Aleksandar Makelov

According to our database, Aleksandar Makelov authored at least 6 papers between 2018 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control.

Aleksandar Makelov, Georg Lange, Neel Nanda

CoRR, 2024

Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching.

Aleksandar Makelov, Georg Lange, Atticus Geiger, Neel Nanda

Proceedings of the Twelfth International Conference on Learning Representations, 2024

2023

Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching.

Aleksandar Makelov, Georg Lange, Neel Nanda

CoRR, 2023

Rethinking Backdoor Attacks.

Alaa Khaddaj, Guillaume Leclerc, Aleksandar Makelov, Kristian Georgiev, Hadi Salman, Andrew Ilyas, Aleksander Madry

Proceedings of the International Conference on Machine Learning, 2023

2022

Towards machine learning models robust to adversarial examples and backdoor attacks

Aleksandar Makelov

PhD thesis, 2022

2018

Towards Deep Learning Models Resistant to Adversarial Attacks.

Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu

Proceedings of the 6th International Conference on Learning Representations, 2018