Search Results for author:
Found 5 papers, 2 papers with code
Explaining SAT Solving Using Causal Reasoning
Subsequently, given a query such as whether a clause with low literals blocks distance (LBD) has a higher clause utility, CausalSAT calculates the causal effect of LBD on clause utility and provides an answer to the question.
Membership Inference Attacks and Generalization: A Causal Perspective
Our causal models also show a new connection between generalization and MI attacks via their shared causal factors.
LPGNet: Link Private Graph Networks for Node Classification
In this paper, we present a new neural network architecture called LPGNet for training on graphs with privacy-sensitive edges.
Scalable Quantitative Verification For Deep Neural Networks
But these existing techniques provide either scalability to large networks or formal guarantees, not both.
Quantitative Verification of Neural Networks And its Security Applications
Neural networks are increasingly employed in safety-critical domains.
