相关论文: Stealing AI Model Weights Through Covert Communica…

Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate…

Covert channel attacks represent a significant threat to system security, leveraging shared resources to clandestinely transmit information from highly secure systems, thereby violating the system's security policies. These attacks exploit…

Deep Neural Networks (DNNs) are susceptible to model stealing attacks, which allows a data-limited adversary with no knowledge of the training dataset to clone the functionality of a target model, just by using black-box query access. Such…

Trojan attacks pose a severe threat to AI systems. Recent works on Transformer models received explosive popularity and the self-attentions are now indisputable. This raises a central question: Can we reveal the Trojans through attention…

Context:With the advancement of artificial intelligence (AI) technology and applications, numerous AI models have been developed, leading to the emergence of open-source model hosting platforms like Hugging Face (HF). Thanks to these…

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…

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…

Machine learning provides automated means to capture complex dynamics of wireless spectrum and support better understanding of spectrum resources and their efficient utilization. As communication systems become smarter with cognitive radio…

Learning-based methods for underwater image enhancement (UWIE) have undergone extensive exploration. However, learning-based models are usually vulnerable to adversarial examples so as the UWIE models. To the best of our knowledge, there is…

AI-enabled wireless communications have attracted tremendous research interest in recent years, particularly with the rise of novel paradigms such as low-altitude integrated sensing and communication (ISAC) networks. Within these systems,…

As Artificial Intelligence (AI) systems increasingly underpin critical applications, from autonomous vehicles to biometric authentication, their vulnerability to transferable attacks presents a growing concern. These attacks, designed to…

Deployment of sensor network in hostile environment makes it mainly vulnerable to battery drainage attacks because it is impossible to recharge or replace the battery power of sensor nodes. Among different types of security threats, low…

The sixth-generation (6G) mobile networks are expected to feature the ubiquitous deployment of machine learning and AI algorithms at the network edge. With rapid advancements in edge AI, the time has come to realize intelligence downloading…

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…

Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat is backdoor attacks, in which adversaries embed hidden behaviors that activate under specific conditions.…

Deep neural networks have been applied in wireless communications system to intelligently adapt to dynamically changing channel conditions, while the users are still under the threat of the malicious attacks due to the broadcasting property…

In privacy-preserving machine learning, it is common that the owner of the learned model does not have any physical access to the data. Instead, only a secured remote access to a data lake is granted to the model owner without any ability…

Embedding models that generate dense vector representations of text are widely used and hold significant commercial value. Companies such as OpenAI and Cohere offer proprietary embedding models via paid APIs, but despite being "hidden"…

Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through Trojaned training samples, which can later be exploited.…

Natural language processing (NLP) tasks, ranging from text classification to text generation, have been revolutionised by the pre-trained language models, such as BERT. This allows corporations to easily build powerful APIs by encapsulating…