Related papers: Watermarks for Language Models via Probabilistic A…

In this thesis, we develop algorithms with theoretical guarantees for ensuring reliability and accountability of Machine Learning (ML) systems. As ML systems evolve from predictive models to generative models and autonomous agents, the…

Large language models (LLMs) demonstrate remarkable capabilities across various tasks. However, their deployment introduces significant risks related to intellectual property. In this context, we focus on model stealing attacks, where…

As large language models (LLMs) are increasingly deployed for text generation, watermarking has become essential for authorship attribution, intellectual property protection, and misuse detection. While existing watermarking methods perform…

Large language model (LLM) watermarking has emerged as a promising approach for detecting and attributing AI-generated text, yet its robustness to black-box spoofing remains insufficiently evaluated. Existing evaluation methods often demand…

Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content. While existing…

Text watermarking algorithms for large language models (LLMs) can effectively identify machine-generated texts by embedding and detecting hidden features in the text. Although the current text watermarking algorithms perform well in most…

We introduce a cryptographic method to hide an arbitrary secret payload in the response of a Large Language Model (LLM). A secret key is required to extract the payload from the model's response, and without the key it is provably…

Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data. Current methods use manual patterns or special perturbations as triggers, while they often overlook the…

The widely adopted and powerful generative large language models (LLMs) have raised concerns about intellectual property rights violations and the spread of machine-generated misinformation. Watermarking serves as a promising approch to…

Large Language Models (LLMs) have demonstrated remarkable capabilities, but their training requires extensive data and computational resources, rendering them valuable digital assets. Therefore, it is essential to watermark LLMs to protect…

Abuse of large language models reveals high risks as large language models are being deployed at an astonishing speed. It is important to protect the model weights to avoid malicious usage that violates licenses of open-source large…

Large language models (LLMs) excellently generate human-like text, but also raise concerns about misuse in fake news and academic dishonesty. Decoding-based watermark, particularly the GumbelMax-trick-based watermark(GM watermark), is a…

The indistinguishability of AI-generated content from human text raises challenges in transparency and accountability. While several methods exist to watermark models behind APIs, embedding watermark strategies directly into model weights…

In this paper, we study the problem of watermarking large language models (LLMs). We consider the trade-off between model distortion and detection ability and formulate it as a constrained optimization problem based on the red-green list…

Recent advances in Text-To-Speech (TTS) technology have enabled synthetic speech to mimic human voices with remarkable realism, raising significant security concerns. This underscores the need for traceable TTS models-systems capable of…

Steganography embeds secret messages in seemingly innocuous carriers for covert communication under surveillance. Current Provably Secure Steganography (PSS) schemes based on language models can guarantee computational indistinguishability…

Invisible watermarks safeguard images' copyrights by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated by AI models. We propose a family of regeneration attacks to…

The availability of bandwidth for internet access is sufficient enough to communicate digital assets. These digital assets are subjected to various types of threats. [19] As a result of this, protection mechanism required for the protection…

Digital multimedia watermarking technology was suggested in the last decade to embed copyright information in digital objects such images, audio and video. However, the increasing use of relational database systems in many real-life…

Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and…