Challenge: Large language models (LLMs) generate coherent, human-like text at scale, but raises concerns about authenticity and trust.
Approach: They propose a threat of watermark spoofing that allows a malicious model to generate text containing the authentic-looking watermark of a trusted, victim model.
Outcome: The proposed attack repurposes watermark radioactivity from a discoverable trait into an attack vector and replicates it.

Similar Papers

Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation? (2025.acl-long)

Copied to clipboard

Challenge: Large Language Model (LLM) watermarking is radioactive and enables the detection of watermarks inherited by student models when trained on the outputs of watermarked teacher models.
Approach: They propose two types of watermark removal attacks that allow student models to perform untraceable knowledge distillation while avoiding watermark inheritance.
Outcome: The proposed attacks eliminate inherited watermarks while maintaining knowledge transfer efficiency and low computational overhead.
ReasMark: A Robust Watermark for Attributing LLM Reasoning Under Knowledge Distillation Attacks (2026.acl-long)

Copied to clipboard

Challenge: Existing reasoning-enhanced large language models fail to provide reliable attribution of reasoning behavior once it is transferred through knowledge distillation.
Approach: They propose to embed a reasoning-length gap in a model by querying a target domain and training a local student to imitate its outputs.
Outcome: et al. show that ReasMark outperforms baselines while preserving task utility.
Distillation-Resistant Watermarking for Model Protection in NLP (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing protection methods such as watermarking only work for images but are not applicable to text.
Approach: They propose a technique that injects watermarks into the victim’s prediction probability corresponding to a secret key and is able to detect such a key by probing a suspect model.
Outcome: The proposed technique detects stealing suspects at 100% accuracy on four NLP tasks while the prior method fails on two.
Robust Data Watermarking in Language Models by Injecting Fictitious Knowledge (2025.findings-acl)

Copied to clipboard

Challenge: Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership.
Approach: They propose a data watermarking approach that injects coherent and plausible yet fictitious knowledge into training data using generated passages describing a fictious entity and its associated attributes.
Outcome: The proposed method is designed to be memorized by the LLM, and that increasing their density, length, and diversity of attributes strengthens their memorization.
Watermark under Fire: A Robustness Evaluation of LLM Watermarking (2025.findings-emnlp)

Copied to clipboard

Challenge: Various watermarking methods have been proposed to identify LLM-generated texts . lack of unified evaluation platforms has left many critical questions unanswered .
Approach: They systematize existing LLM watermarkers and watermark removal attacks and develop a unified platform that integrates them.
Outcome: The proposed systematizes existing LLM watermarkers and watermark removal attacks, mapping out their design spaces.
CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing (2025.emnlp-main)

Copied to clipboard

Challenge: Open-source code language models (code LMs) are a growing threat for intellectual property protection.
Approach: They propose a black-box code LM watermarking framework that uses rule-based watermarks and utility-preserving injection method for user-level model tracing.
Outcome: The proposed framework shows that it performs well across multiple state-of-the-art code LMs and is harmless compared to existing baselines.
WASA: WAtermark-based Source Attribution for Large Language Model-Generated Data (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have impressive performance but intellectual property concerns are looming . a framework that can be used to perform source attribution for LLMs can be developed.
Approach: They propose a framework that enables an LLM to generate synthetic texts with embedded watermarks that contain information about their source.
Outcome: The proposed framework achieves source attribution accuracy and robustness against adversaries.
PostMark: A Robust Blackbox Watermark for Large Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods to detect LLM-generated text require access to the underlying LLM’s logits, which LLM providers are loath to share due to fears of model distillation.
Approach: They develop a post-hoc watermarking procedure that inserts an input-dependent set of words into the text after the decoding process has completed.
Outcome: The proposed method is more robust to paraphrasing attacks than existing methods.
MarkLLM: An Open-Source Toolkit for LLM Watermarking (2024.emnlp-demo)

Copied to clipboard

Challenge: Large Language Models (LLMs) embed imperceptible yet algorithmically detectable signals in outputs to identify LLM-generated text.
Approach: They propose to develop an open-source toolkit for LLM watermarking that embeds imperceptible yet algorithmically detectable signals in model outputs to identify LLM-generated text.
Outcome: MarkLLM provides a unified framework for implementing LLM watermarking algorithms, while providing user-friendly interfaces to ensure ease of access.
Protecting Language Models Against Unauthorized Distillation through Trace Rewriting (2026.acl-long)

Copied to clipboard

Challenge: Knowledge distillation is a widely adopted technique for transferring capabilities from LLMs to smaller, more efficient student models.
Approach: They propose methods for modifying teacher-generated reasoning traces to achieve two objectives that deter unauthorized distillation: (1) anti-distillation, or degrading the training usefulness of query responses; and (2) API watermarking, which embeds verifiable signatures in student models.
Outcome: The proposed method achieves strong anti-distillation effect while maintaining or even improving teacher performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations