Search Results for author:
Found 5 papers, 0 papers with code
Verification of Neural Networks' Global Robustness
We evaluate VHAGaR on several datasets and classifiers and show that, given a three hour timeout, the average gap between the lower and upper bound on the minimal globally robust bound computed by VHAGaR is 1. 9, while the gap of an existing global robustness verifier is 154. 7.
Verification of Neural Networks Local Differential Classification Privacy
We propose Sphynx, an algorithm that computes an abstraction of all networks, with a high probability, from a small set of networks, and verifies LDCP directly on the abstract network.
Boosting Robustness Verification of Semantic Feature Neighborhoods
Deep neural networks have been shown to be vulnerable to adversarial attacks that perturb inputs based on semantic features.
DL2: Training and Querying Neural Networks with Logic
We present DL2, a system for training and querying neural networks with logical constraints.
Learning Disjunctions of Predicates
Our algorithm asks at most $|F| \cdot OPT(F_\vee)$ membership queries where $OPT(F_\vee)$ is the minimum worst case number of membership queries for learning $F_\vee$.
