2024-09-12-dang24a.md

title	abstract	openreview	section	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
Can we Defend Against the Unknown? An Empirical Study About Threshold Selection for Neural Network Monitoring	With the increasing use of neural networks in critical systems, runtime monitoring becomes essential to reject unsafe predictions during inference. Various techniques have emerged to establish rejection scores that maximize the separability between the distributions of safe and unsafe predictions. The efficacy of these approaches is mostly evaluated using threshold-agnostic metrics, such as the area under the receiver operating characteristic curve. However, in real-world applications, an effective monitor also requires identifying a good threshold to transform these scores into meaningful binary decisions. Despite the pivotal importance of threshold optimization, this problem has received little attention. A few studies touch upon this question, but they typically assume that the runtime data distribution mirrors the training distribution, which is a strong assumption as monitors are supposed to safeguard a system against potentially unforeseen threats. In this work, we present rigorous experiments on various image datasets to investigate: 1. The effectiveness of monitors in handling unforeseen threats, which are not available during threshold adjustments. 2. Whether integrating generic threats into the threshold optimization scheme can enhance the robustness of monitors.	nzxnE8t2Sz	Papers	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	dang24a	0	Can we Defend Against the Unknown? An Empirical Study About Threshold Selection for Neural Network Monitoring	930	942	930-942	930	false	Dang, Khoi Tran and Delmas, Kevin and Guiochet, J\'er\'emie and Gu\'erin, Joris	given family Khoi Tran Dang given family Kevin Delmas given family Jérémie Guiochet given family Joris Guérin	2024-09-12		Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence	244	inproceedings	date-parts 2024 9 12	https://raw.githubusercontent.com/mlresearch/v244/main/assets/dang24a/dang24a.pdf