We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Vulnerability to adversarial attacks is a well-known weakness of Deep Neural networks. While most of the studies focus on single-task neural networks with computer vision datasets, very little research has considered complex multi-task models that are common in real applications. In this paper, we evaluate the design choices that impact the robustness of multi-task deep learning networks. We provide evidence that blindly adding auxiliary tasks, or weighing the tasks provides a false sense of robustness. Thereby, we tone down the claim made by previous research and study the different factors which may affect robustness. In particular, we show that the choice of the task to incorporate in the loss function are important factors that can be leveraged to yield more robust models.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2110.15053")
get_code_for_paper("2110.15053")
have("2110.15053")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2110.15053.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2110.15053)
Connect an agent — have() is free.