Related papers: Credit Attribution and Stable Compression

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…

Cooperative decentralized learning relies on direct information exchange between communicating agents, each with access to locally available datasets. The goal is to agree on model parameters that are optimal over all data. However, sharing…

Private machine learning involves addition of noise while training, resulting in lower accuracy. Intuitively, greater stability can imply greater privacy and improve this privacy-utility tradeoff. We study this role of stability in private…

Differential privacy has emerged as the most studied framework for privacy-preserving machine learning. However, recent studies show that enforcing differential privacy guarantees can not only significantly degrade the utility of the model,…

Machine unlearning (MU) addresses privacy risks in pretrained models. The main goal of MU is to remove the influence of designated data while preserving the utility of retained knowledge. Achieving this goal requires preserving semantic…

Instance-dependent cost-sensitive (IDCS) classifiers offer a promising approach to improving cost-efficiency in credit scoring by tailoring loss functions to instance-specific costs. However, the impact of such loss functions on the…

We address nonconvex learning problems over undirected networks. In particular, we focus on the challenge of designing an algorithm that is both communication-efficient and that guarantees the privacy of the agents' data. The first goal is…

When the target of statistical inference is chosen in a data-driven manner, the guarantees provided by classical theories vanish. We propose a solution to the problem of inference after selection by building on the framework of algorithmic…

Differential privacy is the state-of-the-art definition for privacy, guaranteeing that any analysis performed on a sensitive dataset leaks no information about the individuals whose data are contained therein. In this thesis, we develop…

As algorithms increasingly inform and influence decisions made about individuals, it becomes increasingly important to address concerns that these algorithms might be discriminatory. The output of an algorithm can be discriminatory for many…

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…

The ability to transfer knowledge to novel environments and tasks is a sensible desiderata for general learning agents. Despite the apparent promises, transfer in RL is still an open and little exploited research area. In this paper, we…

Feature attribution analysis is critical for interpreting machine learning models and supporting reliable data-driven decisions. However, feature attribution measures often exhibit stochastic variation: different train--test splits, random…

The field of explainable artificial intelligence (XAI) attempts to develop methods that provide insight into how complicated machine learning methods make predictions. Many methods of explanation have focused on the concept of feature…

The class activation mapping, or CAM, has been the cornerstone of feature attribution methods for multiple vision tasks. Its simplicity and effectiveness have led to wide applications in the explanation of visual predictions and…

When applying differential privacy to sensitive data, we can often improve performance using external information such as other sensitive data, public data, or human priors. We propose to use the learning-augmented algorithms (or algorithms…

Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact it pertains to. Continuously updated artificial intelligence systems violate this core…

Post-hoc attribution methods aim to explain deep learning predictions by highlighting influential input pixels. However, these explanations are highly non-robust: small, imperceptible input perturbations can drastically alter the…

Attribution maps are one of the most established tools to explain the functioning of computer vision models. They assign importance scores to input features, indicating how relevant each feature is for the prediction of a deep neural…

Prediction sets capture uncertainty by predicting sets of labels rather than individual labels, enabling downstream decisions to conservatively account for all plausible outcomes. Conformal inference algorithms construct prediction sets…