相关论文: White-box Testing of NLP models with Mask Neuron C…

Neural Networks (NN) have been proposed in the past as an effective means for both modeling and control of systems with very complex dynamics. However, despite the extensive research, NN-based controllers have not been adopted by the…

Machine learning has become a key tool in cybersecurity, improving both attack strategies and defense mechanisms. Deep learning models, particularly Convolutional Neural Networks (CNNs), have demonstrated high accuracy in detecting malware…

Objective The evaluation of natural language processing (NLP) models for clinical text de-identification relies on the availability of clinical notes, which is often restricted due to privacy concerns. The NLP Sandbox is an approach for…

Topic modeling aims to produce interpretable topic representations and topic--document correspondences from corpora, but classical neural topic models (NTMs) remain constrained by limited representation assumptions and semantic abstraction…

The purported "black box" nature of neural networks is a barrier to adoption in applications where interpretability is essential. Here we present DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction of…

Label smoothing loss is a widely adopted technique to mitigate overfitting in deep neural networks. This paper studies label smoothing from the perspective of Neural Collapse (NC), a powerful empirical and theoretical framework which…

Mixup~\cite{zhang2017mixup} is a recently proposed method for training deep neural networks where additional samples are generated during training by convexly combining random pairs of images and their associated labels. While simple to…

This paper deals with neural networks modelling of HVAC systems. In order to increase the neural networks performances, a method based on sensitivity analysis is applied. The same technique is also used to compute the relevance of each…

Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their internal attention mechanisms remain under-explored. This…

VQ (Vendor Qualification) and IOQ (Installation and Operation Qualification) audits are implemented in warehouses to ensure all equipment being turned over in the fulfillment network meets the quality standards. Audit checks are likely to…

Deep neural networks tend to memorize noisy labels, severely degrading their generalization performance. Although Mixup has demonstrated effectiveness in improving generalization and robustness, existing Mixup-based methods typically…

Deep Neural Networks~(DNNs) have been widely deployed in software to address various tasks~(e.g., autonomous driving, medical diagnosis). However, they could also produce incorrect behaviors that result in financial losses and even threaten…

As neural networks are increasingly used for critical decision-making tasks, the threat of integrity attacks, where an adversary maliciously alters a model, has become a significant security and safety concern. These concerns are compounded…

Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We design white-box inference attacks to perform a comprehensive privacy analysis of deep learning models. We measure…

The memorization effect of deep learning hinders its performance to effectively generalize on test set when learning with noisy labels. Prior study has discovered that epistemic uncertainty techniques are robust when trained with noisy…

The ability to remove features from the input of machine learning models is very important to understand and interpret model predictions. However, this is non-trivial for vision models since masking out parts of the input image typically…

Machine learning has been proven to be susceptible to carefully crafted samples, known as adversarial examples. The generation of these adversarial examples helps to make the models more robust and gives us an insight into the underlying…

Though black-box predictors are state-of-the-art for many complex tasks, they often fail to properly quantify predictive uncertainty and may provide inappropriate predictions for unfamiliar data. Instead, we can learn more reliable models…

In recent years, the black-box nature of deep learning models has limited their application in high-stakes domains such as medical diagnosis and finance, where interpretability is essential. To address this, we propose a novel approach…

The following work presents how autoencoding all the possible hidden activations of a network for a given problem can provide insight about its structure, behavior, and vulnerabilities. The method, termed self-introspection, can show that a…