Search Results for author:
Found 7 papers, 2 papers with code
Toward Certified Robustness Against Real-World Distribution Shifts
We consider the problem of certifying the robustness of deep neural networks against real-world distribution shifts.
On the Perils of Cascading Robust Classifiers
We present \emph{cascade attack} (CasA), an adversarial attack against cascading ensembles, and show that: (1) there exists an adversarial input for up to 88\% of the samples where the ensemble claims to be certifiably robust and accurate; and (2) the accuracy of a cascading ensemble under our attack is as low as 11\% when it claims to be certifiably robust and accurate on 97\% of the test set.
Degradation Attacks on Certifiably Robust Neural Networks
Certifiably robust neural networks employ provable run-time defenses against adversarial examples by checking if the model is locally robust at the input under evaluation.
NNrepair: Constraint-based Repair of Neural Network Classifiers
We present novel strategies to enable precise yet efficient repair such as inferring correctness specifications to act as oracles for intermediate layer repair, and generation of experts for each class.
NEUROSPF: A tool for the Symbolic Analysis of Neural Networks
This paper presents NEUROSPF, a tool for the symbolic analysis of neural networks.
Parallelization Techniques for Verifying Neural Networks
Inspired by recent successes with parallel optimization techniques for solving Boolean satisfiability, we investigate a set of strategies and heuristics that aim to leverage parallel computing to improve the scalability of neural network verification.
A Programmatic and Semantic Approach to Explaining and DebuggingNeural Network Based Object Detectors
It is programmatic in that scenario representation is a program in a domain-specific probabilistic programming language which can be used to generate synthetic data to test a given perception module.
