ML03
Model Inversion Attack
Reconstructing training data from ML model access
244 papers Browse all papers
Monthly publications
Paper types
defense 118
attack 70
benchmark 40
survey 13
tool 3
Domains
federated-learning 96
nlp 89
vision 89
generative 24
tabular 14
graph 10
multimodal 7
timeseries 5
audio 2
reinforcement-learning 1
Co-occurring categories
Other OWASP categories that appear on the same papers
Top cited papers
1152635455464738393102
Language Models are Injective and Hence Invertible
2025 attack
Hubble: a Model Suite to Advance the Study of LLM Memorization
2025 benchmark
FAPL-DM-BC: A Secure and Scalable FL Framework with Adaptive Privacy and Dynamic Masking, Blockchain, and XAI for the IoVs
2025 defense
Extracting books from production language models
2026 attack
How Diffusion Models Memorize
2025 benchmark
Extracting alignment data in open models
2025 attack
Fast, Private, and Protected: Safeguarding Data Privacy and Defending Against Model Poisoning Attacks in Federated Learning
2025 defense
FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning
2026 defense
Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
2025 defense
Memories Retrieved from Many Paths: A Multi-Prefix Framework for Robust Detection of Training Data Leakage in Large Language Models
2025 benchmark