mlsanityData to 7 Oct 2026

FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences

arXiv 2606.03330 ↗First posted 2 Jun 2026cs.LG cs.AI cs.CRcited by 3

Not on the map. Why?

Abstract (arXiv)

Literature reveals that a Large Language Model's (LLM) behavior is not only conditioned by its original weights but also its instance-level parameters, such as instructional prompt, sampling configuration or quantization. A model that generates safe outputs under one configuration may produce toxic content under another. However, current LLM identification techniques (such as fingerprinting) focus on intellectual property protection, and their design favors robustness to changes in these instance-level parameters. This poses a critical challenge for AI regulation in which compliance assessments target actual deployed behaviors, not model provenance. In this paper, we introduce instance-level fingerprinting, a regulator-oriented paradigm that distinguishes configurations of the same LLM. Our method FLIPS, exploits biases in generated binary random sequences to reach 96% (closed-set) and 90% (open-set, where some targets are unknown) identification accuracy across 237 model instances, versus 35% for the adapted LLMmap baseline. This shows that instance-level fingerprinting is both necessary for regulation and practically feasible. Code available at https://github.com/GurvanR/FLIPS-LLM-Instance-Fingerprinting.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 32 of its 49 references that are in the map. First posted on arXiv 2 Jun 2026.

Builds on

32 of 49 references.

References · 32

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  2. 2024Refusal in Language Models Is Mediated by a Single Directioncited by 960
  3. 2023Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructionscited by 377
  4. 2024OR-Bench: An Over-Refusal Benchmark for Large Language Modelscited by 222
  5. 2024Non-Determinism of "Deterministic" LLM Settingscited by 84
  6. 2019IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundarycited by 68
  7. 2025Language Models Use Trigonometry to Do Additioncited by 68
  8. 2022Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbationscited by 58
  9. 2024SG-Bench: Evaluating LLM Safety Generalization Across Diverse Tasks and Prompt Typescited by 58
  10. 2024Open Problems in Technical AI Governancecited by 45
  11. 2024Model Equality Testing: Which Model Is This API Serving?cited by 44
  12. 2024TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identificationcited by 33
20 more
  1. 2025Optimizing Temperature for Language Models with Multi-Sample Inferencecited by 33
  2. 2024A Fingerprint for Large Language Modelscited by 26
  3. 2025How Benchmark Prediction from Fewer Data Misses the Markcited by 26
  4. 2024Heads, Tails, and AI Fails: LLMs, Randomness, and Human Judgmentscited by 23
  5. 2025Position is Power: System Prompts as a Mechanism of Bias in Large Language Models (LLMs)cited by 19
  6. 2025Investigating the Impact of Quantization Methods on the Safety and Reliability of Large Language Modelscited by 17
  7. 2022MetaV: A Meta-Verifier Approach to Task-Agnostic Model Fingerprintingcited by 16
  8. 2025Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!cited by 16
  9. 2024ProFLingo: A Fingerprinting-based Intellectual Property Protection Scheme for Large Language Modelscited by 15
  10. 2025SoK: Large Language Model Copyright Auditing via Fingerprintingcited by 14
  11. 2023Arithmetic with Language Models: from Memorization to Computationcited by 12
  12. 2025Monte Carlo Temperature: a robust sampling strategy for LLM's uncertainty quantification methodscited by 12
  13. 2024HarmLevelBench: Evaluating Harm-Level Compliance and the Impact of Quantization on Model Alignmentcited by 9
  14. 2025DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protectioncited by 8
  15. 2024A Comparison of Large Language Model and Human Performance on Random Number Generation Taskscited by 7
  16. 2025Deterministic or probabilistic? The psychology of LLMs as random number generatorscited by 6
  17. 2025RAFP: Identifying LLM Lineages via Rare-Region Fingerprintscited by 6
  18. 2025A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectivescited by 5
  19. 2024LLMs Prompted for Graphs: Hallucinations and Generative Capabilitiescited by 3
  20. 2025How Quantization Shapes Bias in Large Language Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attackscited by 0
  2. 2026Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIscited by 0
  3. 2026Reasoning-Token Spikes Under Prompted Untruthful Responding in Large Language Modelscited by 0