arXiv Computation and Language August 31, 2026 By Abdulrahman Diaa, Jonathan Petit, Florian Kerschbaum

Semantic Watermarking with Order-Robust Detection over Sub-sentence Units

Read the original on arXiv Computation and Language →

The paper introduces an adaptive embedding displacement attack (EDA) that exploits rewording, reordering, and resegmentation to remove semantic watermarks from text, achieving a 32.6%–47.9% success rate across four watermarking schemes. To counter this, the authors propose k‑SwordStamp, a semantic watermarking method that uses order‑robust detection over sub‑sentence units, significantly reducing vulnerability to structure‑based edits. Experiments show that EDA remains effective against k‑SwordStamp, but with a lower success rate (10.8%) compared to its performance on other schemes.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Machine Learning

Jun 18

Signature filtering: a lightweight enhancement for statistical watermark detection in large language models

arXiv:2606. 18430v1 Announce Type: new Abstract: Statistical watermarks help organizations attribute large language model (LLM) outputs, yet existing detectors often struggle when watermark signals are weak, texts are repetitive, or watermarks are edited.

By Chih-Duo Hong, Yen-Pang Chen, Fang Yu

llms rag benchmarks

arXiv Machine Learning

Jul 30

Adaptively Robust LLM Monitoring via Activation Watermarking

arXiv:2603. 23171v3 Announce Type: replace-cross Abstract: Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent.

By Toluwani Aremu, Daniil Ognev, Samuele Poppi, Nils Lukas

llms fine-tuning benchmarks safety

arXiv AI

Aug 14

Tracing Provenance and Detecting Tampering with Complementary LLM Watermarks

arXiv:2608. 12713v1 Announce Type: cross Abstract: Watermarking LLM-generated text is an important task for tracing its provenance.

By Xiaoyan Feng, Yanjun Zhang, He Zhang, Leo Yu Zhang, Shirui Pan

llms rag benchmarks

arXiv Computation and Language

4d ago

CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents

arXiv:2608. 28389v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) augments LLMs with external documents, but public or user-editable sources expose RAG systems to data poisoning: attackers can inject malicious documents to steer outputs toward targeted answers.

By Jaewon Jung, Haizhong Zheng, Hongsun Jang, Jaeyong Song, Beidi Chen, Jinho Lee

llms rag multimodal benchmarks safety

arXiv Computation and Language

2d ago

TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning

arXiv:2609.00470v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) grounds large language models in external corpora, but implicit trust in retrieved documents creates a critical at...

By Muhaimin Bin Munir, Akib Jawad Ononto, Nazia Shehnaz Joynab, Bhavani Thuraisingham, Latifur Khan

llms rag multimodal

arXiv AI

Jun 11

ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning

arXiv:2603. 22934v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) improves large language model applications by grounding generation in retrieved evidence, but also introduces corpus poisoning as a new attack surface.

By Xiangyu Yin, Yi Qi, Chih-Hong Cheng

llms rag