arXiv AI

Alignment Whack-a-Mole : Finetuning Activates Verbatim Recall of Copyrighted Books in Large Language Models

The paper demonstrates that fine‑tuning large language models on a single author’s works can trigger the models to reproduce large verbatim excerpts from copyrighted books, even when prompted only with semantic descriptions. Experiments on GPT‑4o, Gemini‑2.5‑Pro, and DeepSeek‑V3.1 show up to 85‑90% recall of held‑out books, with spans exceeding 460 words, and this effect generalizes across authors and model providers. The findings suggest that fine‑tuning reactivates latent memorization from pre‑training, revealing a widespread vulnerability in industry models.

arXiv Machine Learning
Sep 2

CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs

CopyShield is a benchmark that compares three copyright‑defense methods—contrastive decoding, Direct Preference Optimization (DPO), and activation intervention—across two large language models (LLaMA‑3.1‑8B and Mistral‑7B‑v0.3). The study uses controlled memorization of five public‑domain books to measure literal leakage, calibrated non‑literal leakage, utility, and degeneracy, finding that each intervention level yields distinct compliance‑utility trade‑offs. Results show contrastive decoding limits degeneracy but hits a suppression floor, DPO nearly eliminates literal leakage yet causes paraphrase‑loop degeneracy, and activation intervention blocks most non‑literal queries before generation, with human evaluation highlighting coherence and perceived copyright risk differences.

By Maryam Alshehyari, Dushyant Singh Chauhan, Samuele Poppi, Martin Takac, Salem Lahlou, Nils Lukas
arXiv AI
Jun 17

Combating Data Laundering in LLM Training

arXiv:2604. 01904v3 Announce Type: replace-cross Abstract: Post-hoc unauthorized-training data detection for large language models (LLMs) typically assumes a query-with-originals regime: rights holders query a target LLM with raw proprietary data and assess whether the model assigns them stronger memorization-based detection signals, e.

By Muxing Li, Zesheng Ye, Sharon Li, Feng Liu
arXiv AI
Aug 25

Deep Contrastive Unlearning for Language Models

Deep Contrastive Unlearning for Language Models (DeepCUT) is a framework that removes information from fine‑tuned language models by directly optimizing their latent space. It addresses the challenge of machine unlearning in black‑box models, which has been largely overlooked by previous work that only mitigated output effects. Experiments on real‑world datasets show that DeepCUT consistently outperforms baseline methods in both effectiveness and efficiency.

By Estrid He, Tabinda Sarwar, Ibrahim Khalil, Xun Yi, Ke Wang
arXiv Machine Learning
Jul 27

DCS: A Unified Conditional Sensitivity Framework for Cross-Modal Copyright Infringement Detection

arXiv:2607. 22035v1 Announce Type: new Abstract: Currently, most foundation models can reproduce or strongly depend on copyrighted training content, but output similarity alone is insufficient for infringement detection, because similar outputs may also arise from public-domain concepts, common stylistic conventions, or ordinary statistical generalization.

By Xiafeng Man
arXiv AI
Aug 3

TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text

arXiv:2607. 28862v1 Announce Type: cross Abstract: The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized data exploitation and privacy leakage.

By Chengshuai Zhao, Pingchuan Ma, Dawei Li, Bohan Jiang, Zhiyuan Yu, Zhen Tan, Huan Liu
arXiv Machine Learning
Jul 15

Extractable Memorization From First Principles

arXiv:2607. 12649v1 Announce Type: new Abstract: Recent work on extractable memorization in LLMs suffers from two contrasting validity problems.

By A. Feder Cooper, Marika Swanberg, Jamie Hayes, Lea Duesterwald, Christopher De Sa, Daniel E. Ho, Mark A. Lemley, Percy Liang