ML04
Membership Inference Attack
Detecting if data was used to train an ML model
226 papers Browse all papers
Monthly publications
Paper types
attack 92
defense 60
benchmark 48
survey 16
tool 10
Domains
nlp 109
vision 73
tabular 39
generative 30
federated-learning 24
multimodal 15
timeseries 12
graph 10
audio 6
reinforcement-learning 2
Co-occurring categories
Other OWASP categories that appear on the same papers
ML03 Model Inversion Attack
42 LLM06 Sensitive Information Disclosure
34 LLM01 Prompt Injection
5 ML01 Input Manipulation Attack
5 ML02 Data Poisoning Attack
4 ML05 Model Theft
4 ML10 Model Poisoning
3 ML09 Output Integrity Attack
2 LS06 Red-Team Agents
2 ML06 AI Supply Chain Attacks
1 LS01 Vulnerability Discovery
1 ML07 Transfer Learning Attack
1 LS05 Triage & Prioritization
1Top cited papers
162633435362728292101
Hubble: a Model Suite to Advance the Study of LLM Memorization
2025 benchmark
Synth-MIA: A Testbed for Auditing Privacy Leakage in Tabular Data Synthesis
2025 tool
ContextLeak: Auditing Leakage in Private In-Context Learning Methods
2025 benchmark
AdaMixup: A Dynamic Defense Framework for Membership Inference Attack Mitigation
2025 defense
SoK: Systematic analysis of adversarial threats against deep learning approaches for autonomous anomaly detection systems in SDN-IoT networks
2025 survey
Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure
2025 attack
RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
2025 survey
SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
2025 attack
Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
2025 attack
Unlearning Imperative: Securing Trustworthy and Responsible LLMs through Engineered Forgetting
2025 survey