This work introduces AuxMark, a behavioral watermarking framework for tracing unauthorized agent distillation and dynamically inserts safe, non-essential auxiliary action into teacher trajectories, and stores the associated contexts as private evidence cards.
Abstract
Large language model agents can acquire complex capabilities through multi-step interaction and tool use, but their trajectories can also be illegally collected to dis- till student agents. However, existing watermarking methods either do not fit the structured and interactive nature of agent environments or lack reliable effective- ness across tasks and model architectures. We introduce AuxMark, a behavioral watermarking framework for tracing unauthorized agent distillation. AuxMark dynamically inserts safe, non-essential auxiliary action into teacher trajectories, and stores the associated contexts as private evidence cards. To audit a suspicious student model, AuxMark constructs paired real and fake probes from these cards and applies a card-level sign test. This black-box protocol supports both model- level detection and trace-level attribution. Across three agent benchmarks, two teacher agents, and four student architectures, AuxMark detects all 24 distilled models with zero false positives on 48 clean models. It also preserves task utility and remains effective against data flooding, paraphrasing, truncation, and adaptive cleaning attacks. Our code will be released at this URL.
Skills extend an agent's capabilities by injecting instructions and information into the context, and are widely used by agents such as OpenClaw and Claude Code. Prior work shows third-party marketplaces host malicious skills that give attackers direct influence over the victim's agent. The emerging defense scans skill...
Two universal tool-based defenses are introduced: Attacker Tool Filtering, which uses anomaly detection to identify and remove suspicious tools, and Normal Tool Recalling, a white-box method that restores the agent's original toolset prior to planning.
Verifying the provenance of autonomous LLM agents is a critical security challenge. Existing semantic attribution is easily obfuscated by system prompts, while active watermarking conflicts with schema-constrained tool generation. We propose AgentTrace, an active framework that identifies the foundation model behind a...
This work presents LIDAR (LLM Identification from Decisions and Actions at Runtime), an active black-box fingerprinting method for coding-agent execution that achieves high Top-1 accuracy and MRR and outperforms four existing fingerprinting and API-auditing baselines.
Chu-Yi Wang, Xiao-Hui Xie, Tong-Ze Wang et al.· 2 citations· ⚡1
RAISED substantially reduces the attack success rate of prompt injections in tool responses while, unlike prior training-based defenses, preserving utility on both agentic and general-purpose benchmarks.
Mohamed Dhouib, Clément Elliker, Alexi Canesse et al.· 1 citation
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
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.