paper-with-me

홈 › Papers

Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy

2023-07-25 · Yu Fu, Deyi Xiong, Yue Dong

To mitigate potential risks associated with language models, recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary restrictions and utilizing this information for detection. While these watermarks only induce a slight deterioration in perplexity, our empirical investigation reveals a significant detriment to the performance of conditional text generation. To address this issue, we introduce a simple yet effective semantic-aware watermarking algorithm that considers the characteristics of conditional text generation and the input context. Experimental results demonstrate that our proposed method yields substantial improvements across various text generation models, including BART and Flan-T5, in tasks such as summarization and data-to-text generation while maintaining detection ability.

📄 PDF Abstract BibTeX arXiv:2307.13808

Code (1)

fyyfu/semantic-watermark 공식 구현 pytorch

Tasks

Conditional Text GenerationData-to-Text GenerationText Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

BanglaLorica: Design and Evaluation of a Robust Watermarking Algorithm for Large Language Models in Bangla Text Generation

2026-01-08 · Amit Bin Tariqul, A N M Zahid Hossain Milkan, Sahab-Al-Chowdhury, Syed Rifat Raiyan 외 arxiv

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 watermar…

Text Generation

How Good is Post-Hoc Watermarking With Language Model Rephrasing?

2025-12-18 · Pierre Fernandez, Tom Sander, Hady Elsahar, Hongyan Chang 외 arxiv

Generation-time text watermarking embeds statistical signals into text for traceability of AI-generated content. We explore *post-hoc watermarking* where an LLM rewrites existing text while applying generation-time water…

Beyond Detection: Multi-Scale Hidden-Code for Natural Image Deepfake Recovery and Factual Retrieval

2026-02-26 · Yuan-Chih Chen, Chun-Shien Lu arxiv

Recent advances in image authenticity have primarily focused on deepfake detection and localization, leaving recovery of tampered contents for factual retrieval relatively underexplored. We propose a unified hidden-code …

DeepFake Detection

DMark: Order-Agnostic Watermarking for Diffusion Large Language Models

2025-10-03 · Linyu Wu, Linhao Zhong, Wenjie Qu, Yuexin Li 외 arxiv

Diffusion large language models (dLLMs) offer faster generation than autoregressive models while maintaining comparable quality, but existing watermarking methods fail on them due to their non-sequential decoding. Unlike…

Global Sketch-Based Watermarking for Diffusion Language Models

2026-06-03 · Daniel Zhao arxiv

Watermarking methods for language models have been studied extensively in the autoregressive setting, where tokens are generated sequentially. These works largely focus on local-context schemes that perturb the next toke…