Related papers: Multi-head Ensemble of Smoothed Classifiers for Ce…
Improving distant speech recognition is a crucial step towards flexible human-machine interfaces. Current technology, however, still exhibits a lack of robustness, especially when adverse acoustic conditions are met. Despite the significant…
Most recent self-supervised learning methods learn visual representation by contrasting different augmented views of images. Compared with supervised learning, more aggressive augmentations have been introduced to further improve the…
Deep neural network ensembles hold the potential of improving generalization performance for complex learning tasks. This paper presents formal analysis and empirical evaluation to show that heterogeneous deep ensembles with high ensemble…
Randomized smoothing is a powerful tool for certifying robustness to adversarial perturbations, including poisoning attacks via randomized training and evasion attacks via randomized inference. Extending these guarantees to backdoor…
Training foundation models on extensive datasets and then finetuning them on specific tasks has emerged as the mainstream approach in artificial intelligence. However, the model robustness, which is a critical aspect for safety, is often…
Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to adversarial attacks, which have brought great concerns when…
We propose an algorithm to enhance certified robustness of a deep model ensemble by optimally weighting each base model. Unlike previous works on using ensembles to empirically improve robustness, our algorithm is based on optimizing a…
By driving models to converge to flat minima, sharpness-aware learning algorithms (such as SAM) have shown the power to achieve state-of-the-art performances. However, these algorithms will generally incur one extra forward-backward…
Spectral Clustering is a popular technique to split data points into groups, especially for complex datasets. The algorithms in the Spectral Clustering family typically consist of multiple separate stages (such as similarity matrix…
News recommendation is crucial for facilitating individuals' access to articles, particularly amid the increasingly digital landscape of news consumption. Consequently, extensive research is dedicated to News Recommender Systems (NRS) with…
Randomized Smoothing (RS) is considered the state-of-the-art approach to obtain certifiably robust models for challenging tasks. However, current RS approaches drastically decrease standard accuracy on unperturbed data, severely limiting…
Deep Learning, particularly Convolutional Neural Networks (CNN), has been successful in computer vision tasks and medical image analysis. However, modern CNNs can be overconfident, making them difficult to deploy in real-world scenarios.…
There are inevitably many mislabeled data in real-world datasets. Because deep neural networks (DNNs) have an enormous capacity to memorize noisy labels, a robust training scheme is required to prevent labeling errors from degrading the…
Randomized Smoothing (RS) is currently a scalable certified defense method providing robustness certification against adversarial examples. Although significant progress has been achieved in providing defenses against $\ell_p$ adversaries,…
Distantly-Supervised Named Entity Recognition (DS-NER) effectively alleviates the data scarcity problem in NER by automatically generating training samples. Unfortunately, the distant supervision may induce noisy labels, thus undermining…
Randomized smoothing provides strong, model-agnostic robustness certificates, but existing guarantees are limited to single modalities, treating continuous and discrete inputs in isolation. This limitation becomes critical in multimodal…
Randomized smoothing is considered to be the state-of-the-art provable defense against adversarial perturbations. However, it heavily exploits the fact that classifiers map input objects to class probabilities and do not focus on the ones…
We propose Adaptive Randomized Smoothing (ARS) to certify the predictions of our test-time adaptive models against adversarial examples. ARS extends the analysis of randomized smoothing using $f$-Differential Privacy to certify the adaptive…
We introduce a methodology for designing and training deep neural networks (DNN) that we call "Deep Regression Ensembles" (DRE). It bridges the gap between DNN and two-layer neural networks trained with random feature regression. Each layer…
While prior research has proposed a plethora of methods that build neural classifiers robust against adversarial robustness, practitioners are still reluctant to adopt them due to their unacceptably severe clean accuracy penalties. This…