Machine learning models are often used to decide who will receive a loan...
In this work, we propose a general framework called Concept-Monitor to h...
Concept bottleneck models (CBM) are a popular way of creating more
inter...
Transformations based on domain expertise (expert transformations), such...
Deep neural networks (DNN) have shown great capacity of modeling a dynam...
Interpreting machine learning models is challenging but crucial for ensu...
There has been great interest in enhancing the robustness of neural netw...
Path-tracking control of self-driving vehicles can benefit from deep lea...
In this paper, we propose CLIP-Dissect, a new technique to automatically...
In recent years, a proliferation of methods were developed for cooperati...
Recent research shows that the dynamics of an infinitely wide neural net...
Model-agnostic meta-learning (MAML) has emerged as one of the most succe...
Recent works have developed several methods of defending neural networks...
Randomized smoothing is a recently proposed defense against adversarial
...
Deep neural networks, including reinforcement learning agents, have been...
Deep neural networks are known to be fragile to small adversarial
pertur...
Graph neural networks (GNNs) which apply the deep neural networks to gra...
The vulnerability to adversarial attacks has been a critical issue for d...
The total complexity (measured as the total number of gradient computati...
With deep neural networks providing state-of-the-art machine learning mo...
Verifying robustness of neural network classifiers has attracted great
i...
Finding minimum distortion of adversarial examples and thus certifying
r...
CLEVER (Cross-Lipschitz Extreme Value for nEtwork Robustness) is an Extr...
Verifying the robustness property of a general Rectified Linear Unit (Re...
The robustness of neural networks to adversarial examples has received g...