paper-with-me

Papers

Undetectable Watermarks for Language Models

2023-05-25 · Miranda Christ, Sam Gunn, Or Zamir

Recent advances in the capabilities of large language models such as GPT-4 have spurred increasing concern about our ability to detect AI-generated text. Prior works have suggested methods of embedding watermarks in model outputs, by noticeably altering the output distribution. We ask: Is it possible to introduce a watermark without incurring any detectable change to the output distribution? To this end we introduce a cryptographically-inspired notion of undetectable watermarks for language models. That is, watermarks can be detected only with the knowledge of a secret key; without the secret key, it is computationally intractable to distinguish watermarked outputs from those of the original model. In particular, it is impossible for a user to observe any degradation in the quality of the text. Crucially, watermarks should remain undetectable even when the user is allowed to adaptively query the model with arbitrarily chosen prompts. We construct undetectable watermarks based on the existence of one-way functions, a standard assumption in cryptography.

📄 PDF Abstract BibTeX arXiv:2306.09194

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Position-Wise Feed-Forward Layer 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Watermarking Language Models for Many Adaptive Users

2024-05-17 · Aloni Cohen, Alexander Hoover, Gabe Schoenbach

We study watermarking schemes for language models with provable guarantees. As we show, prior works offer no robustness guarantees against adaptive prompting: when a user queries a language model more than once, as even …

Language Modelling

An Undetectable Watermark for Generative Image Models

2024-10-09 · Sam Gunn, Xuandong Zhao, Dawn Song

We present the first undetectable watermarking scheme for generative image models. Undetectability ensures that no efficient adversary can distinguish between watermarked and un-watermarked images, even after making many…

Picking watermarks from noise (PWFN): an improved robust watermarking model against intensive distortions

2024-05-08 · Sijing Xie, Chengxin Zhao, Nan Sun, Wei Li 외

Digital watermarking is the process of embedding secret information by altering images in an undetectable way to the human eye. To increase the robustness of the model, many deep learning-based watermarking methods use t…

Decoder

Injecting Undetectable Backdoors in Obfuscated Neural Networks and Language Models

2024-06-09 · Alkis Kalavasis, Amin Karbasi, Argyris Oikonomou, Katerina Sotiraki 외

As ML models become increasingly complex and integral to high-stakes domains such as finance and healthcare, they also become more susceptible to sophisticated adversarial attacks. We investigate the threat posed by unde…

Optimizing watermarks for large language models

2023-12-28 · Bram Wouters

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 th…