storage loads. This establishes KRR as a potent and highly efficient method for building high-performance associative memories, providing comparable performance to KLR with substantial training speed advantages. This work provides the first empirical comparison between KRR and KLR in the context of Hopfield network learning.

This paper claims that machine learning models deployed in high stakes domains such as medicine must be interpretable, shareable, reproducible and accountable. We argue that these principles should form the foundational design criteria for machine learning algorithms dealing with critical medical data, including survival analysis and risk prediction tasks. Black box models, while often highly accurate, struggle to gain trust and regulatory approval in health care due to a lack of transparency. We discuss how intrinsically interpretable modeling approaches (such as kernel methods with sparsity, prototype-based learning, and deep kernel models) can serve as powerful alternatives to opaque deep networks, providing insight into biomedical predictions. We then examine accountability in model development, calling for rigorous evaluation, fairness, and uncertainty quantification to ensure models reliably support clinical decisions. Finally, we explore how generative AI and collaborative learning paradigms (such as federated learning and diffusion-based data synthesis) enable reproducible research and cross-institutional integration of heterogeneous biomedical data without compromising privacy, hence shareability. By rethinking machine learning foundations along these axes, we can develop medical AI that is not only accurate but also transparent, trustworthy, and translatable to real-world clinical settings.

--We propose a novel unsupervised outlier detection method based on Randomized Principal Component Analysis (PCA). Inspired by the performance of Randomized PCA (RPCA) Forest in approximate K-Nearest Neighbor (KNN) search, we develop a novel unsupervised outlier detection method that utilizes RPCA Forest for outlier detection. Experimental results showcase the superiority of the proposed approach compared to the classical and state-of-the-art methods in performing the outlier detection task on several datasets while performing competitively on the rest. The extensive analysis of the proposed method reflects it high generalization power and its computational efficiency, highlighting it as a good choice for unsupervised outlier detection. An outlier, as defined by Hawkins [18], is "an observation which deviates so much from other observations as to arouse suspicions that it was generated by a different mechanism." Similarly, Barnett and Lewis [3] describe it as "an observation (or subset of observations) which appears to be inconsistent with the remainder of that set of data." Outlier detection is the process of identifying such outliers, i.e., the data points which differ from the rest of the data. It is one of the most important and fundamental tasks in data mining and machine learning with applications in intrusion detection [20], fault detection [37], fraud detection [7] and others [11], [13], [27]. In recent years, many methods have been proposed to carry out the outlier detection task [1], [9], [10], [23], [42]. Despite the demonstration of promising results, further studies show that these results might be limited only to specific instances of the problem (e.g., a limited selection of datasets, a specific kind of outliers, etc.) [6].