Related papers: LLM Fingerprinting via Semantically Conditioned Wa…

LLM watermarking, which embeds imperceptible yet algorithmically detectable signals in model outputs to identify LLM-generated text, has become crucial in mitigating the potential misuse of large language models. However, the abundance of…

The evolution of Large Language Models (LLMs) into agentic systems that perform autonomous reasoning and tool use has created significant intellectual property (IP) value. We demonstrate that these systems are highly vulnerable to imitation…

The rise of LLMs has increased concerns over source tracing and copyright protection for AIGC, highlighting the need for advanced detection technologies. Passive detection methods usually face high false positives, while active watermarking…

With the widespread adoption of Large Language Models (LLMs), concerns about potential misuse have emerged. To this end, watermarking has been adapted to LLM, enabling a simple and effective way to detect and monitor generated text.…

Radio frequency fingerprint identification (RFFI) distinguishes wireless devices by the small variations in their analog circuits, avoiding heavy cryptographic authentication. While deep learning on spectrograms improves accuracy, models…

As deep learning (DL) models are widely and effectively used in Machine Learning as a Service (MLaaS) platforms, there is a rapidly growing interest in DL watermarking techniques that can be used to confirm the ownership of a particular…

In the present-day scenario, Large Language Models (LLMs) are establishing their presence as powerful instruments permeating various sectors of society. While their utility offers valuable support to individuals, there are multiple concerns…

Recent studies have shown that the outputs from large language models (LLMs) can often reveal the identity of their source model. While this is a natural consequence of LLMs modeling the distribution of their training data, such…

Watermarking has become a key technique for proprietary language models, enabling the distinction between AI-generated and human-written text. However, in many real-world scenarios, LLM-generated content may undergo post-generation edits,…

Large language models (LLMs) demonstrate general intelligence across a variety of machine learning tasks, thereby enhancing the commercial value of their intellectual property (IP). To protect this IP, model owners typically allow user…

Watermarking has emerged as a promising technique to track AI-generated content and differentiate it from authentic human creations. While prior work extensively studies watermarking for autoregressive large language models (LLMs) and image…

The increasing use of Large Language Models (LLMs) for generating highly coherent and contextually relevant text introduces new risks, including misuse for unethical purposes such as disinformation or academic dishonesty. To address these…

Generative models have rapidly evolved to generate realistic outputs. However, their synthetic outputs increasingly challenge the clear distinction between natural and AI-generated content, necessitating robust watermarking techniques.…

This paper introduces a novel problem, distributional information embedding, motivated by the practical demands of multi-bit watermarking for large language models (LLMs). Unlike traditional information embedding, which embeds information…

The rapid development of LLMs has raised concerns about their potential misuse, leading to various watermarking schemes that typically offer high detectability. However, existing watermarking techniques often face trade-off between…

Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a…

As large language models (LLMs) grow more powerful, concerns over copyright infringement of LLM-generated texts have intensified. LLM watermarking has been proposed to trace unauthorized redistribution or resale of generated content by…

Recent advances in Large Language Models (LLMs) have led to significant improvements in natural language processing tasks, but their ability to generate human-quality text raises significant ethical and operational concerns in settings…

The rapid growth of Large Language Models (LLMs) has highlighted the pressing need for reliable mechanisms to verify content ownership and ensure traceability. Watermarking offers a promising path forward, but it remains limited by privacy…

We propose dgMARK, a decoding-guided watermarking method for discrete diffusion language models (dLLMs). Unlike autoregressive models, dLLMs can generate tokens in arbitrary order. While an ideal conditional predictor would be invariant to…