# Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage Risks

arXiv: https://arxiv.org/abs/2602.05252 · HTML: https://mlsanity.com/paper/2602.05252/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 28 of 28)

- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [MUSE: Machine Unlearning Six-Way Evaluation for Language Models](https://mlsanity.com/paper/2407.06460/) (2024)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4](https://mlsanity.com/paper/2305.00118/) (2023)
- [Quantifying Uncertainty in Answers from any Language Model and Enhancing their Trustworthiness](https://mlsanity.com/paper/2308.16175/) (2023)
- [LUQ: Long-text Uncertainty Quantification for LLMs](https://mlsanity.com/paper/2403.20279/) (2024)
- [Catastrophic Failure of LLM Unlearning via Quantization](https://mlsanity.com/paper/2410.16454/) (2024)
- [DE-COP: Detecting Copyrighted Content in Language Models Training Data](https://mlsanity.com/paper/2402.09910/) (2024)
- [Do Language Models Plagiarize?](https://mlsanity.com/paper/2203.07618/) (2022)
- [Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)](https://mlsanity.com/paper/2407.14937/) (2024)
- [Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs](https://mlsanity.com/paper/2505.16831/) (2025)
- [CopyBench: Measuring Literal and Non-Literal Reproduction of Copyright-Protected Text in Language Model Generation](https://mlsanity.com/paper/2407.07087/) (2024)
- [Extracting memorized pieces of (copyrighted) books from open-weight language models](https://mlsanity.com/paper/2505.12546/) (2025)
- [GUARD: Generation-time LLM Unlearning via Adaptive Restriction and Detection](https://mlsanity.com/paper/2505.13312/) (2025)
- [Extracting books from production language models](https://mlsanity.com/paper/2601.02671/) (2026)
- [Evaluating Uncertainty-based Failure Detection for Closed-Loop LLM Planners](https://mlsanity.com/paper/2406.00430/) (2024)
- [An overview of model uncertainty and variability in LLM-based sentiment analysis. Challenges, mitigation strategies and the role of explainability](https://mlsanity.com/paper/2504.04462/) (2025)
- [Do LLMs Know to Respect Copyright Notice?](https://mlsanity.com/paper/2411.01136/) (2024)
- [Measuring Copyright Risks of Large Language Model via Partial Information Probing](https://mlsanity.com/paper/2409.13831/) (2024)
- [Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models](https://mlsanity.com/paper/2506.17279/) (2025)
- [SUA: Stealthy Multimodal Large Language Model Unlearning Attack](https://mlsanity.com/paper/2506.17265/) (2025)
- [GRAIL: Gradient-Based Adaptive Unlearning for Privacy and Copyright in LLMs](https://mlsanity.com/paper/2504.12681/) (2025)
- [DP2Unlearning: An Efficient and Guaranteed Unlearning Framework for LLMs](https://mlsanity.com/paper/2504.13774/) (2025)
- [ISACL: Internal State Analyzer for Copyrighted Training Data Leakage](https://mlsanity.com/paper/2508.17767/) (2025)

## Built on by (most cited first, 1 of 1)

- [LLM-Oriented Information Retrieval: A Denoising-First Perspective](https://mlsanity.com/paper/2605.00505/) (2026)

## Abstract (arXiv)

We present Copyright Detective, the first interactive forensic system for detecting, analyzing, and visualizing potential copyright risks in LLM outputs. The system treats copyright infringement versus compliance as an evidence discovery process rather than a static classification task due to the complex nature of copyright law. It integrates multiple detection paradigms, including content recall testing, paraphrase-level similarity analysis, persuasive jailbreak probing, and unlearning verification, within a unified and extensible framework. Through interactive prompting, response collection, and iterative workflows, our system enables systematic auditing of verbatim memorization and paraphrase-level leakage, supporting responsible deployment and transparent evaluation of LLM copyright risks even with black-box access.