Related papers: Corruptions of Supervised Learning Problems: Typol…
This systematic literature review examines the role of machine learning in fraud detection within digital banking, synthesizing evidence from 118 peer-reviewed studies and institutional reports. Following the PRISMA guidelines, the review…
Large language models (LLMs) are increasingly exposed to data contamination, i.e., performance gains driven by prior exposure of test datasets rather than generalization. However, in the context of tabular data, this problem is largely…
Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier. In this work, we present a unifying view of randomized…
While large language models have achieved remarkable performance on various code generation benchmarks, there have been growing concerns regarding potential contamination of these benchmarks as they may be leaked into pretraining and…
A large body of work shows that machine learning (ML) models can leak sensitive or confidential information about their training data. Recently, leakage due to distribution inference (or property inference) attacks is gaining attention. In…
We study how networking corruptions--data corruptions caused by networking errors--affect video machine learning (ML) models. We discover apparent networking corruptions in Kinetics-400, a benchmark video ML dataset. In a simulation study,…
Fair machine learning research has been primarily concerned with classification tasks that result in discrimination. However, as machine learning algorithms are applied in new contexts the harms and injustices that result are qualitatively…
As Large Language Models (LLMs) scale in size and complexity, the consequences of failures during training become increasingly severe. A major challenge arises from Silent Data Corruption (SDC): hardware-induced faults that bypass…
The classification of crime into discrete categories entails a massive loss of information. Crimes emerge out of a complex mix of behaviors and situations, yet most of these details cannot be captured by singular crime type labels. This…
Weakly supervised learning has emerged as a practical alternative to fully supervised learning when complete and accurate labels are costly or infeasible to acquire. However, many existing methods are tailored to specific supervision…
In many large-scale classification problems, classes are organized in a known hierarchy, typically represented as a tree expressing the inclusion of classes in superclasses. We introduce a loss for this type of supervised hierarchical…
Developing a reliable vision system is a fundamental challenge for robotic technologies (e.g., indoor service robots and outdoor autonomous robots) which can ensure reliable navigation even in challenging environments such as adverse…
We introduce a unified probabilistic framework for solving sequential decision making problems ranging from Bayesian optimisation to contextual bandits and reinforcement learning. This is accomplished by a probabilistic model-based approach…
This paper provides the first systematic analysis of a synergistic threat model encompassing memory corruption vulnerabilities and microarchitectural side-channel vulnerabilities. We study speculative shield bypass attacks that leverage…
Complementary-label learning is a weakly supervised learning problem in which each training example is associated with one or multiple complementary labels indicating the classes to which it does not belong. Existing consistent approaches…
Scalable oversight studies methods of training and evaluating AI systems in domains where human judgment is unreliable or expensive, such as scientific research and software engineering in complex codebases. Most work in this area has…
Self-supervised contrastive representation learning has proved incredibly successful in the vision and natural language domains, enabling state-of-the-art performance with orders of magnitude less labeled data. However, such methods are…
Semi-supervised learning is a setting in which one has labeled and unlabeled data available. In this survey we explore different types of theoretical results when one uses unlabeled data in classification and regression tasks. Most methods…
One of the most important problems in regression-based error model is modeling the complex representation error caused by various corruptions and environment changes in images. For example, in robust face recognition, images are often…
Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a…