ML03
Model Inversion Attack
Reconstructing training data from ML model access
269 papers Browse all papers
Monthly publications
Paper types
defense 128
attack 81
benchmark 44
survey 13
tool 3
Domains
federated-learning 103
nlp 100
vision 99
generative 25
tabular 18
graph 10
multimodal 8
timeseries 5
audio 2
reinforcement-learning 1
Co-occurring categories
Other OWASP categories that appear on the same papers
LLM06 Sensitive Information Disclosure
83 ML04 Membership Inference Attack
42 ML02 Data Poisoning Attack
23 LLM01 Prompt Injection
6 ML10 Model Poisoning
5 ML05 Model Theft
5 ML01 Input Manipulation Attack
4 LS06 Red-Team Agents
1 ML09 Output Integrity Attack
1 ML06 AI Supply Chain Attacks
1 LS05 Triage & Prioritization
1Top 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
Extracting alignment data in open models
2025 attack
How Diffusion Models Memorize
2025 benchmark
Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
2025 defense
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
SMOTE and Mirrors: Exposing Privacy Leakage from Synthetic Minority Oversampling
2025 attack