Related papers: Understanding the Interaction of Adversarial Train…
This paper addresses the tradeoff between standard accuracy on clean examples and robustness against adversarial examples in deep neural networks (DNNs). Although adversarial training (AT) improves robustness, it degrades the standard…
Machine Learning (ML) models are applied in a variety of tasks such as network intrusion detection or Malware classification. Yet, these models are vulnerable to a class of malicious inputs known as adversarial examples. These are slightly…
We analyze the properties of adversarial training for learning adversarially robust halfspaces in the presence of agnostic label noise. Denoting $\mathsf{OPT}_{p,r}$ as the best robust classification error achieved by a halfspace that is…
The recent success of deep neural networks is powered in part by large-scale well-labeled training data. However, it is a daunting task to laboriously annotate an ImageNet-like dateset. On the contrary, it is fairly convenient, fast, and…
Recently, deep learning models have been widely applied in program understanding tasks, and these models achieve state-of-the-art results on many benchmark datasets. A major challenge of deep learning for program understanding is that the…
Label-noise or curated unlabeled data is used to compensate for the assumption of clean labeled data in training the conditional generative adversarial network; however, satisfying such an extended assumption is occasionally laborious or…
Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieved empirical success in practice, it still remains unclear…
Adversarial training is a defense technique that improves adversarial robustness of a deep neural network (DNN) by including adversarial examples in the training data. In this paper, we identify an overlooked problem of adversarial training…
We study the robustness to symmetric label noise of GNNs training procedures. By combining the nonlinear neural message-passing models (e.g. Graph Isomorphism Networks, GraphSAGE, etc.) with loss correction methods, we present a…
Recent breakthroughs in defenses against adversarial examples, like adversarial training, make the neural networks robust against various classes of attackers (e.g., first-order gradient-based attacks). However, it is an open question…
Data-driven software engineering processes, such as vulnerability prediction heavily rely on the quality of the data used. In this paper, we observe that it is infeasible to obtain a noise-free security defect dataset in practice. Despite…
Training deep neural networks (DNNs) with limited supervision has been a popular research topic as it can significantly alleviate the annotation burden. Self-training has been successfully applied in semi-supervised learning tasks, but one…
In the realm of continual learning, the presence of noisy labels within data streams represents a notable obstacle to model reliability and fairness. We focus on the data stream scenario outlined in pertinent literature, characterized by…
For multi-class classification under class-conditional label noise, we prove that the accuracy metric itself can be robust. We concretize this finding's inspiration in two essential aspects: training and validation, with which we address…
Noisy Labels are commonly present in data sets automatically collected from the internet, mislabeled by non-specialist annotators, or even specialists in a challenging task, such as in the medical field. Although deep learning models have…
Adversarial Training (AT), which is commonly accepted as one of the most effective approaches defending against adversarial examples, can largely harm the standard performance, thus has limited usefulness on industrial-scale production and…
Neural network based classifiers are still prone to manipulation through adversarial perturbations. State of the art attacks can overcome most of the defense or detection mechanisms suggested so far, and adversaries have the upper hand in…
The challenge of learning with noisy labels is significant in machine learning, as it can severely degrade the performance of prediction models if not addressed properly. This paper introduces a novel framework that conceptualizes noisy…
Labelling of data for supervised learning can be costly and time-consuming and the risk of incorporating label noise in large data sets is imminent. When training a flexible discriminative model using a strictly proper loss, such noise will…
Corruptions due to data perturbations and label noise are prevalent in the datasets from unreliable sources, which poses significant threats to model training. Despite existing efforts in developing robust models, current learning methods…