Multi-Channel Spread-Spectrum Code Watermarking

• URL: http://arxiv.org/abs/2607.06009v1
• Date: Tue, 07 Jul 2026 08:50:19 GMT
• Title: Multi-Channel Spread-Spectrum Code Watermarking
• Abstract summary: We present multi-channel spread-spectrum watermarking with a 24-bit payload and formal robustness guarantees.<n>Across 1,750 Python files from CodeNet and from GPT-4.1 and Llama-4 generations, the watermark achieves 100% clean-detection accuracy with zero false positives.
• Score: 10.27405810850982
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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. Generation-time schemes require access to the producing model and cannot be applied to third-party code, while post-hoc schemes work on any code but carry at most 4 bits of payload, far too few to distinguish the many deployed model configurations. We present multi-channel spread-spectrum watermarking, the first post-hoc, training-free code watermark with a 24-bit payload and formal robustness guarantees. The scheme encodes bits in variable naming conventions and in eight pairs of semantically equivalent code patterns, and a keyed pseudo-random permutation maps every site to a codeword bit so that each bit receives multiple independent votes. Majority voting absorbs distributed corruption, while an outer Reed-Solomon code recovers the identifier when concentrated channel attacks defeat the vote, yielding provable robustness bounds for formatting, syntactic, and structural attacks. Across 1,750 Python files from CodeNet and from GPT-4.1 and Llama-4 generations, the watermark achieves 100% clean-detection accuracy with zero false positives. Under 17 attack types, it recovers the identifier at 97.6% accuracy under 8 variable renames and 94.1% under 10% random per-site corruption, while the strongest post-hoc baseline collapses to 0% under any single-transform attack. Embedding and detection together take under 200 ms on CPU without training data or GPU.

Related papers

• Asymmetric Phase Coding Video Watermarking [4.564848621539382]
  We present a training-free video watermark that removes the shared secret.<n>The signer embeds a complete Ed25519 signature into the phase spectrum of the chroma plane.<n>On 1000 uncurated real-world clips the system ships a verifying signature for 99.3% of the corpus and accepts a wrong public key zero times in 1000 attempts.
  arXiv  Detail & Related papers  (2026-08-29T11:53:25Z)
• Open-Source Intelligence for Code Provenance and the Security Patterns that Separate Human and Large-Language-Model Implementations of Common Programming Tasks [0.0]
  Developers now draw code from two very different sources.<n>Can the provenance of a code snippet be recovered from the code itself?<n>Do the two sources differ in the security patterns they adopt for the same task?
  arXiv  Detail & Related papers  (2026-07-14T08:59:42Z)
• BitC-3DGS: High-Capacity 3D Gaussian Splatting Watermarking via Bit Compression [68.33622936663876]
  High-capacity watermarking is necessary for 3D Gaussian Splatting (3DGS) assets to embed rich information.<n>Existing bit-to-token watermarking methods are limited to 77-bit messages due to CLIP's fixed 77-token context length.<n>We introduce BitC-3DGS, a bit-compression framework that encodes multiple message bits per token.
  arXiv  Detail & Related papers  (2026-05-28T08:28:04Z)
• Every Bit, Everywhere, All at Once: A Binomial Multibit LLM Watermark [16.543554028816477]
  We introduce binomial encoding to encode every bit of the payload at every token position.<n>We complement our approach with a stateful encoder that dynamically redirects encoding pressure toward underencoded bits.<n>Our scheme achieves superior message accuracy and robustness, with the gap to baseline methods widening.
  arXiv  Detail & Related papers  (2026-05-12T07:14:45Z)
• Asymmetric Phase Coding Audio Watermarking [7.627186551029829]
  Deepfake audio challenges voice-based authentication systems.<n>We propose Asymmetric Phase Coding, a training-free cryptographic signing layer for audio.<n>We achieve cryptographic verification rates between 97.5% and 98.3% on every condition at meanQ.02 and tens-of-milliseconds latency.
  arXiv  Detail & Related papers  (2026-05-08T04:54:59Z)
• Chainwash: Multi-Step Rewriting Attacks on Diffusion Language Model Watermarks [0.0]
  This paper studies what happens when watermarked text is rewritten not once but several times.<n>The watermark is detected on 87.9% of the original outputs at the standard significance threshold.<n>After five chained rewrites, detection falls to 4.86%, meaning 94.76% of the originally detected texts are no longer flagged.
  arXiv  Detail & Related papers  (2026-05-06T23:00:26Z)
• VibeGuard: A Security Gate Framework for AI-Generated Code [0.11080037957254413]
  Anthropic's Claude Code CLI shipped a 59.8 MB source map file in its npm package exposing 512,000 lines of proprietary TypeScript.<n>We present VibeGuard, a pre-publish security gate that targets five such blind spots.<n>We discuss how these results inform a defense-in-depth workflow for teams that rely on AI code generation.
  arXiv  Detail & Related papers  (2026-04-01T15:57:01Z)
• Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice [23.788321123219244]
  Distinguishing AI-generated code from human-written code is crucial for authorship attribution, content tracking, and misuse detection.<n>N-gram-based watermarking schemes have emerged as prominent, which inject secret watermarks to be detected during the generation.<n>Most claims rely solely on defenses against simple code transformations or code optimizations as a simulation of attack, creating a questionable sense of robustness.
  arXiv  Detail & Related papers  (2025-07-07T22:18:19Z)
• Decompiling Smart Contracts with a Large Language Model [51.49197239479266]
  Despite Etherscan's 78,047,845 smart contracts deployed on (as of May 26, 2025), a mere 767,520 ( 1%) are open source.<n>This opacity necessitates the automated semantic analysis of on-chain smart contract bytecode.<n>We introduce a pioneering decompilation pipeline that transforms bytecode into human-readable and semantically faithful Solidity code.
  arXiv  Detail & Related papers  (2025-06-24T13:42:59Z)
• Zero-Shot Detection of Machine-Generated Codes [83.0342513054389]
  This work proposes a training-free approach for the detection of LLMs-generated codes. We find that existing training-based or zero-shot text detectors are ineffective in detecting code. Our method exhibits robustness against revision attacks and generalizes well to Java codes.
  arXiv  Detail & Related papers  (2023-10-08T10:08:21Z)
• An Unforgeable Publicly Verifiable Watermark for Large Language Models [84.2805275589553]
  Current watermark detection algorithms require the secret key used in the watermark generation process, making them susceptible to security breaches and counterfeiting during public detection. We propose an unforgeable publicly verifiable watermark algorithm named UPV that uses two different neural networks for watermark generation and detection, instead of using the same key at both stages.
  arXiv  Detail & Related papers  (2023-07-30T13:43:27Z)
• Who Wrote this Code? Watermarking for Code Generation [53.24895162874416]
  We propose Selective WatErmarking via Entropy Thresholding (SWEET) to detect machine-generated text. Our experiments show that SWEET significantly improves code quality preservation while outperforming all baselines.
  arXiv  Detail & Related papers  (2023-05-24T11:49:52Z)
• Watermarking Text Generated by Black-Box Language Models [103.52541557216766]
  A watermark-based method was proposed for white-box LLMs, allowing them to embed watermarks during text generation. A detection algorithm aware of the list can identify the watermarked text. We develop a watermarking framework for black-box language model usage scenarios.
  arXiv  Detail & Related papers  (2023-05-14T07:37:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.