AI ethics evidence index Search
Source-linked daily record
Evidence record 3533 · automatically gathered

AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing

Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and merging, which commonly arise under strong paraphrasers like DIPPER and GPT-3.5. To mitigate this issue, we propose AliMark, a framework that reformulates sentence-level watermarking as a bit sequence encoding and alignment problem between a potentially water

Record details

Published: 28 May 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Environment
Retrieved: 14 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

Also mentions OpenAI · Shared topic: Safety & alignment

A Counterexample to Fourier Alignment in Single-Neuron Modular Addition

arXiv cs.LG · 5 August 2026

Also mentions OpenAI · Shared topic: Safety & alignment

A Counterexample to Fourier Alignment in Single-Neuron Modular Addition

arXiv cs.LG · 5 August 2026

Also mentions OpenAI · Shared topic: Safety & alignment

We’re running out of reasons to ignore AI safety

The Verge · 29 July 2026

Also mentions OpenAI · Shared topic: Safety & alignment

Third-party cyber evaluations involving OpenAI models

Simon Willisons Weblog · 5 August 2026

Also mentions OpenAI · Shared topic: Safety & alignment

Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WER (13.8% cWER)

arXiv · 29 May 2026

Also mentions OpenAI · Shared topic: Safety & alignment

MultiTurnPSB: Evaluating Multi-Turn Jailbreak Attacks an dClassifier-Based Defenses for Medical AI Safety

arXiv · 30 May 2026

How to cite this record

ethics.ai (28 May 2026), “AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing,” evidence record 3533, https://ethics.ai/record/3533 (originally published by arXiv).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.