ML Security Papers

ML04

Membership Inference Attack

Detecting if data was used to train an ML model

211 papers Browse all papers

Monthly publications

Paper types

attack 83

defense 56

benchmark 46

survey 16

tool 10

Domains

nlp 102

vision 68

tabular 36

generative 29

federated-learning 20

multimodal 15

timeseries 11

graph 10

audio 6

reinforcement-learning 2

Co-occurring categories

Other OWASP categories that appear on the same papers

ML03 Model Inversion Attack

LLM06 Sensitive Information Disclosure

LLM01 Prompt Injection

ML05 Model Theft

ML01 Input Manipulation Attack

ML10 Model Poisoning

ML02 Data Poisoning Attack

ML09 Output Integrity Attack

ML06 AI Supply Chain Attacks

ML07 Transfer Learning Attack

Top cited papers

Hubble: a Model Suite to Advance the Study of LLM Memorization

Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesis

ContextLeak: Auditing Leakage in Private In-Context Learning Methods

SoK: Systematic analysis of adversarial threats against deep learning approaches for autonomous anomaly detection systems in SDN-IoT networks

AdaMixup: A Dynamic Defense Framework for Membership Inference Attack Mitigation

Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts

RAG Security and Privacy: Formalizing the Threat Model and Attack Surface

SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling

Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure

FiMMIA: scaling semantic perturbation-based membership inference across modalities

Browse all 211 papers