Related papers: Detecting Stealthy Data Poisoning Attacks in AI Co…
Large-scale language models have achieved tremendous success across various natural language processing (NLP) applications. Nevertheless, language models are vulnerable to backdoor attacks, which inject stealthy triggers into models for…
Deep Learning (DL) is vulnerable to out-of-distribution and adversarial examples resulting in incorrect outputs. To make DL more robust, several posthoc (or runtime) anomaly detection techniques to detect (and discard) these anomalous…
Large Language Models (LLMs) are known to be vulnerable to backdoor attacks, where triggers embedded in poisoned samples can maliciously alter LLMs' behaviors. In this paper, we move beyond attacking LLMs and instead examine backdoor…
Deep neural networks (DNNs) have gain its popularity in various scenarios in recent years. However, its excellent ability of fitting complex functions also makes it vulnerable to backdoor attacks. Specifically, a backdoor can remain hidden…
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their reliance on large-scale…
Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets, based on which researchers and developers can easily…
Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. These attacks can occur in almost every stage of the deep learning pipeline. Although the attacked model behaves normally on benign…
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…
Recent studies have shown that deep neural networks (DNNs) are vulnerable to backdoor attacks, where a designed trigger is injected into the dataset, causing erroneous predictions when activated. In this paper, we propose a novel defense…
Training-data poisoning attacks can induce targeted, undetectable failure in deep neural networks by corrupting a vanishingly small fraction of training labels. We demonstrate this on acoustic vehicle classification using the MELAUDIS urban…
Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…
Recently, backdoor attacks pose a new security threat to the training process of deep neural networks (DNNs). Attackers intend to inject hidden backdoors into DNNs, such that the attacked model performs well on benign samples, whereas its…
Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick…
Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…
Neural code models (NCMs) have demonstrated extraordinary capabilities in code intelligence tasks. Meanwhile, the security of NCMs and NCMs-based systems has garnered increasing attention. In particular, NCMs are often trained on…
Advances in distributed machine learning can empower future communications and networking. The emergence of federated learning (FL) has provided an efficient framework for distributed machine learning, which, however, still faces many…
Retrieval-augmented generation (RAG) systems are vulnerable to attacks that inject poisoned passages into the retrieved context, even at low corruption rates. We show that existing attacks are not designed to be stealthy, allowing reliable…
The growing reliance of intelligent systems on data makes the systems vulnerable to data poisoning attacks. Such attacks could compromise machine learning or deep learning models by disrupting the input data. Previous studies on data…
With tools like GitHub Copilot, automatic code suggestion is no longer a dream in software engineering. These tools, based on large language models, are typically trained on massive corpora of code mined from unvetted public sources. As a…
In this work we present a formal theoretical framework for assessing and analyzing two classes of malevolent action towards generic Artificial Intelligence (AI) systems. Our results apply to general multi-class classifiers that map from an…