Sanjay Kariyappa
7 papers · 2020–2024 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🗺️ Taxonomy Completionist (13) 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird 🏆 Keyword Champion (3)
🧭
Keyword Pioneer
🏆
Grand Slam
Venues
Top co-authors
Research topics
Machine Learning
(7)
Application Areas
(5)
Security & Privacy
(4)
Privacy
(4)
Artificial Intelligence
(3)
Deep Learning
(3)
Core AI
(2)
Core Methods
(2)
Learning Types · Machine Learning
(2)
Natural Language Processing
(1)
Applications
(1)
Architectures
(1)
Learning Paradigms · Artificial Intelligence
(1)
Learning Paradigms · Machine Learning
(1)
Learning Types · Deep Learning
(1)
Keywords
model stealing
(3)
black-box attack
(3)
privacy attack
(1)
independent component analysis
(1)
pac learning
(1)
feature importance
(1)
fisher information
(1)
synthetic data
(1)
adversarial attack
(1)
gradient estimation
(1)
generative model
(1)
multi-armed bandit
(1)
deep neural network
(1)
adversarial defense
(1)
blind source separation
(1)
decision boundary
(1)
zeroth-order optimization
(1)
out-of-distribution detection
(1)
privacy risk
(1)
federated learning
(1)
Papers
Progressive Inference: Explaining Decoder-Only Sequence Classification Models Using Intermediate Predictions
ICML 2024
SHAP@k: Efficient and Probably Approximately Correct (PAC) Identification of Top-K Features
AAAI 2024
Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information
NeurIPS 2023
Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component Analysis
ICML 2023
MAZE: Data-Free Model Stealing Attack Using Zeroth-Order Gradient Estimation
CVPR 2021
Protecting DNNs from Theft using an Ensemble of Diverse Models
ICLR 2021
Defending Against Model Stealing Attacks With Adaptive Misinformation
CVPR 2020