相关论文: A Semantic Model for Physical Layer Deception

Spoken language understanding (SLU), one of the key enabling technologies for human-computer interaction in IoT devices, provides an easy-to-use user interface. Human speech can contain a lot of user-sensitive information, such as gender,…

Data at the physical layer transmits via media such as copper cable, fiber optic, or wireless. Physical attack vectors exist that challenge data confidentiality and availability. Protocols and encryption standards help obfuscate but often…

In real-life scenarios, a Reinforcement Learning (RL) agent aiming to maximise their reward, must often also behave in a safe manner, including at training time. Thus, much attention in recent years has been given to Safe RL, where an agent…

Today's high-stakes adversarial interactions feature attackers who constantly breach the ever-improving security measures. Deception mitigates the defender's loss by misleading the attacker to make suboptimal decisions. In order to formally…

Pseudo-labeling (PL), a semi-supervised learning (SSL) method where a seed model performs self-training using pseudo-labels generated from untranscribed speech, has been shown to enhance the performance of end-to-end automatic speech…

Reliable detection of deceptive behavior in Large Language Model (LLM) agents is an essential prerequisite for safe deployment in high-stakes agentic contexts. Prior work on scheming detection has focused exclusively on black-box monitors…

Large language models (LLMs) have been widely integrated into critical automated workflows, including contract review and job application processes. However, LLMs are susceptible to manipulation by fraudulent information, which can lead to…

Deployed large language models (LLMs) often rely on speculative decoding, a technique that generates and verifies multiple candidate tokens in parallel, to improve throughput and latency. In this work, we reveal a new side-channel whereby…

Integrating visible light communication (VLC) and radio-frequency (RF) networks can improve the performance of communication systems in terms of coverage and data rates. However, adding RF links to VLC networks weakens the secrecy…

In the era of Large Language Models (LLMs), generative linguistic steganography has become a prevalent technique for hiding information within model-generated texts. However, traditional steganography methods struggle to effectively align…

Physical layer key generation (PLKG) has emerged as a promising solution for achieving highly secured and low-latency key distribution, offering information-theoretic security that is inherently resilient to quantum attacks. However,…

The security of wireless challenge-response Physical Layer Authentication (PLA) based on Orthogonal Frequency Division Multiplexing (OFDM) relies on a sufficiently random fading channel condition, which is commonly assumed in existing…

Growing interest in utilizing the wireless spectrum by heterogeneous devices compels us to rethink the physical layer security to protect the transmitted waveform from an eavesdropper. We propose an end-to-end symmetric key neural…

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential…

Mechanistic approaches to deception in large language models (LLMs) often rely on "lie detectors", that is, truth probes trained to identify internal representations of model outputs as false. The lie detector approach to LLM deception…

Deceptive path planning (DPP) is the problem of designing a path that hides its true goal from an outside observer. Existing methods for DPP rely on unrealistic assumptions, such as global state observability and perfect model knowledge,…

In this paper we consider tandem error control coding and cryptography in the setting of the {\em wiretap channel} due to Wyner. In a typical communications system a cryptographic application is run at a layer above the physical layer and…

Deep learning (DL) has shown great potential in revolutionizing the traditional communications system. Many applications in communications have adopted DL techniques due to their powerful representation ability. However, the learning-based…

Semantic communication, an intelligent communication paradigm that aims to transmit useful information in the semantic domain, is facilitated by deep learning techniques. Robust semantic features can be learned and transmitted in an analog…

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…