Reproduce “Black-Box Adversarial Example Attacks on Machine Learning based Election Systems” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Subek Acharya, Syed Ayon, Khaleque Md Aashiq Kamal, Alina Barnett, Surya Eada, Kaleel Mahmood
The authors test whether black-box attacks can alter ballot classifiers without access to their weights or architecture. They evaluate eight research models digitally and after printing and scanning. On CaiT, Square robust accuracy rises from 0.500 to 0.896. Transfer tests also reveal cross-model weaknesses, though some model pairs show no transfer; these experiments do not demonstrate attacks on live elections.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.