Segui
Aleksandar Makelov
Aleksandar Makelov
Independent
Email verificata su mit.edu - Home page
Titolo
Citata da
Citata da
Anno
Towards deep learning models resistant to adversarial attacks
A Madry, A Makelov, L Schmidt, D Tsipras, A Vladu
arXiv preprint arXiv:1706.06083, 2017
112632017
Towards deep learning models resistant to adversarial attacks
A Mądry, A Makelov, L Schmidt, D Tsipras, A Vladu
stat 1050, 9, 2017
202017
Expansion in lifts of graphs
AA Makelov
72015
Rethinking backdoor attacks
A Khaddaj, G Leclerc, A Makelov, K Georgiev, H Salman, A Ilyas, A Madry
International Conference on Machine Learning, 16216-16236, 2023
32023
Is this the subspace you are looking for? An interpretability illusion for subspace activation patching
A Makelov, G Lange, A Geiger, N Nanda
The Twelfth International Conference on Learning Representations, 2023
22023
Backdoor or Feature? A New Perspective on Data Poisoning
A Khaddaj, G Leclerc, A Makelov, K Georgiev, A Ilyas, H Salman, A Madry
2022
Il sistema al momento non può eseguire l'operazione. Riprova più tardi.
Articoli 1–6