Related papers: Unanticipated Adversarial Robustness of Semantic C…

In this paper, the analysis of excess distortion exponent for joint source-channel coding (JSCC) in semantic-aware communication systems is presented. By introducing an unobservable semantic source, we extend the classical results by…

At the confluence of 6G, deep learning (DL), and natural language processing (NLP), DL-enabled text semantic communication (SemCom) has emerged as a 6G enabler since it minimizes bandwidth consumption, transmission delay, and power usage.…

Deep Neural Networks are vulnerable to small perturbations that can drastically alter their predictions for perceptually unchanged inputs. The literature on adversarially robust Deep Learning attempts to either enhance the robustness of…

Recent advances in deep learning have led to increased interest in solving high-efficiency end-to-end transmission problems using methods that employ the nonlinear property of neural networks. These techniques, we call neural joint…

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…

Semantic communications has received growing interest since it can remarkably reduce the amount of data to be transmitted without missing critical information. Most existing works explore the semantic encoding and transmission for text and…

Adversarial perturbations exploit vulnerabilities in automatic speech recognition (ASR) systems while preserving human perceived linguistic content. Neural audio codecs impose a discrete bottleneck that can suppress fine-grained signal…

Deep neural networks (DNNs) have shown remarkable performance in a variety of domains such as computer vision, speech recognition, or natural language processing. Recently they also have been applied to various software engineering tasks,…

Machine learning models are vulnerable to tiny adversarial input perturbations optimized to cause a very large output error. To measure this vulnerability, we need reliable methods that can find such adversarial perturbations. For image…

The emerging field semantic communication is driving the research of end-to-end data transmission. By utilizing the powerful representation ability of deep learning models, learned data transmission schemes have exhibited superior…

We consider a semantic communication system for speech signals, named DeepSC-S. Motivated by the breakthroughs in deep learning (DL), we make an effort to recover the transmitted speech signals in the semantic communication systems, which…

Discrete image tokenizers encode visual inputs as sequences of tokens from a finite vocabulary and are gaining popularity in multimodal systems, including encoder-only, encoder-decoder, and decoder-only models. However, unlike CLIP…

Semantic communication technology emerges as a pivotal bridge connecting AI with classical communication. The current semantic communication systems are generally modeled as an Auto-Encoder (AE). AE lacks a deep integration of AI principles…

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.…

To address the challenges of robust data transmission over complex time-varying channels, this paper introduces channel learning and enhanced adaptive reconstruction (CLEAR) strategy for semantic communications. CLEAR integrates deep joint…

Safety-critical applications like autonomous vehicles and industrial IoT are adopting semantic communication (SemCom) systems using deep neural networks to reduce bandwidth and increase transmission speed by transmitting only task-relevant…

Semantic communication is emerging as the next pillar in wireless communication technology due to its transformative capabilities in reducing communication overhead, enhancing robustness, and enabling intelligent information exchange. The…

The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative…

Despite significant advances, deep networks remain highly susceptible to adversarial attack. One fundamental challenge is that small input perturbations can often produce large movements in the network's final-layer feature space. In this…

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under attacks. Recent work…