Haitham Khedr
Haitham Khedr
About
Publications
Light
Dark
Automatic
1
DeepBern-Nets: Taming the Complexity of Certifying Neural Networks using Bernstein Polynomial Activations and Precise Bound Propagation
Formal certification of Neural Networks (NNs) is crucial for ensuring their safety, fairness, and robustness. Unfortunately, on the one …
Haitham Khedr
,
Yasser Shoukry
PDF
CertiFair: A Framework for Certified Global Fairness of Neural Networks (AAAI 23')
We consider the problem of whether a Neural Network (NN) model satisfies global individual fairness. Individual Fairness suggests that …
Haitham Khedr
,
Yasser Shoukry
PDF
Fast BATLLNN: Fast Box Analysis of Two-Level Lattice Neural Networks (HSCC 22')
In this paper, we present the tool Fast Box Analysis of Two-Level Lattice Neural Networks (Fast BATLLNN) as a fast verifier of box-like …
James Ferlez
,
Haitham Khedr
,
Yasser Shoukry
PDF
Cite
PEREGRiNN: Penalized-Relaxation Greedy Neural Network Verifier (CAV 21')
In this paper, we propose PEREGRiNN, an algorithm for efficiently and formally verifying the input/output behavior of ReLU NNs.
Haitham Khedr
,
James Ferlez
,
Yasser Shoukry
PDF
Cite
Formal Verification of Neural Network Controlled Autonomous Systems (HSCC 19')
In this paper, we consider the problem of formally verifying the safety of an autonomous robot equipped with a Neural Network (NN) …
Xiaowu Sun
,
Haitham Khedr
,
Yasser Shoukry
PDF
Cite
Cite
×