Related papers: AdaptDel: Adaptable Deletion Rate Randomized Smoot…
Methods to certify the robustness of neural networks in the presence of input uncertainty are vital in safety-critical settings. Most certification methods in the literature are designed for adversarial input uncertainty, but researchers…
Adversarial attacks pose a significant threat to the reliability of pre-trained language models (PLMs) such as GPT, BERT, RoBERTa, and T5. This paper presents Adversarial Robustness through Dynamic Ensemble Learning (ARDEL), a novel scheme…
We investigate an application in the automatic tuning of computer codes, an area of research that has come to prominence alongside the recent rise of distributed scientific processing and heterogeneity in high-performance computing…
We propose a framework for learning calibrated uncertainties under domain shifts, where the source (training) distribution differs from the target (test) distribution. We detect such domain shifts via a differentiable density ratio…
Feature attribution methods highlight the important input tokens as explanations to model predictions, which have been widely applied to deep neural networks towards trustworthy AI. However, recent works show that explanations provided by…
Neural networks lack adversarial robustness, i.e., they are vulnerable to adversarial examples that through small perturbations to inputs cause incorrect predictions. Further, trust is undermined when models give miscalibrated predictions,…
We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially…
Gradient clipping is a standard training technique used in deep learning applications such as large-scale language modeling to mitigate exploding gradients. Recent experimental studies have demonstrated a fairly special behavior in the…
Randomized smoothing is the primary certified robustness method for accessing the robustness of deep learning models to adversarial perturbations in the l2-norm, by adding isotropic Gaussian noise to the input image and returning the…
A reliable application of deep neural network classifiers requires robustness certificates against adversarial perturbations. Gaussian smoothing is a widely analyzed approach to certifying robustness against norm-bounded perturbations,…
In response to subtle adversarial examples flipping classifications of neural network models, recent research has promoted certified robustness as a solution. There, invariance of predictions to all norm-bounded attacks is achieved through…
Software engineering activities frequently involve edits to existing code. However, contemporary code language models (LMs) lack the ability to handle diverse types of code-edit requirements. In this work, we attempt to overcome this…
Data augmentation is a widely adopted technique utilized to improve the robustness of automatic speech recognition (ASR). Employing a fixed data augmentation strategy for all training data is a common practice. However, it is important to…
Previous approaches to robustness in natural language processing usually treat deviant input by relaxing grammatical constraints whenever a successful analysis cannot be provided by ``normal'' means. This schema implies, that error…
Recently smoothing deep neural network based classifiers via isotropic Gaussian perturbation is shown to be an effective and scalable way to provide state-of-the-art probabilistic robustness guarantee against $\ell_2$ norm bounded…
Recently, more and more personalized speech enhancement systems (PSE) with excellent performance have been proposed. However, two critical issues still limit the performance and generalization ability of the model: 1) Acoustic environment…
Over the recent years, various deep learning-based methods were proposed for extracting a fixed-dimensional embedding vector from speech signals. Although the deep learning-based embedding extraction methods have shown good performance in…
Sound event detection (SED), as a core module of acoustic environmental analysis, suffers from the problem of data deficiency. The integration of semi-supervised learning (SSL) largely mitigates such problem while bringing no extra…
Randomized smoothing is a technique for providing provable robustness guarantees against adversarial attacks while making minimal assumptions about a classifier. This method relies on taking a majority vote of any base classifier over…
Science and engineering problems subject to uncertainty are frequently both computationally expensive and feature nonsmooth parameter dependence, making standard Monte Carlo too slow, and excluding efficient use of accelerated uncertainty…