Cho-Jui Hsieh, Kai-Wei Chang, Yao Li, Fan Yin
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.
Adversarial Examples Detection (AED) is a crucial defense technique against adversarial attacks and has drawn increasing attention from the Natural Language Processing (NLP) community. Despite the surge of new AED methods, our studies show that existing methods heavily rely on a shortcut to achieve good performance. In other words, current search-based adversarial attacks in NLP stop once model predictions change, and thus most adversarial examples generated by those attacks are located near model decision boundaries. To surpass this shortcut and fairly evaluate AED methods, we propose to test AED methods with Far Boundary (FB) adversarial examples. Existing methods show worse than random guess performance under this scenario. To overcome this limitation, we propose a new technique, ADDMU, adversary detection with data and model uncertainty, which combines two types of uncertainty estimation for both regular and FB adversarial example detection. Our new method outperforms previous methods by 3.6 and 6.0 AUC points under each scenario. Finally, our analysis shows that the two types of uncertainty provided by ADDMU can be leveraged to characterize adversarial examples and identify the ones that contribute most to model's robustness in adversarial training.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2210.12396")
get_code_for_paper("2210.12396")
have("2210.12396")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2210.12396.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2210.12396)
Connect an agent — have() is free.