← all datasets

BackdoorBench

Emerging
1papers using it
2022first seen

BackdoorBench is a comprehensive benchmark for backdoor learning that includes an extensible modular-based codebase with implementations of state-of-the-art attacks and defense algorithms, used to evaluate the performance and effectiveness of these methods in the context of deep neural networks' vulnerabilities.

Papers using BackdoorBench (1)

BackdoorBench dataset β€” papers, benchmarks & downloads Β· Cybersecurity