Related papers: Attribution Methods Reveal Flaws in Fingerprint-Ba…

Machine learning (ML) models are costly to train as they can require a significant amount of data, computational resources and technical expertise. Thus, they constitute valuable intellectual property that needs protection from adversaries…

Object recognition and instance segmentation are fundamental skills in any robotic or autonomous system. Existing state-of-the-art methods are often unable to capture meaningful uncertainty in challenging or ambiguous scenes, and as such…

The success of learning-based coding techniques and the development of learning-based image coding standards, such as JPEG-AI, point towards the adoption of such solutions in different fields, including the storage of biometric data, like…

Undetected overfitting can occur when there are significant redundancies between training and validation data. We describe AVE, a new measure of training-validation redundancy for ligand-based classification problems that accounts for the…

As the size of accessible compound libraries expands to over 10 billion, the need for more efficient structure-based virtual screening methods is emerging. Different pre-screening methods have been developed for rapid screening, but there…

Feature attribution methods, which explain an individual prediction made by a model as a sum of attributions for each input feature, are an essential tool for understanding the behavior of complex deep learning models. However, ensuring…

Deep learning models for dermatological image analysis remain sensitive to acquisition variability and domain-specific visual characteristics, leading to performance degradation when deployed in clinical settings. We investigate how visual…

Denoising diffusion models have emerged as a dominant approach for image generation, however they still suffer from slow convergence in training and color shift issues in sampling. In this paper, we identify that these obstacles can be…

AI developers are releasing large language models (LLMs) under a variety of different licenses. Many of these licenses restrict the ways in which the models or their outputs may be used. This raises the question how license violations may…

Many statistical learning models hold an assumption that the training data and the future unlabeled data are drawn from the same distribution. However, this assumption is difficult to fulfill in real-world scenarios and creates barriers in…

Prediction of protein-ligand binding affinity is a major goal in drug discovery. Generally, free energy gap is calculated between two states (e.g., ligand binding and unbinding). The energy gap implicitly includes the effects of changes in…

Biases in the dataset often enable the model to achieve high performance on in-distribution data, while poorly performing on out-of-distribution data. To mitigate the detrimental effect of the bias on the networks, previous works have…

Controlling the patterns a model learns is essential to preventing reliance on irrelevant or misleading features. Such reliance on irrelevant features, often called shortcut features, has been observed across domains, including medical…

Large language models often achieve strong benchmark gains without corresponding improvements in broader capability. We hypothesize that this discrepancy arises from differences in training regimes induced by data distribution. To…

AI generative models leave implicit traces in their generated images, which are commonly referred to as model fingerprints and are exploited for source attribution. Prior methods rely on model-specific cues or synthesis artifacts, yielding…

Recent device fingerprinting approaches rely on deep learning to extract device-specific features solely from raw RF signals to identify, classify and authenticate wireless devices. One widely known issue lies in the inability of these…

Existing fingerprinting-based localization methods often require extensive data collection and struggle to generalize to new environments. In contrast to previous environment-unknown MetaLoc, we propose GenMetaLoc in this paper, which first…

If the extraction of sensor fingerprints represents nowadays an important forensic tool for sensor attribution, it has been shown recently that images coming from several sensors were more prone to generate False Positives (FP) by…

Designing 3D ligands within a target binding site is a fundamental task in drug discovery. Existing structured-based drug design methods treat all ligand atoms equally, which ignores different roles of atoms in the ligand for drug design…

In practice, and especially when training deep neural networks, visual recognition rules are often learned based on various sources of information. On the other hand, the recent deployment of facial recognition systems with uneven…