activity
20172026
most citedTowards Deep Learning Models Resistant to Adversarial Attacks

1.5k citations · 1.5k across the 6 of their papers we have counts for

collaborators
Showing 2023Show all

2 papers · 1 filter

cs.LG2023★ 1 cited

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

Aleksandar Makelov, Georg Lange, Neel Nanda

Mechanistic interpretability aims to understand model behaviors in terms of specific, interpretable features, often hypothesized to manifest as low-dimensional subspaces of activat…

cs.CR2023★ 3 cited

Rethinking Backdoor Attacks

Alaa Khaddaj, Guillaume Leclerc, Aleksandar Makelov +4

In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against s…