33 citations · 44 across the 3 of their papers we have counts for
3 papers
On the limits of neural network explainability via descrambling
Shashank Sule, Richard G. Spencer, Wojciech Czaja
We characterize the exact solutions to neural network descrambling--a mathematical model for explaining the fully connected layers of trained neural networks (NNs). By reformulatin…
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
Liam Fowl, Jonas Geiping, Steven Reich +4
A central tenet of Federated learning (FL), which trains models without centralizing user data, is privacy. However, previous work has shown that the gradient updates used in FL ca…
Adversarial Examples Make Strong Poisons
Liam Fowl, Micah Goldblum, Ping-yeh Chiang +3
The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversari…