Aleksandar Makelov

4 papers · 2018–2025 · 2 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (2) 🏃 Academic Marathon (7) 🌉 Interdisciplinary Bridge 🐝 Cross-Pollinator (15) ❓ The Questioner 🚀 Conference Pioneer

Conferences

ICLR (3) ICML (1)

Top co-authors

Georg Lange (2) Neel Nanda (2) Aleksander Madry (2) Dimitris Tsipras (1) Guillaume Leclerc (1) Adrian Vladu (1) Andrew Ilyas (1) Ludwig Schmidt (1) Kristian Georgiev (1) Hadi Salman (1)

Research topics

Keywords

adversarial learning (1) data poisoning (1) robust statistics (1) outlier detection (1) machine learning security (1) backdoor attack (1) theoretical guarantee (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