English
Related papers

Related papers: Watermarking Pre-trained Language Models with Back…

200 papers

Large Language Models (LLMs) suffer from a range of vulnerabilities that allow malicious users to solicit undesirable responses through manipulation of the input text. These so-called jailbreak prompts are designed to trick the LLM into…

Computation and Language · Computer Science 2025-10-13 John Hawkins , Aditya Pramar , Rodney Beard , Rohitash Chandra

Watermarking (WM) is a critical mechanism for detecting and attributing AI-generated content. Current WM methods for Large Language Models (LLMs) are predominantly tailored for autoregressive (AR) models: They rely on tokens being generated…

Computation and Language · Computer Science 2026-01-21 Ofek Raban , Ethan Fetaya , Gal Chechik

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…

Cryptography and Security · Computer Science 2025-08-05 Qihao Lin , Chen Tang , Lan zhang , Junyang zhang , Xiangyang Li

Large language models (LLMs) have acquired the ability to handle longer context lengths and understand nuances in text, expanding their dialogue capabilities beyond a single utterance. A popular user-facing application of LLMs is the…

Computation and Language · Computer Science 2024-10-29 Terry Tong , Jiashu Xu , Qin Liu , Muhao Chen

Safeguarding the intellectual property of machine learning models has emerged as a pressing concern in AI security. Model watermarking is a powerful technique for protecting ownership of machine learning models, yet its reliability has been…

Cryptography and Security · Computer Science 2024-09-11 Aoting Hu , Yanzhi Chen , Renjie Xie , Adrian Weller

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…

Cryptography and Security · Computer Science 2024-11-19 Or Zamir

The pre-training of large language models (LLMs) relies on massive text datasets sourced from diverse and difficult-to-curate origins. Although membership inference attacks and hidden canaries have been explored to trace data usage, such…

Cryptography and Security · Computer Science 2025-06-19 Wassim Bouaziz , Mathurin Videau , Nicolas Usunier , El-Mahdi El-Mhamdi

Deep neural networks are playing an important role in many real-life applications. After being trained with abundant data and computing resources, a deep neural network model providing service is endowed with economic value. An important…

Cryptography and Security · Computer Science 2021-12-28 Fangqi Li , Shilin Wang

Pretrained language models have achieved state-of-the-art performance when adapted to a downstream NLP task. However, theoretical analysis of these models is scarce and challenging since the pretraining and downstream tasks can be very…

Machine Learning · Computer Science 2022-04-22 Colin Wei , Sang Michael Xie , Tengyu Ma

Watermarking large language models (LLMs) is vital for preventing their misuse, including the fabrication of fake news, plagiarism, and spam. It is especially important to watermark LLM-generated code, as it often contains intellectual…

Cryptography and Security · Computer Science 2025-12-18 Li Lin , Siyuan Xin , Yang Cao , Xiaochun Cao

Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample-wise to more fine-grained sentence element-wise (e.g.,…

Computation and Language · Computer Science 2024-09-24 Zhenting Wang , Zhizhi Wang , Mingyu Jin , Mengnan Du , Juan Zhai , Shiqing Ma

Despite progress in watermarking algorithms for large language models (LLMs), real-world deployment remains limited. We argue that this gap stems from misaligned incentives among LLM providers, platforms, and end users, which manifest as…

Cryptography and Security · Computer Science 2026-04-22 Yepeng Liu , Xuandong Zhao , Dawn Song , Gregory W. Wornell , Yuheng Bu

Backdoor data poisoning is a crucial technique for ownership protection and defending against malicious attacks. Embedding hidden triggers in training data can manipulate model outputs, enabling provenance verification, and deterring…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-24 Kuan-Yu Chen , Yi-Cheng Lin , Jeng-Lin Li , Jian-Jiun Ding

Federated learning is a distributed learning technique where machine learning models are trained on client devices in which the local training data resides. The training is coordinated via a central server which is, typically, controlled by…

Cryptography and Security · Computer Science 2021-07-23 Buse Gul Atli , Yuxi Xia , Samuel Marchal , N. Asokan

Watermarking has recently emerged as an effective strategy for detecting the generations of large language models (LLMs). The strength of a watermark typically depends strongly on the entropy afforded by the language model and the set of…

Computation and Language · Computer Science 2026-02-05 Dara Bahri , John Wieting

Supervised relation extraction methods based on deep neural network play an important role in the recent information extraction field. However, at present, their performance still fails to reach a good level due to the existence of…

Computation and Language · Computer Science 2020-04-09 Cheng Li , Ye Tian

Multimodal Large Language Model (MLLM) have demonstrated strong generalization capabilities across diverse distributions and tasks, largely due to extensive pre-training datasets. Fine-tuning MLLM has become a common practice to improve…

Computation and Language · Computer Science 2024-11-19 Wenke Huang , Jian Liang , Zekun Shi , Didi Zhu , Guancheng Wan , He Li , Bo Du , Dacheng Tao , Mang Ye

The rapid advancement of customized Large Language Models (LLMs) offers considerable convenience. However, it also intensifies concerns regarding the protection of copyright/confidential information. With the extensive adoption of private…

Cryptography and Security · Computer Science 2024-12-18 Yuehan Zhang , Peizhuo Lv , Yinpeng Liu , Yongqiang Ma , Wei Lu , Xiaofeng Wang , Xiaozhong Liu , Jiawei Liu

Large Language Models (LLMs) have made significant advances in natural language processing, but their underlying mechanisms are often misunderstood. Despite exhibiting coherent answers and apparent reasoning behaviors, LLMs rely on…

Computation and Language · Computer Science 2024-08-05 Bo Zhou , Daniel Geißler , Paul Lukowicz

Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models…

Computation and Language · Computer Science 2022-11-22 Jaechul Roh , Minhao Cheng , Yajun Fang