Related papers: Overlearning Reveals Sensitive Attributes
A large body of research in machine learning is concerned with supervised learning from examples. The examples are typically represented as vectors in a multi-dimensional feature space (also known as attribute-value descriptions). A teacher…
Sensitive attributes are legally protected characteristics that should not be used to discriminate. Careful steps have been taken to minimize the risk of human bias regarding these fields, such as race and age. Large language models (LLMs)…
Machine unlearning has become a promising solution for fulfilling the "right to be forgotten", under which individuals can request the deletion of their data from machine learning models. However, existing studies of machine unlearning…
These days, deep learning models have achieved great success in multiple fields, from autonomous driving to medical diagnosis. These models have expanded the abilities of artificial intelligence by offering great solutions to complex…
A key goal of unsupervised representation learning is "inverting" a data generating process to recover its latent properties. Existing work that provably achieves this goal relies on strong assumptions on relationships between the latent…
Active learning is a powerful tool when labelling data is expensive, but it introduces a bias because the training data no longer follows the population distribution. We formalize this bias and investigate the situations in which it can be…
Deep Learning models have achieved remarkable success. Training them is often accelerated by building on top of pre-trained models which poses the risk of perpetuating encoded biases. Here, we investigate biases in the representations of…
Machine Learning models increasingly face data integrity challenges due to the use of large-scale training datasets drawn from the Internet. We study what model developers can do if they detect that some data was manipulated or incorrect.…
Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety. Existing machine unlearning methods…
Research in social psychology has shown that people's biased, subjective judgments about another's personality based solely on their appearance are not predictive of their actual personality traits. But researchers and companies often…
Models can fail in unpredictable ways during deployment due to task ambiguity, when multiple behaviors are consistent with the provided training data. An example is an object classifier trained on red squares and blue circles: when…
Deep neural networks are efficient at learning the data distribution if it is sufficiently sampled. However, they can be strongly biased by non-relevant factors implicitly incorporated in the training data. These include operational biases,…
Deep neural networks are widely used prediction algorithms whose performance often improves as the number of weights increases, leading to over-parametrization. We consider a two-layered neural network whose first layer is frozen while the…
Deep neural networks are often seen as different from other model classes by defying conventional notions of generalization. Popular examples of anomalous generalization behaviour include benign overfitting, double descent, and the success…
Subliminal learning describes a student language model inheriting a behavioral bias by fine-tuning on seemingly innocuous data generated by a biased teacher model. Prior work has begun to characterize this phenomenon but leaves open…
Probing or fine-tuning (large-scale) pre-trained models results in state-of-the-art performance for many NLP tasks and, more recently, even for computer vision tasks when combined with image data. Unfortunately, these approaches also entail…
Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its restrictive assumptions make it unsuitable for LLMs, giving…
Bias in AI/ML-based systems is a ubiquitous problem and bias in AI/ML systems may negatively impact society. There are many reasons behind a system being biased. The bias can be due to the algorithm we are using for our problem or may be…
Removing information from a machine learning model is a non-trivial task that requires to partially revert the training process. This task is unavoidable when sensitive data, such as credit card numbers or passwords, accidentally enter the…
In a world increasingly reliant on artificial intelligence, it is more important than ever to consider the ethical implications of artificial intelligence on humanity. One key under-explored challenge is labeler bias, which can create…