Related papers: Multilayer Perceptron Guided Key Generation Throug…

Large language models (LLMs) successfully model natural language from vast amounts of text without the need for explicit supervision. In this paper, we investigate the efficacy of LLMs in modeling passwords. We present PassGPT, a LLM…

Conventionally, secrecy is achieved using cryptographic techniques beyond the physical layer. Recent studies raise the interest of performing encryption within the physical layer by exploiting some unique features of the physical wireless…

In low-bitrate speech coding, end-to-end speech coding networks aim to learn compact yet expressive features and a powerful decoder in a single network. A challenging problem as such results in unwelcome complexity increase and inferior…

Natural Language Generation (NLG) models are prone to generating repetitive utterances. In this work, we study the repetition problem for encoder-decoder models, using both recurrent neural network (RNN) and transformer architectures. To…

Reliable image transmission over wireless channels is particularly challenging at extremely low transmission rates, where conventional compression and channel coding schemes fail to preserve adequate visual quality. To address this issue,…

Multi-layer perceptrons (MLP) have proven to be effective scene encoders when combined with higher-dimensional projections of the input, commonly referred to as \textit{positional encoding}. However, scenes with a wide frequency spectrum…

Large Language Models (LLMs) excel at generating coherent text within a single prompt but fall short in sustaining relevance, personalization, and continuity across extended interactions. Human communication, however, relies on multiple…

We extend covert communication to the quantum regime by showing that covert quantum communication is possible over optical channels with noise arising either from the environment or from the sender's lab. In particular, we show that…

Recent advances in text-guided image compression have shown great potential to enhance the perceptual quality of reconstructed images. These methods, however, tend to have significantly degraded pixel-wise fidelity, limiting their…

Wireless key generation holds significant promise for establishing cryptographic keys in Next-Gen Internet of Vehicles (IoV) systems. However, existing approaches often face inefficiencies and performance limitations caused by frequent…

Generative Pre-trained Transformer (GPT) models have achieved remarkable performance on various natural language processing tasks, and have shown great potential as backbones for audio-and-text large language models (LLMs). Previous…

As wireless ad hoc and mobile networks are emerging and the transferred data become more sensitive, information security measures should make use of all the available contextual resources to secure information flows. The physical layer…

To ensure large language models (LLMs) are used safely, one must reduce their propensity to hallucinate or to generate unacceptable answers. A simple and often used strategy is to first let the LLM generate multiple hypotheses and then…

Recent progress in generative compression technology has significantly improved the perceptual quality of compressed data. However, these advancements primarily focus on producing high-frequency details, often overlooking the ability of…

We study covert communication and covert secret key generation with positive rates over quantum state-dependent channels. Specifically, we consider fully quantum state-dependent channels when the transmitter shares an entangled state with…

In this paper, we address task-oriented (or goal-oriented) communications where an encoder at the transmitter learns compressed latent representations of data, which are then transmitted over a wireless channel. At the receiver, a decoder…

Natural language generation (NLG) is a critical component in a spoken dialogue system. This paper presents a Recurrent Neural Network based Encoder-Decoder architecture, in which an LSTM-based decoder is introduced to select, aggregate…

It is hard to generate an image at target view well for previous cross-view image translation methods that directly adopt a simple encoder-decoder or U-Net structure, especially for drastically different views and severe deformation cases.…

Large language models (LLMs) have recently shown remarkable performance across a wide range of tasks. However, the substantial number of parameters in LLMs contributes to significant latency during model inference. This is particularly…

Multi-hop question generation (MQG) aims to generate questions that require synthesizing multiple information snippets from documents to derive target answers. The primary challenge lies in effectively pinpointing crucial information…