Pith. sign in

REVIEW 9 cited by

DE-COP: Detecting Copyrighted Content in Language Models Training Data

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.09910 v2 pith:742LGJGJ submitted 2024-02-15 cs.CL cs.LG

classification cs.CLcs.LG
keywords de-coptrainingcontentcopyrightedlanguagemodelmodelsprior
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

How can we detect if copyrighted content was used in the training process of a language model, considering that the training data is typically undisclosed? We are motivated by the premise that a language model is likely to identify verbatim excerpts from its training text. We propose DE-COP, a method to determine whether a piece of copyrighted content was included in training. DE-COP's core approach is to probe an LLM with multiple-choice questions, whose options include both verbatim text and their paraphrases. We construct BookTection, a benchmark with excerpts from 165 books published prior and subsequent to a model's training cutoff, along with their paraphrases. Our experiments show that DE-COP surpasses the prior best method by 9.6% in detection performance (AUC) on models with logits available. Moreover, DE-COP also achieves an average accuracy of 72% for detecting suspect books on fully black-box models where prior methods give approximately 4% accuracy. The code and datasets are available at https://github.com/LeiLiLab/DE-COP.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs

    cs.CR 2025-06 conditional novelty 7.0 of 10

    A new attack, DDE, extracts supervised fine-tuning data from LLMs by exploiting low-confidence tokens and comparing fine-tuned versus base model generation branches.

  2. Unlocking Post-hoc Dataset Inference with Synthetic Data

    cs.LG 2025-06 conditional novelty 7.0 of 10

    Synthetic suffix-completion data, plus a dual-classifier t-test calibration, enables Dataset Inference to detect training membership while avoiding the false positives caused by distribution shift.

  3. PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglement

    cs.CR 2026-07 conditional novelty 6.0 of 10

    Existing MLLM unlearning methods reduce private-attribute leakage on entangled images but substantially harm co-occurring public figures and landmarks, with private knowledge often re-emerging after public finetuning.

  4. Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Framework

    cs.AI 2025-07 reject novelty 6.0 of 10

    NA-PDD detects pre-training data in LLMs by comparing which neurons activate for a test text against neurons linked to known training versus non-training texts, and claims large AUC improvements on three benchmarks.

  5. Automatic Calibration for Membership Inference Attack on Large Language Models

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A temperature-calibrated scoring method, ACMIA, improves membership inference against LLMs by amplifying probability gaps between training and non-training texts without reference models.

  6. Investigating the Feasibility of Mitigating Potential Copyright Infringement via Large Language Model Unlearning

    cs.CL 2024-12 conditional novelty 6.0 of 10

    SSU combines task-vector negation, random-label loss, and weight saliency to forget copyrighted books sequentially while retaining more general language ability than existing baselines.

  7. LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage

    cs.CR 2024-12 conditional novelty 6.0 of 10

    An RL-trained prompt generator outperforms rule-based and fuzzing baselines at extracting system prompts and training data from black-box LLMs.

  8. SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks

    cs.CR 2025-06 conditional novelty 5.0 of 10

    SOFT paraphrases low-loss fine-tuning samples before training, reducing MIA AUC from about 0.82 to about 0.54 across six datasets at roughly 7% perplexity cost.

  9. On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs

    cs.CR 2024-12 reject novelty 4.0 of 10

    Applying CVSS, DREAD, OWASP, and SSVC to 56 adversarial LLM attacks via three LLM judges yields near-constant factor scores, which the authors take as evidence that these metrics cannot differentiate LLM attacks.

Pith tools