arXiv Machine Learning
The Challenge of Identifying the Origin of Black-Box Large Language Models
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Aug 14
Security and Detectability Analysis of Unicode Text Watermarking Methods against Large Language Models
arXiv:2512. 13325v2 Announce Type: replace-cross Abstract: Securing digital text is becoming increasingly relevant due to the widespread use of large language models.
arXiv Computation and Language
Sep 1
Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs
arXiv:2502.10673v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) has become an effective method for enhancing large language models (LLMs) with up-to-date knowledge. How...
arXiv Machine Learning
Aug 31
OpenStamp: A Watermark for Open-Source Language Models
arXiv:2608.27899v1 Announce Type: cross Abstract: With the growing prevalence of large language model (LLM) generated content, watermarking is considered a promising approach for attributing text to...
arXiv Computation and Language
Aug 27
Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution
The paper introduces TRACE, a lightweight framework for detecting corpus poisoning in Retrieval-Augmented Generation systems. TRACE works by tracing answer-related tokens through token influence attribution, first identifying recurrent high-influence keywords across retrieved documents and then verifying their impact on model predictions. Experiments on three QA benchmarks and six large language models show that TRACE achieves strong detection performance while also revealing attacker-specified target answers.
arXiv AI
Jun 11
T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking
arXiv:2606. 11698v1 Announce Type: cross Abstract: Model watermarking safeguards AI model intellectual property by embedding distinctive knowledge that induces unique behavioral signatures.
arXiv AI
Aug 12
Protecting Creative Writing Copyright against AI Imitation via Implicit Watermarking
arXiv:2504. 00035v4 Announce Type: replace-cross Abstract: Large language models (LLMs) enable powerful knowledge injection through approaches such as in-context learning and fine-tuning, but they also introduce new risks of unauthorized imitation of high-value creative works.