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.
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.
arXiv:2603. 23171v3 Announce Type: replace-cross Abstract: Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent.
arXiv:2608. 12713v1 Announce Type: cross Abstract: Watermarking LLM-generated text is an important task for tracing its provenance.
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.
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...
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.
arXiv:2607. 06009v1 Announce Type: cross Abstract: Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need.
arXiv:2602. 09611v2 Announce Type: replace-cross Abstract: Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs).
IRIS is a training‑free watermarking scheme for diffusion‑generated images that binds a watermark to the image’s visual semantics. It derives an intrinsic ring identifier from a content code of the non‑watermarked image and injects it late in the generation trajectory, ensuring the mark survives common processing while breaking under semantic changes or foreign images. Experiments on three prompt datasets show IRIS reliably detects watermarks, maintains fidelity to the original image, and resists forgery techniques that defeat other marks.
arXiv:2601. 11629v2 Announce Type: replace-cross Abstract: We demonstrate that while the current approaches for language model watermarking are effective for open-ended generation, they are inadequate at watermarking LM outputs for constrained generation tasks with low-entropy output spaces.
The paper investigates watermarking for large language model outputs, noting that stronger single-layer watermarks reduce token entropy and weaken subsequent layers. It demonstrates that detectability is limited by entropy and that watermark ensembles monotonically lower entropy and the green‑list ratio. The authors propose using weaker single‑layer watermarks to maintain entropy, showing through theory and experiments that this approach improves both detectability and robustness compared to strong baselines.
arXiv:2607. 05694v1 Announce Type: cross Abstract: Logit-based watermarking is a widely used mechanism for identifying LLM generated content, yet its effectiveness is governed by a fundamental trade-off between detectability and semantic distortion.