AutoLoRa: A Parameter-Free Automated Robust Fine-Tuning Framework. (arXiv:2310.01818v1 [cs.LG])

Robust Fine-Tuning (RFT) is a low-cost strategy to obtain adversarial
robustness in downstream applications, without requiring a lot of computational
resources and collecting significant amounts of data. This paper uncovers an
issue with the existing RFT, where optimizing both adversarial and natural
objectives through the feature extractor (FE) yields significantly divergent
gradient directions. This divergence introduces instability in the optimization
process, thereby hindering the attainment of adversarial robustness and
rendering RFT highly sensitive to hyperparameters. To mitigate this issue, we …

adversarial applications automated collecting computational cost data divergent feature framework free issue low natural objectives parameter resources robustness strategy