Related papers: CATMark: A Context-Aware Thresholding Framework fo…
Recently, watermarking schemes for large language models (LLMs) have been proposed to distinguish text generated by machines and by humans. The present paper explores philosophical, political, and ethical ramifications of implementing and…
As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is a simple and effective strategy for mitigating such harms by enabling the…
The recent explosion of high-quality language models has necessitated new methods for identifying AI-generated text. Watermarking is a leading solution and could prove to be an essential tool in the age of generative AI. Existing approaches…
Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…
Watermarking has emerged as a promising way to detect LLM-generated text, by augmenting LLM generations with later detectable signals. Recent work has proposed multiple families of watermarking schemes, several of which focus on preserving…
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…
Recommender systems often struggle with data sparsity and cold-start scenarios, limiting their ability to provide accurate suggestions for new or infrequent users. This paper presents a Graph Attention Network (GAT) based Collaborative…
Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. However, existing watermarking methods are often vulnerable to semantic-invariant attacks, such as…
In the rapidly evolving domain of artificial intelligence, safeguarding the intellectual property of Large Language Models (LLMs) is increasingly crucial. Current watermarking techniques against model extraction attacks, which rely on…
Large Vision-Language Models (LVLMs) achieve strong performance on single-image tasks, but their performance declines when multiple images are provided as input. One major reason is the cross-image information leakage, where the model…
With the rise of large language models (LLMs) and concerns about potential misuse, watermarks for generative LLMs have recently attracted much attention. An important aspect of such watermarks is the trade-off between their identifiability…
Scene graph generation (SGG) is a sophisticated task that suffers from both complex visual features and dataset long-tail problem. Recently, various unbiased strategies have been proposed by designing novel loss functions and data balancing…
Invisible watermarking of AI-generated images can help with copyright protection, enabling detection and identification of AI-generated media. In this work, we present a novel approach to watermark images of T2I Latent Diffusion Models…
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…
Given how large parts of publicly available text are crawled to pretrain large language models (LLMs), data creators increasingly worry about the inclusion of their proprietary data for model training without attribution or licensing. Their…
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 Easymark, a family of embarrassingly simple yet effective watermarks. Text watermarking is becoming increasingly important with the advent of Large Language Models (LLM). LLMs can generate texts that cannot be distinguished from…
We show the viability of tackling misuses of large language models beyond the identification of machine-generated text. While existing zero-bit watermark methods focus on detection only, some malicious misuses demand tracing the adversary…
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…
Code Large Language Models (Code LLMs) have revolutionized software development but raised critical concerns regarding code provenance, copyright protection, and security. Existing code watermarking approaches suffer from two fundamental…