Reproduce “Feature compression is the root cause of adversarial fragility in neural network classifiers” 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
Jingchao Gao, Ziqing Lu, Raghu Mudumbai, Xiaodong Wu, Jirong Yi, Myung Cho, Catherine Xu, Hui Xie and 1 more
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.