Related papers: Generalization Bound and New Algorithm for Clean-L…

This dissertation studies a fundamental open challenge in deep learning theory: why do deep networks generalize well even while being overparameterized, unregularized and fitting the training data to zero error? In the first part of the…

Well-known (non-malicious) sources of overfitting in deep neural net (DNN) classifiers include: i) large class imbalances; ii) insufficient training-set diversity; and iii) over-training. In recent work, it was shown that backdoor…

Recent studies have shown that deep learning models are very vulnerable to poisoning attacks. Many defense methods have been proposed to address this issue. However, traditional poisoning attacks are not as threatening as commonly believed.…

Although deep neural networks (DNNs) have made rapid progress in recent years, they are vulnerable in adversarial environments. A malicious backdoor could be embedded in a model by poisoning the training dataset, whose intention is to make…

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

Machine learning based data-driven technologies have shown impressive performances in a variety of application domains. Most enterprises use data from multiple sources to provide quality applications. The reliability of the external data…

Federated learning is particularly susceptible to model poisoning and backdoor attacks because individual users have direct control over the training data and model updates. At the same time, the attack power of an individual user is…

One of the principal scientific challenges in deep learning is explaining generalization, i.e., why the particular way the community now trains networks to achieve small training error also leads to small error on held-out data from the…

Data poisoning attacks, in which an adversary corrupts a training set with the goal of inducing specific desired mistakes, have raised substantial concern: even just the possibility of such an attack can make a user no longer trust the…

State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…

We study the generalization error of stochastic learning algorithms from an information-theoretic perspective, with a particular emphasis on deriving sharper bounds for differentially private algorithms. It is well known that the…

We study the problem of attacking a machine learning model in the hard-label black-box setting, where no model information is revealed except that the attacker can make queries to probe the corresponding hard-label decisions. This is a very…

Backdoor attacks on deep neural networks have emerged as significant security threats, especially as DNNs are increasingly deployed in security-critical applications. However, most existing works assume that the attacker has access to the…

Poisoning attacks are a primary threat to machine learning models, aiming to compromise their performance and reliability by manipulating training datasets. This paper introduces a novel attack - Outlier-Oriented Poisoning (OOP) attack,…

Performing supervised learning from the data synthesized by using Generative Adversarial Networks (GANs), dubbed GAN-synthetic data, has two important applications. First, GANs may generate more labeled training data, which may help improve…

Backdoor attacks have emerged as a prominent threat to natural language processing (NLP) models, where the presence of specific triggers in the input can lead poisoned models to misclassify these inputs to predetermined target classes.…

Poisoning attacks can compromise the safety of large language models (LLMs) by injecting malicious documents into their training data. Existing work has studied pretraining poisoning assuming adversaries control a percentage of the training…

Backdoors and adversarial examples are the two primary threats currently faced by deep neural networks (DNNs). Both attacks attempt to hijack the model behaviors with unintended outputs by introducing (small) perturbations to the inputs.…

We have widely observed that neural networks are vulnerable to small additive perturbations to the input causing misclassification. In this paper, we focus on the $\ell_0$-bounded adversarial attacks, and aim to theoretically characterize…

We derive a tight generalization bound for quantum machine learning that is applicable to a wide range of supervised tasks, data, and models. Our bound is both efficiently computable and free of big-O notation. Furthermore, we point out…