Search Results for author:
Found 8 papers, 3 papers with code
UR4NNV: Neural Network Verification, Under-approximation Reachability Works!
However, these strategies face challenges in addressing the "unknown dilemma" concerning whether the exact output region or the introduced approximation error violates the property in question.
An Automata-Theoretic Approach to Synthesizing Binarized Neural Networks
Quantized neural networks (QNNs) have been developed, with binarized neural networks (BNNs) restricted to binary values as a special case.
Verifying Safety of Neural Networks from Topological Perspectives
Moreover, for NNs that do not feature these properties with respect to the input set, we explore subsets of the input set for establishing the local homeomorphism property and then abandon these subsets for reachability computations.
Repairing Deep Neural Networks Based on Behavior Imitation
For the fine-tuning repair process, BIRDNN analyzes the behavior differences of neurons on positive and negative samples to identify the most responsible neurons for the erroneous behaviors.
Credit Assignment for Trained Neural Networks Based on Koopman Operator Theory
Based on Koopman operator theory, this paper presents an alternative perspective of linear dynamics on dealing with the credit assignment problem for trained neural networks.
Safety Verification for Neural Networks Based on Set-boundary Analysis
The homeomorphism property exists in some widely used NNs such as invertible NNs.
On Sufficient and Necessary Conditions in Bounded CTL: A Forgetting Approach
To address such a scenario in a principled way, we introduce a forgetting-based approach in CTL and show that it can be used to compute SNC and WSC of a property under a given model and over a given signature.
Kullback-Leibler Divergence-Based Out-of-Distribution Detection with Flow-Based Generative Models
For point-wise anomaly detection, our method achieves 90. 7\% AUROC on average and outperforms the baseline by 5. 2\% AUROC.
