Skip to content
Preprint

TrajMark: Ownership Attribution and Segment-Level Tamper Localization for Coding-Agent Trajectories

Sep 2026 · 1 citation · 58 references
Computer Science

TL;DR

TrajMark is proposed, a training-free, symmetric-key, visible-only trajectory watermarking framework that separates robust ownership attribution from fragile local integrity verification, and provides a design-level analysis of owner recoverability, integrity collision probability, structural overhead, and localization behavior.

Abstract

Watermarking the final patch produced by a coding agent provides provenance evidence for the submitted artifact, but does not authenticate the visible process that produced it. Behavioral watermarking methods primarily provide a global detection or identifier-recovery signal, so a locally edited trajectory may retain sufficient ownership evidence without revealing which protected region has become inconsistent. To address this limitation, we propose TrajMark, a training-free, symmetric-key, visible-only trajectory watermarking framework that separates robust ownership attribution from fragile local integrity verification. Our framework consists of two complementary layers: a sparse owner layer that encodes a six-bit deployment identifier by rewriting a keyed subset of naturally occurring READ actions into masked linear equations, and a localization layer that inserts linked Q12 ordinary, group, and terminal seals to commit to protected critical-action segments. This separation allows ownership evidence to accumulate robustly across trajectories, while local modifications perturb nearby keyed commitments and expose the affected protocol region. We further provide a design-level analysis of owner recoverability, integrity collision probability, structural overhead, and localization behavior. Across three coding-agent frameworks and three LLMs, TrajMark recovers the exact owner in all evaluated clean full-watermark batches. Under exhaustive eligible single-site attacks it detects 95.5%-100% of edits, and under random single-action corruption it localizes 95.8% of modified sites to an accepted protocol region rather than to the individual action. Owner marking adds no trajectory actions; the integrity layer adds explicit read-only seals, and matched Pass@1 is 26.9% versus 26.3% for unwatermarked runs.

View source

Similar papers

Preprint Oct 2026

Session-Bound Behavioral Watermarking for Autonomous LLM Agents

Large Language Model (LLM) agents are increasingly acting through Web interfaces and external tools. They produce trajectories. Those trajectories may pass through several intermediaries. They can store, modify, or dispute those trajectories. In Web-based agent deployments, trajectories may pass through APIs, marketpla...

Md Facklasur Rahaman, Yong Xiang, Md. Palash Uddin et al. · 0 citations
Preprint Sep 2026

LoRo-Mark:Provably Lossless and Robust Agent Watermarking

As LLM agents are increasingly deployed as commercial services, protecting proprietary orchestration logic and tool-use policies is important. We consider agent repackaging: an adversary integrates a protected agent into its own application via API and presents it under its own identity. It may modify parts of executio...

Hao-Yang Zou, Yao-Zi Wang, Jun Yao et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Semantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM Agents

Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Prior agent watermarks break in two ways. First, all three prior schemes bind the watermark to the exact action symbol, so renaming a tool desynchronizes decoding even when t...

Su-Xin Ji, Hung-Tao Wan, Shao-Xuan Chen et al. · 0 citations
#artificial intelligence Preprint Oct 2026

SkillMarker: A KGW-Based Watermarking Method for Agent Skill Ownership Verification

Agent skills encode operational procedures and domain expertise as reusable knowledge assets, yet their distribution in plaintext exposes them to unauthorized copying and leakage. However, practical mechanisms for skill ownership verification and leakage tracing remain underdeveloped. Watermark embedding before distrib...

Alan Tang, Li-Feng Wang, Gang Wu et al. · 0 citations
Book Open access Nov 2026

AnonAgentBench: Measuring Coding-Agent Utility Under Reversible Repository Anonymization

Organizations may want to use hosted coding agents on private repositories. However, a coding session can expose sensitive text through file reads, search results, test logs, stack traces, and patches. Cleaning only the initial prompt leaves these later channels exposed. We introduce AnonAgentBench, a benchmark for eva...

Luís Brito · 0 citations
Preprint Oct 2026

Decision Uncertainty-Oriented Watermarking (DUOW): Securing Multi-Agent Routing Against Policy Cloning

Routing policies in Multi-Agent Systems (MAS) represent valuable intellectual property, yet their exposure through execution logs creates significant risks of unauthorized policy cloning. Existing agent watermarking methods protect intellectual property by modifying internal generation processes, such as perturbing tok...

Zi-Ming Zhang, Li Li, Guo-Rui Feng et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.