Say Shibboleth: Fingerprinting the LLMs and Harnesses Behind Agentic Attacks
cs.CR, cs.AI
Submitted: 2026-11-09
Updated: 2026-11-18
Comments: v0.1
Code: https://github.com/SayShibboleth/Shibboleth
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Rouxii: Exploiting Honeypots with Deception-Aware AI Pentesters
- Trace: Unmasking AI Attack Agents Through Terminal Behavior Fingerprinting
- On the Internet, Nobody Knows You're an LLM Bot: Unmasking Web Agents with Multi-Layer Fingerprinting
- Countering Autonomous Cyber Threats
- Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents
- Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces
- Cybersecurity AI: Hacking the AI Hackers via Prompt Injection
- Red-Teaming the Agentic Red-Team
- LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild
- EmbeddingGemma: Powerful and Lightweight Text Representations
- The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
- Who Is Behind the Harness? Verifying Model Identity in Coding Agents through Behavioral Fingerprinting
- AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Web Penetration Agents
- AgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing Agents
- AgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data