Logan Engstrom, Shibani Santurkar, Dimitris Tsipras, Alexander Turner, Mit
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We show that there may exist an inherent tension between the goal of adversarial robustness and that of standard generalization. Specifically, training robust models may not only be more resource-consuming, but also lead to a reduction of standard accuracy. We demonstrate that this trade-off between the standard accuracy of a model and its robustness to adversarial perturbations provably exists in a fairly simple and natural setting. These findings also corroborate a similar phenomenon observed empirically in more complex settings. Further, we argue that this phenomenon is a consequence of robust classifiers learning fundamentally different feature representations than standard classifiers. These differences, in particular, seem to result in unexpected benefits: the representations learned by robust models tend to align better with salient data characteristics and human perception.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("1805.12152")
get_code_for_paper("1805.12152")
have("1805.12152")
Connect an agent — have() is free.