Aleksandar Makelov
4 papers · 2018–2025 · 2 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 ↓+1 more ↓ Show less ↑
๐ Conference Polyglot ยท Bronze ๐ Academic Marathon ยท Sprint ๐ Interdisciplinary Bridge ยท Bronze ๐ฃ Hot Topic Early Bird โ The Questioner
๐
Conference Pioneer
Top co-authors
Research topics
Keywords
unsupervised learning
(1)
causal inference
(1)
adversarial learning
(1)
robust optimization
(1)
adversarial robustness
(1)
data poisoning
(1)
robust statistics
(1)
feature disentanglement
(1)
outlier detection
(1)
machine learning security
(1)
backdoor attack
(1)
adversarial attack
(1)
mechanistic interpretability
(1)
sparse autoencoder
(1)
adversarial example
(1)
theoretical guarantee
(1)
activation patching
(1)
neural network
(1)
model control
(1)
first-order adversary
(1)
Papers
Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
ICLR 2025
Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching
ICLR 2024
Rethinking Backdoor Attacks
ICML 2023
Towards Deep Learning Models Resistant to Adversarial Attacks
ICLR 2018