相关论文: Avoiding Leakage Poisoning: Concept Interventions …

Machine learning accelerates molecular property prediction, yet state-of-the-art Large Language Models and Graph Neural Networks operate as black boxes. In drug discovery, where safety is critical, this opacity risks masking false…

Deep learning algorithms have recently gained significant attention due to their impressive performance. However, their high complexity and un-interpretable mode of operation hinders their confident deployment in real-world safety-critical…

In many real-world applications, from robotics to pedestrian trajectory prediction, there is a need to predict multiple real-valued outputs to represent several potential scenarios. Current deep learning techniques to address…

Concept Bottleneck Models (CBNMs) are deep learning models that provide interpretability by enforcing a bottleneck layer where predictions are based exclusively on human-understandable concepts. However, this constraint also restricts…

This paper proposes a novel out-of-distribution (OOD) detection framework named MoodCat for image classifiers. MoodCat masks a random portion of the input image and uses a generative model to synthesize the masked image to a new image…

Out-of-distribution (OOD) detection is essential for deploying deep learning models in open-world environments. Existing approaches, such as energy-based scoring and gradient-projection methods, typically rely on high-dimensional…

We propose a metric -- Projection Norm -- to predict a model's performance on out-of-distribution (OOD) data without access to ground truth labels. Projection Norm first uses model predictions to pseudo-label test samples and then trains a…

Machine learning is a vital part of many real-world systems, but several concerns remain about the lack of interpretability, explainability and robustness of black-box AI systems. Concept Bottleneck Models (CBM) address some of these…

Overconfident predictions on out-of-distribution (OOD) samples is a thorny issue for deep neural networks. The key to resolve the OOD overconfidence issue inherently is to build a subset of OOD samples and then suppress predictions on them.…

Out-of-distribution (OOD) detection is essential in autonomous driving, to determine when learning-based components encounter unexpected inputs. Traditional detectors typically use encoder models with fixed settings, thus lacking effective…

Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability…

Out-of-distribution detection is an important capability that has long eluded vanilla neural networks. Deep Neural networks (DNNs) tend to generate over-confident predictions when presented with inputs that are significantly…

Recent large vision-language models such as CLIP have shown remarkable out-of-distribution (OOD) detection and generalization performance. However, their zero-shot in-distribution (ID) accuracy is often limited for downstream datasets.…

In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate…

Large language models (LLMs) are often fine-tuned on uncurated text datasets that adversaries can poison. Existing poisoning attacks primarily rely on fixed trigger phrases that defenses such as outlier detection, clean-data regularization,…

Out-of-distribution (OOD) detection aims to discern outliers from the intended data distribution, which is crucial to maintaining high reliability and a good user experience. Most recent studies in OOD detection utilize the information from…

Out-of-distribution (OOD) detection is critical for ensuring the reliability of deep learning systems, particularly in safety-critical applications. Likelihood-based deep generative models have historically faced criticism for their…

Concept Bottleneck Models (CBMs) ground predictions in human-understandable concepts but face fundamental limitations: the absence of a metric to pre-evaluate concept relevance, the "linearity problem" causing recent CBMs to bypass the…

CDD, or Contamination Detection via output Distribution, identifies data contamination by measuring the peakedness of a model's sampled outputs. We study the conditions under which this approach succeeds and fails on small language models…

In vision classification, generating inputs that elicit confident predictions is key to understanding model behavior and reliability, especially under adversarial or out-of-distribution (OOD) conditions. While traditional adversarial…