Related papers: Overlearning Reveals Sensitive Attributes
We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…
As deep learning models are becoming larger and data-hungrier, there are growing ethical, legal and technical concerns over use of data: in practice, agreements on data use may change over time, rendering previously-used training data…
Training fair machine learning models, aiming for their interpretability and solving the problem of domain shift has gained a lot of interest in the last years. There is a vast amount of work addressing these topics, mostly in separation.…
Recent work suggests that convolutional neural networks of different architectures learn to classify images in the same order. To understand this phenomenon, we revisit the over-parametrized deep linear network model. Our analysis reveals…
We study the ability of foundation models to learn representations for classification that are transferable to new, unseen classes. Recent results in the literature show that representations learned by a single classifier over many classes…
Supervised learning, characterized by both discriminative and generative learning, seeks to predict the values of single (or sometimes multiple) predefined target attributes based on a predefined set of predictor attributes. For…
We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features. Assuming data about the predictor, target, and membership in the…
Deep learning has raised hopes and expectations as a general solution for many applications; indeed it has proven effective, but it also showed a strong dependence on large quantities of data. Luckily, it has been shown that, even when data…
Modern machine learning models often employ a huge number of parameters and are typically optimized to have zero training loss; yet surprisingly, they possess near-optimal prediction performance, contradicting classical learning theory. We…
Models can expose sensitive information about their training data. In an attribute inference attack, an adversary has partial knowledge of some training records and access to a model trained on those records, and infers the unknown values…
Privacy and transparency are two key foundations of trustworthy machine learning. Model explanations offer insights into a model's decisions on input data, whereas privacy is primarily concerned with protecting information about the…
Duplication is a prevalent issue within datasets. Existing research has demonstrated that the presence of duplicated data in training datasets can significantly influence both model performance and data privacy. However, the impact of data…
It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence. In this work, we take the opposite stance: an overly confident model is more likely to be vulnerable to…
Model identifiability is a desirable property in the context of unsupervised representation learning. In absence thereof, different models may be observationally indistinguishable while yielding representations that are nontrivially related…
Meta learning has demonstrated tremendous success in few-shot learning with limited supervised data. In those settings, the meta model is usually overparameterized. While the conventional statistical learning theory suggests that…
AI systems frequently exhibit and amplify social biases, leading to harmful consequences in critical areas. This study introduces a novel encoder-decoder approach that leverages model gradients to learn a feature neuron encoding societal…
A major component of overfitting in model-free reinforcement learning (RL) involves the case where the agent may mistakenly correlate reward with certain spurious features from the observations generated by the Markov Decision Process…
Identifying the causes of a model's unfairness is an important yet relatively unexplored task. We look into this problem through the lens of training data - the major source of unfairness. We ask the following questions: How would the…
It is incredibly easy for a system designer to misspecify the objective for an autonomous system ("robot''), thus motivating the desire to have the robot learn the objective from human behavior instead. Recent work has suggested that people…
Machine unlearning enables models to selectively forget training data, driven by privacy regulations such as GDPR and CCPA. However, its fairness implications remain underexplored: when a model forgets a demographic group, does it…