David Dobre
5 papers · 2022–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
๐
Conference Polyglot
(3)
๐
Interdisciplinary Bridge
๐
Cross-Pollinator
(15)
Conferences
NIPS (3)
ICLR (1)
ICML (1)
Top co-authors
Keywords
stochastic optimization
(1)
stochastic gradient descent
(1)
adversarial robustness
(1)
variational inequality
(1)
embedding space
(1)
model unlearning
(1)
adversarial training
(1)
safety alignment
(1)
adversarial attack
(1)
diffusion model
(1)
jailbreak attack
(1)
gradient descent ascent
(1)
gradient descent-ascent
(1)
stochastic extragradient
(1)
certified defense
(1)
heavy-tailed noise
(1)
robustness certificate
(1)
minimax problem
(1)
large language model
(1)
Papers
Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning
ICLR 2025
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
NIPS 2024
On the Scalability of Certified Adversarial Robustness with Generated Data
NIPS 2024
Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features
ICML 2024
Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise
NIPS 2022