Related papers: BriarPatches: Pixel-Space Interventions for Induci…
The classification of time-series data is pivotal for streaming data and comes with many challenges. Although the amount of publicly available datasets increases rapidly, deep neural models are only exploited in a few areas. Traditional…
Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, much of this…
As learning-to-rank models are increasingly deployed for decision-making in areas with profound life implications, the FairML community has been developing fair learning-to-rank (LTR) models. These models rely on the availability of…
Image patch matching, which is the process of identifying corresponding patches across images, has been used as a subroutine for many computer vision and image processing tasks. State -of-the-art patch matching techniques take image patches…
Biases inherent in both data and algorithms make the fairness of widespread machine learning (ML)-based decision-making systems less than optimal. To improve the trustfulness of such ML decision systems, it is crucial to be aware of the…
Ensuring fairness in deep-learning-based segmentors is crucial for health equity. Much effort has been dedicated to mitigating unfairness in the training datasets or procedures. However, with the increasing prevalence of foundation models…
Ensuring fairness in Graph Neural Networks is fundamental to promoting trustworthy and socially responsible machine learning systems. In response, numerous fair graph learning methods have been proposed in recent years. However, most of…
Mechanistic interpretability aims to understand model behaviors in terms of specific, interpretable features, often hypothesized to manifest as low-dimensional subspaces of activations. Specifically, recent studies have explored subspace…
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…
Algorithmic fairness is becoming increasingly important in data mining and machine learning. Among others, a foundational notation is group fairness. The vast majority of the existing works on group fairness, with a few exceptions,…
Representation learning algorithms offer the opportunity to learn invariant representations of the input data with regard to nuisance factors. Many authors have leveraged such strategies to learn fair representations, i.e., vectors where…
Predictive algorithms have a powerful potential to offer benefits in areas as varied as medicine or education. However, these algorithms and the data they use are built by humans, consequently, they can inherit the bias and prejudices…
In contrast to human vision, common recognition algorithms often fail on partially occluded images. We propose characterizing, empirically, the algorithmic limits by finding a minimal recognizable patch (MRP) that is by itself sufficient to…
Deep neural networks are successfully used in various applications, but show their vulnerability to adversarial examples. With the development of adversarial patches, the feasibility of attacks in physical scenes increases, and the defenses…
Spectral clustering is popular among practitioners and theoreticians alike. While performance guarantees for spectral clustering are well understood, recent studies have focused on enforcing ``fairness'' in clusters, requiring them to be…
Deep neural networks (DNNs) have been showed to be highly vulnerable to imperceptible adversarial perturbations. As a complementary type of adversary, patch attacks that introduce perceptible perturbations to the images have attracted the…
The development of fair and unbiased machine learning models remains an ongoing objective for researchers in the field of artificial intelligence. We introduce the Differential Adjusted Parity (DAP) loss to produce unbiased informative…
Despite modifying only a small localized input region, adversarial patches can drastically change the prediction of computer vision models. However, prior methods either cannot perform satisfactorily under targeted attack scenarios or fail…
Predictive uncertainties in classification tasks are often a consequence of model inadequacy or insufficient training data. In popular applications, such as image processing, we are often required to scrutinise these uncertainties by…
Artificial Intelligence-generated content has become increasingly popular, yet its malicious use, particularly the deepfakes, poses a serious threat to public trust and discourse. While deepfake detection methods achieve high predictive…