# Attacks and Defenses Against LLM Fingerprinting

arXiv: https://arxiv.org/abs/2508.09021 · HTML: https://mlsanity.com/paper/2508.09021/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Builds on (most cited first, 21 of 21)

- [Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring](https://mlsanity.com/paper/1802.04633/) (2018)
- [Reinforcement Learning for Combinatorial Optimization: A Survey](https://mlsanity.com/paper/2003.03600/) (2020)
- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [Is Cosine-Similarity of Embeddings Really About Similarity?](https://mlsanity.com/paper/2403.05440/) (2024)
- [Getting pwn'd by AI: Penetration Testing with Large Language Models](https://mlsanity.com/paper/2308.00121/) (2023)
- [Instructional Fingerprinting of Large Language Models](https://mlsanity.com/paper/2401.12255/) (2024)
- [Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing](https://mlsanity.com/paper/2010.12001/) (2020)
- [LLMmap: Fingerprinting For Large Language Models](https://mlsanity.com/paper/2407.15847/) (2024)
- [A Systematic Review on Model Watermarking for Neural Networks](https://mlsanity.com/paper/2009.12153/) (2020)
- [Model Stealing Attacks Against Inductive Graph Neural Networks](https://mlsanity.com/paper/2112.08331/) (2021)
- [Adversarial Attacks and Defenses in Large Language Models: Old and New Threats](https://mlsanity.com/paper/2310.19737/) (2023)
- [CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization](https://mlsanity.com/paper/2504.04310/) (2025)
- [A Fingerprint for Large Language Models](https://mlsanity.com/paper/2407.01235/) (2024)
- [Generalization to New Actions in Reinforcement Learning](https://mlsanity.com/paper/2011.01928/) (2020)
- [In-Context Reinforcement Learning for Variable Action Spaces](https://mlsanity.com/paper/2312.13327/) (2023)
- [A Survey of Adversarial Defences and Robustness in NLP](https://mlsanity.com/paper/2203.06414/) (2022)
- [Demystifying Embedding Spaces using Large Language Models](https://mlsanity.com/paper/2310.04475/) (2023)
- [Paraphrase Identification with Deep Learning: A Review of Datasets and Methods](https://mlsanity.com/paper/2212.06933/) (2022)
- [Language Guided Exploration for RL Agents in Text Environments](https://mlsanity.com/paper/2403.03141/) (2024)
- [ImF: Implicit Fingerprint for Large Language Models](https://mlsanity.com/paper/2503.21805/) (2025)
- [Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challenges](https://mlsanity.com/paper/2506.02048/) (2025)

## Built on by (most cited first, 1 of 1)

- [SoK: Large Language Model Copyright Auditing via Fingerprinting](https://mlsanity.com/paper/2508.19843/) (2025)

## Abstract (arXiv)

As large language models are increasingly deployed in sensitive environments, fingerprinting attacks pose significant privacy and security risks. We present a study of LLM fingerprinting from both offensive and defensive perspectives. Our attack methodology uses reinforcement learning to automatically optimize query selection, achieving better fingerprinting accuracy with only 3 queries compared to randomly selecting 3 queries from the same pool. Our defensive approach employs semantic-preserving output filtering through a secondary LLM to obfuscate model identity while maintaining semantic integrity. The defensive method reduces fingerprinting accuracy across tested models while preserving output quality. These contributions show the potential to improve fingerprinting tools capabilities while providing practical mitigation strategies against fingerprinting attacks.