ML Security Papers

LLM10

Model Theft

Stealing LLM models

58 papers Browse all papers

Monthly publications

Paper types

defense 45

attack 10

benchmark 2

survey 1

Domains

nlp 58

multimodal 3

vision 2

Co-occurring categories

Other OWASP categories that appear on the same papers

ML05 Model Theft

ML09 Output Integrity Attack

LLM01 Prompt Injection

Top cited papers

Are Robust LLM Fingerprints Adversarially Robust?

DNF: Dual-Layer Nested Fingerprinting for Large Language Model Intellectual Property Protection

SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From

Verifying LLM Inference to Detect Model Weight Exfiltration

$δ$-STEAL: LLM Stealing Attack with Local Differential Privacy

TZ-LLM: Protecting On-Device Large Language Models with Arm TrustZone

Information-Preserving Reformulation of Reasoning Traces for Antidistillation

Model Correlation Detection via Random Selection Probing

SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting

Fingerprinting LLMs via Prompt Injection

Browse all 58 papers