Related papers: $\texttt{dattri}$: A Library for Efficient Data At…
Attribution methods provide an insight into the decision-making process of machine learning models, especially deep neural networks, by assigning contribution scores to each individual feature. However, the attribution problem has not been…
Explaining the decisions of an Artificial Intelligence (AI) model is increasingly critical in many real-world, high-stake applications. Hundreds of papers have either proposed new feature attribution methods, discussed or harnessed these…
Data Attribution (DA) methods quantify the influence of individual training data points on model outputs and have broad applications such as explainability, data selection, and noisy label identification. However, existing DA methods are…
Advanced Persistent Threat (APT) attribution is a critical challenge in cybersecurity and implies the process of accurately identifying the perpetrators behind sophisticated cyber attacks. It can significantly enhance defense mechanisms and…
Research in Explainable Artificial Intelligence (XAI) is increasing, aiming to make deep learning models more transparent. Most XAI methods focus on justifying the decisions made by Artificial Intelligence (AI) systems in security-relevant…
Training data attribution (TDA) methods aim to quantify the influence of individual training data points on the model predictions, with broad applications in data-centric AI, such as mislabel detection, data selection, and copyright…
As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors, particularly unintended ones. Training Data Attribution (TDA) methods address this by…
This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed the most to the…
Attribution methods compute importance scores for input features to explain model predictions. However, assessing the faithfulness of these methods remains challenging due to the absence of attribution ground truth to model predictions. In…
Performance attribution analysis, defined as the process of explaining the drivers of the excess performance of an investment portfolio against a benchmark, stands as a significant feature of portfolio management and plays a crucial role in…
Data attribution methods play a crucial role in understanding machine learning models, providing insight into which training data points are most responsible for model outputs during deployment. However, current state-of-the-art approaches…
Machine unlearning -- efficiently removing the effect of a small "forget set" of training data on a pre-trained machine learning model -- has recently attracted significant research interest. Despite this interest, however, recent work…
Ensuring the trustworthiness and interpretability of machine learning models is critical to their deployment in real-world applications. Feature attribution methods have gained significant attention, which provide local explanations of…
Attribution of cyber-attacks remains a complex but critical challenge for cyber defenders. Currently, manual extraction of behavioral indicators from dense forensic documentation causes significant attribution delays, especially following…
The goal of data attribution is to trace model predictions back to training data. Despite a long line of work towards this goal, existing approaches to data attribution tend to force users to choose between computational tractability and…
The goal of data attribution for text-to-image models is to identify the training images that most influence the generation of a new image. Influence is defined such that, for a given output, if a model is retrained from scratch without the…
Trajectory-based data attribution methods estimate the influence of training samples on model predictions by unrolling the training trajectory. They are widely used in applications such as data selection, data valuation, and model…
This report investigates Training Data Attribution (TDA) and its potential importance to and tractability for reducing extreme risks from AI. First, we discuss the plausibility and amount of effort it would take to bring existing TDA…
In this paper we introduce a novel, unified, open-source model interpretability library for PyTorch [12]. The library contains generic implementations of a number of gradient and perturbation-based attribution algorithms, also known as…
AI coding assistants have transformed software development, raising questions about transparency and attribution practices. We examine the "AI attribution paradox": how developers strategically balance acknowledging AI assistance with…