Tudor Dumitras
8 papers · 2018–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
🐝 Cross-Pollinator (15) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (3) 🏃 Academic Marathon (6)
🌈
Renaissance Researcher
(5)
🌉
Interdisciplinary Bridge
👑
Triple Crown
❓
The Questioner
(2)
Conferences
ICLR (4)
ICML (2)
NIPS (2)
Top co-authors
Research topics
Keywords
adversarial attack
(2)
federated learning
(1)
image classification
(1)
data poisoning
(1)
transfer learning
(1)
data augmentation
(1)
neural network optimization
(1)
early exit
(1)
backdoor attack
(1)
image classifier
(1)
inference efficiency
(1)
membership inference attack
(1)
neural network
(1)
clean-label poisoning
(1)
model compression
(1)
utility-privacy trade-off
(1)
Papers
Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds
ICLR 2024
DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
ICLR 2024
A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
ICLR 2021
When Does Data Augmentation Help With Membership Inference Attacks?
ICML 2021
Qu-ANTI-zation: Exploiting Quantization Artifacts for Achieving Adversarial Outcomes
NIPS 2021
How to 0wn the NAS in Your Spare Time
ICLR 2020
Shallow-Deep Networks: Understanding and Mitigating Network Overthinking
ICML 2019
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
NIPS 2018