most citedSound Symbolic Execution via Abstract Interpretation and its Application to Security

4 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2024

Verification of Geometric Robustness of Neural Networks via Piecewise Linear Approximation and Lipschitz Optimisation

Ben Batten, Yang Zheng, Alessandro De Palma +2

We address the problem of verifying neural networks against geometric transformations of the input image, including rotation, scaling, shearing, and translation. The proposed metho…

cs.LG2023★ 1 cited

Expressive Losses for Verified Robustness via Convex Combinations

Alessandro De Palma, Rudy Bunel, Krishnamurthy Dvijotham +3

In order to train networks for verified adversarial robustness, it is common to over-approximate the worst-case loss over perturbation regions, resulting in networks that attain ve…