相关论文: ERIS: Evolutionary Real-world Interference Scheme …

Acoustic Environment Matching (AEM) is the task of transferring clean audio into a target acoustic environment, enabling engaging applications such as audio dubbing and auditory immersive virtual reality (VR). Recovering similar room…

The potential of Reconfigurable Intelligent Surfaces (RISs) for energy-efficient and performance-boosted wireless communications is recently gaining remarkable research attention, motivating their consideration for various $5$-th Generation…

As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this…

The intelligent reflecting surface (IRS) is a promising new paradigm in wireless communications for meeting the growing connectivity demands in next-generation mobile networks. IRS, also known as software-controlled metasurfaces, consist of…

Despite the widespread application of large language models (LLMs) across various tasks, recent studies indicate that they are susceptible to jailbreak attacks, which can render their defense mechanisms ineffective. However, previous…

The rise of Large Audio Language Models (LAMs) brings both potential and risks, as their audio outputs may contain harmful or unethical content. However, current research lacks a systematic, quantitative evaluation of LAM safety especially…

Sensing-assisted communication schemes have recently garnered significant research attention. In this work, we design a dual-function reconfigurable intelligent surface (RIS), integrating both active and passive elements, referred to as the…

Large Audio-Language Models (LALMs) are becoming essential as a powerful multimodal backbone for real-world applications. However, recent studies show that audio inputs can more easily elicit harmful responses than text, exposing new risks…

With the widespread application of automatic speech recognition (ASR) systems, their vulnerability to adversarial attacks has been extensively studied. However, most existing adversarial examples are generated on specific individual models,…

Robust alignment guardrails for large language models (LLMs) are becoming increasingly important with their widespread application. In contrast to previous studies, we demonstrate that inference-time activation interventions can bypass…

Insider threats pose a significant challenge to organizational security, often evading traditional rule-based detection systems due to their subtlety and contextual nature. This paper presents an AI-powered Insider Risk Management (IRM)…

Despite efforts to align large language models (LLMs) with societal and moral values, these models remain susceptible to jailbreak attacks -- methods designed to elicit harmful responses. Jailbreaking black-box LLMs is considered…

Physical layer security in reconfigurable intelligent surface (RIS)-assisted wireless systems can be improved through coordinated control of signal transmission and RIS configuration. In this work, the base station simultaneously transmits…

Reconfigurable intelligent surfaces (RIS) can both help and hinder the physical layer secret key generation (PL-SKG) of communications systems. Whilst a legitimate RIS can yield beneficial impacts, including increased channel randomness to…

Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores…

Reconfigurable Intelligent Surfaces (RISs) have emerged as a promising technology for next-generation wireless communications, offering energy-efficient control of electromagnetic (EM) waves. While conventional RIS models based on phase…

An innovative evolutionary method for the dynamic control of reconfigurable intelligent surfaces (RISs) is proposed. It leverages, on the one hand, on the exploration capabilities of evolutionary strategies and their effectiveness in…

Large Language Models (LLMs) have unveiled remarkable capabilities in understanding and generating both natural language and code, but LLM reasoning is prone to hallucination and struggle with complex, novel scenarios, often getting stuck…

Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…

Large language models (LLMs) remain vulnerable to jailbreak prompts that elicit harmful or policy-violating outputs, while many existing defenses rely on expensive fine-tuning, intrusive prompt rewriting, or external guardrails that add…