Related papers: The Model Inversion Eavesdropping Attack in Semant…

Gradient inversion attacks on federated learning systems reconstruct client training data from exchanged gradient information. To defend against such attacks, a variety of defense mechanisms were proposed. However, they usually lead to an…

Semantic communication (SemCom) has emerged as a promising paradigm for next-generation networks. However, its typical end-to-end joint source--channel coding (JSCC) architecture also raises serious privacy concerns. To guide future secure…

Semantic communication, due to its focus on the transmitting meaning rather than the raw bit data, poses unique security challenges compared to the traditional communication systems. In particular, semantic communication systems are…

Label smoothing -- using softened labels instead of hard ones -- is a widely adopted regularization method for deep learning, showing diverse benefits such as enhanced generalization and calibration. Its implications for preserving model…

Semantic communication has emerged as a promising paradigm for next-generation wireless systems, improving the communication efficiency by transmitting high-level semantic features. However, reliance on unimodal representations can degrade…

Decentralized training has become a resource-efficient framework to democratize the training of large language models (LLMs). However, the privacy risks associated with this framework, particularly due to the potential inclusion of…

Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that ML models are vulnerable to…

Textual data is often represented as real-numbered embeddings in NLP, particularly with the popularity of large language models (LLMs) and Embeddings as a Service (EaaS). However, storing sensitive information as embeddings can be…

Deep Neural Networks (DNNs) have revolutionized various domains with their exceptional performance across numerous applications. However, Model Inversion (MI) attacks, which disclose private information about the training dataset by abusing…

Typical magnetic induction (MI) communication is commonly considered a secure underwater wireless communication (UWC) technology due to its non-audible and non-visible nature compared to acoustic and optical UWC technologies. However,…

Semantic communication is of crucial importance for the next-generation wireless communication networks. The existing works have developed semantic communication frameworks based on deep learning. However, systems powered by deep learning…

Semantic communication (SemCom) significantly improves inter-vehicle interactions in intelligent connected vehicles (ICVs) within limited wireless spectrum. However, the open nature of wireless communications introduces eavesdropping risks.…

Model Inversion (MI) attacks pose a significant threat to the privacy of Deep Neural Networks by recovering training data distribution from well-trained models. While existing defenses often rely on regularization techniques to reduce…

Model Inversion (MI), in which an adversary abuses access to a trained Machine Learning (ML) model attempting to infer sensitive information about its original training data, has attracted increasing research attention. During MI, the…

With the emergence of powerful large-scale foundation models, the training paradigm is increasingly shifting from from-scratch training to transfer learning. This enables high utility training with small, domain-specific datasets typical in…

Deep learning-based semantic communication (SemCom) has emerged as a promising paradigm for next-generation wireless networks, offering superior transmission efficiency by extracting and conveying task-relevant semantic latent…

Machine learning (ML) models have the potential to transform military battlefields, presenting a large external pressure to rapidly incorporate them into operational settings. However, it is well-established that these ML models are…

Large scale deep learning model, such as modern language models and diffusion architectures, have revolutionized applications ranging from natural language processing to computer vision. However, their deployment in distributed or…

Embeddings are functions that map raw input data to low-dimensional vector representations, while preserving important semantic information about the inputs. Pre-training embeddings on a large amount of unlabeled data and fine-tuning them…

This paper highlights vulnerabilities of deep learning-driven semantic communications to backdoor (Trojan) attacks. Semantic communications aims to convey a desired meaning while transferring information from a transmitter to its receiver.…