Pith. sign in

REVIEW 4 cited by

Watermarking Pre-trained Language Models with Backdooring

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 2210.07543 v2 pith:TZEWO3XP submitted 2022-10-14 cs.CL cs.LG

Watermarking Pre-trained Language Models with Backdooring

classification cs.CL cs.LG
keywords plmslanguagedatasetsdownstreamfine-tunedhardmodelsmultiple
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large pre-trained language models (PLMs) have proven to be a crucial component of modern natural language processing systems. PLMs typically need to be fine-tuned on task-specific downstream datasets, which makes it hard to claim the ownership of PLMs and protect the developer's intellectual property due to the catastrophic forgetting phenomenon. We show that PLMs can be watermarked with a multi-task learning framework by embedding backdoors triggered by specific inputs defined by the owners, and those watermarks are hard to remove even though the watermarked PLMs are fine-tuned on multiple downstream tasks. In addition to using some rare words as triggers, we also show that the combination of common words can be used as backdoor triggers to avoid them being easily detected. Extensive experiments on multiple datasets demonstrate that the embedded watermarks can be robustly extracted with a high success rate and less influenced by the follow-up fine-tuning.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. SWAN: Semantic Watermarking with Abstract Meaning Representation

    cs.CL 2026-05 unverdicted novelty 7.0

    SWAN uses AMR to embed semantic watermarks that persist through paraphrases, matching SOTA detection on original text and improving AUC by 13.9 points on paraphrased RealNews data.

  2. Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends

    cs.CR 2025-08 accept novelty 7.0

    A survey of LLM copyright protection that unifies text watermarking, model watermarking, and model fingerprinting while presenting new coverage of fingerprint transfer and removal.

  3. Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP

    cs.LG 2024-12 conditional novelty 7.0

    PAR fine-tunes CLIP to remove backdoors from structured triggers while preserving standard performance, and works even with only synthetic image-text pairs.

  4. Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation

    cs.CR 2026-05 unverdicted novelty 6.0

    P2F generates low-rank parameter increments for LLM fingerprinting directly from textual descriptions in a single forward pass.