Search Results for author:
Found 4 papers, 1 papers with code
Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and Relearning
The application of deep neural network models in various security-critical applications has raised significant security concerns, particularly the risk of backdoor attacks.
Verifying Neural Networks Against Backdoor Attacks
To the best of our knowledge, the only line of work which certifies the absence of backdoor is based on randomized smoothing, which is known to significantly reduce neural network performance.
SOCRATES: Towards a Unified Platform for Neural Network Analysis
Studies show that neural networks, not unlike traditional programs, are subject to bugs, e. g., adversarial samples that cause classification errors and discriminatory instances that demonstrate the lack of fairness.
sFuzz: An Efficient Adaptive Fuzzer for Solidity Smart Contracts
In this work, we present an adaptive fuzzer for smart contracts on the Ethereum platform called sFuzz.
Software Engineering
