Related papers: Concealed Data Poisoning Attacks on NLP Models
Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In…
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…
Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), such that the attacked model performs well on benign samples, whereas its prediction will be maliciously changed if the hidden backdoor is activated by the…
Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks -- malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. However,…
Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…
This paper investigates the critical issue of data poisoning attacks on AI models, a growing concern in the ever-evolving landscape of artificial intelligence and cybersecurity. As advanced technology systems become increasingly prevalent…
While numerous defense methods have been proposed to prohibit potential poisoning attacks from untrusted data sources, most research works only defend against specific attacks, which leaves many avenues for an adversary to exploit. In this…
Machine learning has been widely applied in wireless communications. However, the security aspects of machine learning in wireless applications have not been well understood yet. We consider the case that a cognitive transmitter senses the…
Deep learning has become a cornerstone of modern artificial intelligence, enabling transformative applications across a wide range of domains. As the core element of deep learning, the quality and security of training data critically…
Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…
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…
Machine learning models have been widely adopted in several fields. However, most recent studies have shown several vulnerabilities from attacks with a potential to jeopardize the integrity of the model, presenting a new window of research…
Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into…
Existing model poisoning attacks to federated learning assume that an attacker has access to a large fraction of compromised genuine clients. However, such assumption is not realistic in production federated learning systems that involve…
We show that continual pretraining on plausible misinformation can overwrite specific factual knowledge in large language models without degrading overall performance. Unlike prior poisoning work under static pretraining, we study repeated…
Visual modifications to text are often used to obfuscate offensive comments in social media (e.g., "!d10t") or as a writing style ("1337" in "leet speak"), among other scenarios. We consider this as a new type of adversarial attack in NLP,…
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 is susceptible to poisoning attacks, in which an attacker controls a small fraction of the training data and chooses that data with the goal of inducing some behavior unintended by the model developer in the trained model.…
To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that…