This paper introduces HiTMS, a method for concealing secrets in large language models across multiple responses in successive rounds, improving throughput and reducing steganalyzer detection.

The paper introduces ReTokSync, a self-synchronizing framework that resolves tokenization ambiguity in Generative Linguistic Steganography (GLS) by correcting mismatches only when they occur, thereby…

The paper introduces a novel framework using steganographic canary files to detect and block unauthorized processing of sensitive documents by LLMs, even when the data passes through traditional secur…

The paper proposes an efficient and provably secure linguistic steganography method using range coding that achieves high embedding capacity and speed, outperforming existing methods.

The paper introduces LUNA, a linguistically adaptive watermarking technique that achieves high detection accuracy across diverse languages while maintaining minimal text distortion, outperforming exis…

The paper proposes a provably secure steganography scheme based on list decoding that significantly increases embedding capacity for Large Language Models (LLMs) compared to existing methods.

TextSeal is a novel, non-overhead, and robust watermark for LLMs that enables accurate provenance tracking and detection of unauthorized use even after model distillation.

The paper analyzes the robustness of current LLM watermarking schemes against various text modifications, concluding that watermarks can be removed with reasonable effort.

This paper develops provably undetectable and robust watermarking schemes for LLM outputs even when the per-token entropy is only constant, removing previous dependencies on high entropy rates or larg…

The paper proposes a novel global sketch-based watermarking technique for diffusion language models that controls the entire sequence's statistics, offering an order-agnostic and context-independent a…

PASA introduces a robust, semantic-level watermarking technique that embeds and detects watermarks in the latent embedding space, successfully resisting semantic-invariant attacks like paraphrasing.

The paper proposes SSG, a novel logit-balanced vocabulary partitioning method, to enhance the watermark strength and detectability of LLM-generated content, especially in low-entropy domains like code…

The paper proposes REED, a post-training representation editing method that significantly improves cross-domain linguistic steganalysis performance by deterministically editing intermediate feature re…

The paper proposes RPSG, a method that uses private seeds and differential privacy to generate highly realistic and strongly privacy-preserving synthetic data replicas of private text for LLMs.

The paper proposes a secure and practical black-box text steganography method that uses a dynamic codebook and a multimodal LLM to embed secret messages into captions, outperforming existing technique…

XMark introduces a novel multi-bit watermarking technique that reliably embeds binary messages into LLM-generated text while maintaining high text quality and robust performance even with limited toke…

The paper demonstrates a class of steganographic exfiltration attacks against vector databases by hiding data within embeddings, and proposes VectorPin, a cryptographic provenance protocol to detect s…

The paper demonstrates that combining outputs from multiple large language models (LLMs) effectively cancels out statistical watermarks, revealing a fundamental vulnerability in current AI text detect…

The paper proposes a character-level differential privacy mechanism to sanitize sensitive user prompts for LLMs, achieving high privacy for PII while maintaining utility for non-sensitive context.

The paper argues that current AI content watermarking benchmarks fail to test for bias across different languages, cultures, and demographics, proposing a new set of evaluation standards to ensure fai…