Related papers: Semantic Security with Unreliable Entanglement Ass…
This letter explores the positive side of the adversarial attack for the security-aware semantic communication system. Specifically, a pair of matching pluggable modules is installed: one after the semantic transmitter and the other before…
Underutilized wireless channel is a waste of spectral resource. Eavesdropping compromises data secrecy. How to overcome the two problems with one solution? In this paper, we propose a spectrum sharing model that defends against…
The increasing adoption of Cloud-based Large Language Models (CLLMs) has raised significant concerns regarding data privacy during user interactions. While existing approaches primarily focus on encrypting sensitive information, they often…
The rapid growth of large language models has spurred significant interest in model compression as a means to enhance their accessibility and practicality. While extensive research has explored model compression through the lens of safety,…
Semantic communication is deemed as a revolution of Shannon's paradigm in the six-generation (6G) wireless networks. It aims at transmitting the extracted information rather than the original data, which receivers will try to recover.…
Safety-aligned language models often refuse prompts that are actually harmless. Current evaluations mostly report global rates such as false rejection or compliance. These scores treat each prompt alone and miss local inconsistency, where a…
Large vision-language models (LVLMs) are vulnerable to harmful input compared to their language-only backbones. We investigated this vulnerability by exploring LVLMs internal dynamics, framing their inherent safety understanding in terms of…
Deep learning draws heavily on the latest progress in semantic communications. The present paper aims to examine the security aspect of this cutting-edge technique from a novel shuffling perspective. Our goal is to improve upon the…
Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to…
Two styles of definitions are usually considered to express that a security protocol preserves the confidentiality of a data s. Reachability-based secrecy means that s should never be disclosed while equivalence-based secrecy states that…
Semantic communication has emerged as a promising paradigm for enhancing communication efficiency in sixth-generation (6G) networks. However, the broadcast nature of wireless channels makes SemCom systems vulnerable to eavesdropping, which…
Large language models (LLMs) have exhibited impressive capabilities in comprehending complex instructions. However, their blind adherence to provided instructions has led to concerns regarding risks of malicious use. Existing defence…
Adversarial robustness has been studied extensively in image classification, especially for the $\ell_\infty$-threat model, but significantly less so for related tasks such as object detection and semantic segmentation, where attacks turn…
The problem of secure lossy source-channel wiretapping with arbitrarily correlated side informations at both receivers is investigated. This scenario consists of an encoder (referred to as Alice) that wishes to compress a source and send it…
We explore semantic correspondence estimation through the lens of unsupervised learning. We thoroughly evaluate several recently proposed unsupervised methods across multiple challenging datasets using a standardized evaluation protocol…
Interpretable and explainable machine learning has seen a recent surge of interest. We focus on safety as a key motivation behind the surge and make the relationship between interpretability and safety more quantitative. Toward assessing…
A promising platform for semi-device-independent quantum information is prepare-and-measure experiments restricted only by a bound on the energy of the communication. Here, we investigate the role of shared entanglement in such scenarios.…
This paper presents a semantic parsing approach for unrestricted texts. Semantic parsing is one of the major bottlenecks of Natural Language Understanding (NLU) systems and usually requires building expensive resources not easily portable…
Semantic Web is an open, distributed, and dynamic environment where access to resources cannot be controlled in a safe manner unless the access decision takes into account during discovery of web services. Security becomes the crucial…
Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities when queried in low-resource languages. We attribute this gap to a mismatch between language-agnostic…