G. Edward Suh
8 papers · 2019–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (3) π Academic Marathon (6) π Cross-Pollinator (13)
πΊοΈ
Taxonomy Completionist
(12)
π
Triple Crown
π
Trend Setter
Conferences
ICLR (3)
NIPS (3)
ICML (2)
Top co-authors
Research topics
Keywords
privacy-preserving machine learning
(1)
model compression
(1)
federated learning
(1)
privacy attack
(1)
adversarial learning
(1)
adversarial robustness
(1)
blind source separation
(1)
independent component analysis
(1)
knowledge distillation
(1)
data augmentation
(1)
adversarial training
(1)
neural network optimization
(1)
efficient computing
(1)
computational efficiency
(1)
fisher information
(1)
convolutional neural network
(1)
privacy risk
(1)
hardware acceleration
(1)
gradient inversion
(1)
robust training
(1)
Papers
Trustworthy Machine Learning through Data-Specific Indistinguishability
ICML 2025
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
ICLR 2025
MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection
ICLR 2023
Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information
NIPS 2023
Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component Analysis
ICML 2023
BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining
NIPS 2021
Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations
ICLR 2020
Channel Gating Neural Networks
NIPS 2019