Attacks and Defenses Against LLM Fingerprinting
Not on the map. Why?
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 12 Aug 2025.
Builds on
21 of 32 references.
References · 21
- 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
- 2020Reinforcement Learning for Combinatorial Optimization: A Surveycited by 235
- 2023Harms from Increasingly Agentic Algorithmic Systemscited by 134
- 2024Is Cosine-Similarity of Embeddings Really About Similarity?cited by 89
- 2023Getting pwn'd by AI: Penetration Testing with Large Language Modelscited by 82
- 2024Instructional Fingerprinting of Large Language Modelscited by 64
- 2020Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routingcited by 61
- 2024LLMmap: Fingerprinting For Large Language Modelscited by 56
- 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
- 2020A Systematic Review on Model Watermarking for Neural Networkscited by 49
- 2023Adversarial Attacks and Defenses in Large Language Models: Old and New Threatscited by 49
- 2025CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimizationcited by 28
9 more
- 2024A Fingerprint for Large Language Modelscited by 26
- 2020Generalization to New Actions in Reinforcement Learningcited by 25
- 2023In-Context Reinforcement Learning for Variable Action Spacescited by 23
- 2022A Survey of Adversarial Defences and Robustness in NLPcited by 22
- 2023Demystifying Embedding Spaces using Large Language Modelscited by 17
- 2022Paraphrase Identification with Deep Learning: A Review of Datasets and Methodscited by 13
- 2024Language Guided Exploration for RL Agents in Text Environmentscited by 9
- 2025ImF: Implicit Fingerprint for Large Language Modelscited by 5
- 2025Improving LLM Agents with Reinforcement Learning on Cryptographic CTF Challengescited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.