MPI-INF Logo
Campus Event Calendar

Event Entry

What and Who

Adversarially Robust Anomaly Detection through Spurious Negative Pair Mitigation

Mojtaba Nafez
Sharif University of Technology
PhD Application Talk
AG 1, AG 2, AG 3, INET, AG 4, AG 5, D6, SWS, RG1, MMCI  
AG Audience
English

Date, Time and Location

Tuesday, 4 February 2025
14:30
30 Minutes
Virtual talk
zoom

Abstract

Despite significant progress in Anomaly Detection (AD), the robustness of existing detection methods against adversarial attacks remains a challenge, compromising their reliability in critical real-world applications such as autonomous driving. This issue primarily arises from the AD setup, which assumes that training data is limited to a group of unlabeled normal samples, making the detectors vulnerable to adversarial anomaly samples during testing. Additionally, implementing adversarial training as a safeguard encounters difficulties, such as formulating an effective objective function without access to labels. An ideal objective function for adversarial training in AD should promote strong perturbations both within and between the normal and anomaly groups to maximize margin between normal and anomaly distribution. To address these issues, we first propose crafting a pseudo-anomaly group derived from normal group samples. Then, we demonstrate that adversarial training with contrastive loss could serve as an ideal objective function, as it creates both inter- and intra-group perturbations. However, we notice that spurious negative pairs compromise the conventional contrastive loss for achieving robust AD. Spurious negative pairs are those that should be mapped closely but are erroneously separated. These pairs introduce noise and misguide the direction of inter-group adversarial perturbations. To overcome the effect of spurious negative pairs, we define opposite pairs and adversarially pull them apart to strengthen inter-group perturbations. Experimental results demonstrate our superior performance in both clean and adversarial scenarios, with a 26.1% improvement in robust detection across various challenging benchmark datasets.

Contact

Ina Geisler
+49 681 9325 1802
--email hidden

Virtual Meeting Details

Zoom
passcode not visible
logged in users only

Ina Geisler, 01/27/2025 09:50
Ina Geisler, 01/27/2025 09:50 -- Created document.