Hassan Dbouk
5 papers · 2020–2025 · 4 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 ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
Venues
Top co-authors
Research topics
Keywords
adversarial perturbation
(2)
adversarial robustness
(2)
randomized ensemble
(2)
adversarial attack
(1)
boosting algorithm
(1)
robustness evaluation
(1)
speculative sampling
(1)
language model inference
(1)
ensemble classifier
(1)
depthwise separable convolution
(1)
norm-bounded adversary
(1)
efficient neural network
(1)
token generation
(1)
post-training approximation
(1)
block efficiency
(1)
model compression
(1)
acceptance probability
(1)
model robustness
(1)
importance sampling
(1)
Papers
Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits
ICLR 2025
On the Robustness of Randomized Ensembles to Adversarial Perturbations
ICML 2023
Adversarial Vulnerability of Randomized Ensembles
ICML 2022
Generalized Depthwise-Separable Convolutions for Adversarially Robust and Efficient Neural Networks
NeurIPS 2021
DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks
ECCV 2020