Blaine Nelson
8 papers · 2010–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🏃 Academic Marathon (15) 🧭 Keyword Pioneer 🌍 Conference Polyglot (6) 🐝 Cross-Pollinator (9)
🧭
Keyword Pioneer
🌍
Conference Polyglot
(6)
🏃
Academic Marathon
(15)
🧬
Topic Evolution
📈
Trend Setter
🚀
Conference Pioneer
Conferences
ACML (2)
JMLR (2)
AACL (1)
AISTATS (1)
IJCNLP (1)
NIPS (1)
Top co-authors
Research topics
Keywords
adversarial learning
(3)
adversarial attack
(2)
convex optimization
(2)
latent space geometry
(2)
support vector machine
(2)
kernel methods
(2)
linear separability
(2)
classifier evasion
(2)
prompt engineering
(1)
safety alignment
(1)
bayesian inference
(1)
model alignment
(1)
label noise
(1)
sensitivity analysis
(1)
ai safety
(1)
black-box attack
(1)
posterior sampling
(1)
query complexity
(1)
semantic representation
(1)
kernel matrix
(1)
Papers
Large Language Models Encode Semantics and Alignment in Linearly Separable Representations
IJCNLP 2025
Large Language Models Encode Semantics and Alignment in Linearly Separable Representations
AACL 2025
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
NIPS 2024
Differential Privacy for Bayesian Inference through Posterior Sampling
JMLR 2017
Query Strategies for Evading Convex-Inducing Classifiers
JMLR 2012
Support Vector Machines Under Adversarial Label Noise
ACML 2011
Microbagging Estimators: An Ensemble Approach to Distance-weighted Classifiers
ACML 2011
Near-Optimal Evasion of Convex-Inducing Classifiers
AISTATS 2010