Related papers: MultiGuard: Provably Robust Multi-label Classifica…

It is well-known that classifiers are vulnerable to adversarial perturbations. To defend against adversarial perturbations, various certified robustness results have been derived. However, existing certified robustnesses are limited to…

Competitive methods for multi-label classification typically invest in learning labels together. To do so in a beneficial way, analysis of label dependence is often seen as a fundamental step, separate and prior to constructing a…

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

We show that label noise exists in adversarial training. Such label noise is due to the mismatch between the true label distribution of adversarial examples and the label inherited from clean examples - the true label distribution is…

Self-learning is a classical approach for learning with both labeled and unlabeled observations which consists in giving pseudo-labels to unlabeled training instances with a confidence score over a predetermined threshold. At the same time,…

Deep neural networks are vulnerable to so-called adversarial examples: inputs which are intentionally constructed to cause the model to make incorrect predictions or classifications. Adversarial examples are often visually indistinguishable…

In recent years, multi-label classification has attracted a significant body of research, motivated by real-life applications, such as text classification and medical diagnoses. Although sparsely studied in this context, Learning Classifier…

The bulk of existing research in defending against adversarial examples focuses on defending against a single (typically bounded Lp-norm) attack, but for a practical setting, machine learning (ML) models should be robust to a wide variety…

Annotating data for sensitive labels (e.g., disease, smoking) poses a potential threats to individual privacy in many real-world scenarios. To cope with this problem, we propose a novel setting to protect privacy of each instance, namely…

Integrated Speech and Large Language Models (SLMs) that can follow speech instructions and generate relevant text responses have gained popularity lately. However, the safety and robustness of these models remains largely unclear. In this…

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…

Randomized smoothing has become essential for achieving certified adversarial robustness in machine learning models. However, current methods primarily use isotropic noise distributions that are uniform across all data dimensions, such as…

Label-noise learning (LNL) aims to increase the model's generalization given training data with noisy labels. To facilitate practical LNL algorithms, researchers have proposed different label noise types, ranging from class-conditional to…

Deep neural networks have been shown to be very powerful methods for many supervised learning tasks. However, they can also easily overfit to training set biases, i.e., label noise and class imbalance. While both learning with noisy labels…

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…

Alongside the well-publicized accomplishments of deep neural networks there has emerged an apparent bug in their success on tasks such as object recognition: with deep models trained using vanilla methods, input images can be slightly…

Adversarial examples, which are usually generated for specific inputs with a specific model, are ubiquitous for neural networks. In this paper we unveil a surprising property of adversarial noises when they are put together, i.e.,…

Robustness to label noise is a critical property for weakly-supervised classifiers trained on massive datasets. Robustness to label noise is a critical property for weakly-supervised classifiers trained on massive datasets. In this paper,…

Boosting is known to be sensitive to label noise. We studied two approaches to improve AdaBoost's robustness against labelling errors. One is to employ a label-noise robust classifier as a base learner, while the other is to modify the…

While machine learning models have proven effective across various scenarios, it is widely acknowledged that many models are vulnerable to adversarial attacks. Recently, there have emerged numerous efforts in adversarial defense. Among…