Efficient Adversarial Input Generation via Neural Net Patching. (arXiv:2211.16808v1 [cs.LG])

The adversarial input generation problem has become central in establishing
the robustness and trustworthiness of deep neural nets, especially when they
are used in safety-critical application domains such as autonomous vehicles and
precision medicine. This is also practically challenging for multiple
reasons-scalability is a common issue owing to large-sized networks, and the
generated adversarial inputs often lack important qualities such as naturalness
and output-impartiality. We relate this problem to the task of patching neural
nets, i.e. applying small changes in …

adversarial input patching