CosPGD: a unified white-box adversarial attack for pixel-wise prediction tasks

Agnihotri, Shashank; Keuper, Margret

doi:10.48550/arxiv.2302.02213

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is a way to generate such examples through various techniques. It can be divided into test-time adversarial attack methods (Goodfellow, Shlens, and Szegedy 2015;Carlini and Wagner 2017;Madry et al 2018;Gu et al 2022;Agnihotri and Keuper 2023) and training-time ones (Feng, Cai, and Zhou 2019). The former generates adversarial images during inference and confuses the model to produce false predictions.…”

Section: Adversarial Attackmentioning

confidence: 99%

Attacks on Continual Semantic Segmentation by Perturbing Incremental Samples

Yu,

Yang,

Xie

et al. 2024

AAAI

View full text Add to dashboard Cite

As an essential computer vision task, Continual Semantic Segmentation (CSS) has received a lot of attention. However, security issues regarding this task have not been fully studied. To bridge this gap, we study the problem of attacks in CSS in this paper. We first propose a new task, namely, attacks on incremental samples in CSS, and reveal that the attacks on incremental samples corrupt the performance of CSS in both old and new classes. Moreover, we present an adversarial sample generation method based on class shift, namely Class Shift Attack (CS-Attack), which is an offline and easy-to-implement approach for CSS. CS-Attack is able to significantly degrade the performance of models on both old and new classes without knowledge of the incremental learning approach, which undermines the original purpose of the incremental learning, i.e., learning new classes while retaining old knowledge. Experiments show that on the popular datasets Pascal VOC, ADE20k, and Cityscapes, our approach easily degrades the performance of currently popular CSS methods, which reveals the importance of security in CSS.

show abstract

Section: Adversarial Attackmentioning

confidence: 99%