Related papers: Naive Bayes Classifiers over Missing Data: Decisio…

Testing Machine Learning (ML) models and AI-Infused Applications (AIIAs), or systems that contain ML models, is highly challenging. In addition to the challenges of testing classical software, it is acceptable and expected that statistical…

Classification models are very sensitive to data uncertainty, and finding robust classifiers that are less sensitive to data uncertainty has raised great interest in the machine learning literature. This paper aims to construct robust…

We study the problem of certifying the robustness of Bayesian neural networks (BNNs) to adversarial input perturbations. Given a compact set of input points $T \subseteq \mathbb{R}^m$ and a set of output points $S \subseteq \mathbb{R}^n$,…

Adversarial examples pose a security threat to many critical systems built on neural networks (such as face recognition systems, and self-driving cars). While many methods have been proposed to build robust models, how to build certifiably…

In this paper, we present a scientific evaluation of four prominent malware detection tools to assist an organization with two primary questions: To what extent do ML-based tools accurately classify previously- and never-before-seen files?…

The detection of zero-day attacks and vulnerabilities is a challenging problem. It is of utmost importance for network administrators to identify them with high accuracy. The higher the accuracy is, the more robust the defense mechanism…

Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting "poisoned" data into the training process, have attracted significant recent attention. In this work, we take a closer look at existing poisoning…

Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples into the training data, causing a model to misclassify a…

Intensive algorithmic efforts have been made to enable the rapid improvements of certificated robustness for complex ML models recently. However, current robustness certification methods are only able to certify under a limited perturbation…

A fundamental question in adversarial machine learning is whether a robust classifier exists for a given task. A line of research has made some progress towards this goal by studying the concentration of measure, but we argue standard…

To achieve reliable, robust, and safe AI systems, it is vital to implement fallback strategies when AI predictions cannot be trusted. Certifiers for neural networks are a reliable way to check the robustness of these predictions. They…

Poisoning attacks are a category of adversarial machine learning threats in which an adversary attempts to subvert the outcome of the machine learning systems by injecting crafted data into training data set, thus increasing the machine…

Data poisoning considers an adversary that distorts the training set of machine learning algorithms for malicious purposes. In this work, we bring to light one conjecture regarding the fundamentals of data poisoning, which we call the…

Downstream applications often require text classification models to be accurate and robust. While the accuracy of the state-of-the-art Language Models (LMs) approximates human performance, they often exhibit a drop in performance on noisy…

Deep neural networks (DNNs) have achieved remarkable success in a variety of computer vision tasks, where massive labeled images are routinely required for model optimization. Yet, the data collected from the open world are unavoidably…

We present a certified defense to clean-label poisoning attacks under $\ell_2$-norm. These attacks work by injecting a small number of poisoning samples (e.g., 1%) that contain bounded adversarial perturbations into the training data to…

Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive class imbalance in real-world scenarios that can amplify backdoor threats. This paper…

In this paper we compare traditional machine learning and deep learning models trained on a malware dataset when subjected to adversarial attack based on label-flipping. Specifically, we investigate the robustness of Support Vector Machines…

Deep neural networks can memorize corrupted labels, making data quality critical for model performance, yet real-world datasets are frequently compromised by both label noise and input noise. This paper proposes a mutual information-based…

In supervised machine learning, models are typically trained using data with hard labels, i.e., definite assignments of class membership. This traditional approach, however, does not take the inherent uncertainty in these labels into…