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.
A watermark for large language models.arXiv preprint arXiv:2301.10226, 2023a
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7verdicts
UNVERDICTED 7representative citing papers
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
TextSeal provides a localized, distortion-free LLM watermark that enables provenance tracking and distillation detection while preserving performance and text quality.
Existing LLM watermarking schemes can be defeated by semantic-preserving attacks including lexical changes, machine translation, and neural paraphrasing.
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
Chained rewrites by open-weight LLMs reduce watermark detection on diffusion LM outputs from 87.9% to 4.86% after five steps across multiple styles and models.
LLMSniffer improves detection of LLM-generated code on GPTSniffer and Whodunit benchmarks by fine-tuning GraphCodeBERT via two-stage supervised contrastive learning plus preprocessing and MLP classification.
citing papers explorer
-
SWAN: Semantic Watermarking with Abstract Meaning Representation
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.
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection
TextSeal provides a localized, distortion-free LLM watermark that enables provenance tracking and distillation detection while preserving performance and text quality.
-
Vaporizer: Breaking Watermarking Schemes for Large Language Model Outputs
Existing LLM watermarking schemes can be defeated by semantic-preserving attacks including lexical changes, machine translation, and neural paraphrasing.
-
Response Time Enhances Alignment with Heterogeneous Preferences
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
-
Chainwash: Multi-Step Rewriting Attacks on Diffusion Language Model Watermarks
Chained rewrites by open-weight LLMs reduce watermark detection on diffusion LM outputs from 87.9% to 4.86% after five steps across multiple styles and models.
-
LLMSniffer: Detecting LLM-Generated Code via GraphCodeBERT and Supervised Contrastive Learning
LLMSniffer improves detection of LLM-generated code on GPTSniffer and Whodunit benchmarks by fine-tuning GraphCodeBERT via two-stage supervised contrastive learning plus preprocessing and MLP classification.