paper-with-me

홈 › Papers

One for Many: an Instagram inspired black-box adversarial attack

2021-09-29 · Alina Elena Baia, Alfredo Milani, Valentina Poggioni

It is well known that deep learning models are susceptible to adversarial attacks. To produce more robust and effective attacks, we propose a nested evolutionary algorithm able to produce multi-network (decision-based) black-box adversarial attacks based on Instagram inspired image filters. Due to the multi-network training, the system reaches a high transferability rate of attacks and, due to the composition of image filters, it is able to bypass standard detection mechanisms. Moreover, this kind of attack is semantically robust: our filter composition cannot be distinguished from any other filter composition used extensively every day to enhance images; this raises new security issues and challenges for real-world systems. Experimental results demonstrate that the method is also effective against ensemble-adversarially trained models and it has a low cost in terms of queries to the victim model.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack

Similar Papers 제목 키워드 기반

Log-normal Mutations and their Use in Detecting Surreptitious Fake Images

2024-09-23 · Ismail Labiad, Thomas Bäck, Pierre Fernandez, Laurent Najman 외

In many cases, adversarial attacks are based on specialized algorithms specifically dedicated to attacking automatic image classifiers. These algorithms perform well, thanks to an excellent ad hoc distribution of initial…

Meta Gradient Adversarial Attack

2021-08-09 · ICCV 2021 10 · Zheng Yuan, Jie Zhang, Yunpei Jia, Chuanqi Tan 외

In recent years, research on adversarial attacks has become a hot spot. Although current literature on the transfer-based adversarial attack has achieved promising results for improving the transferability to unseen blac…

Adversarial AttackMeta-Learning

Learn2Weight: Weights Transfer Defense against Similar-domain Adversarial Attacks

2021-01-01 · Siddhartha Datta

Recent work in black-box adversarial attacks for NLP systems has attracted attention. Prior black-box attacks assume that attackers can observe output labels from target models based on selected inputs. In this work, ins…

Adversarial AttackDomain AdaptationMulti-Domain Sentiment ClassificationSentiment Analysis+1

Learn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks

2022-05-15 · COLING 2022 10 · Siddhartha Datta

Recent work in black-box adversarial attacks for NLP systems has attracted much attention. Prior black-box attacks assume that attackers can observe output labels from target models based on selected inputs. In this work…

Adversarial AttackDomain AdaptationMeta-LearningMulti-Domain Sentiment Classification+2

SMART: Skeletal Motion Action Recognition aTtack

2019-11-16 · He Wang, Feixiang He, Zhexi Peng, Yong-Liang Yang 외

Adversarial attack has inspired great interest in computer vision, by showing that classification-based solutions are prone to imperceptible attack in many tasks. In this paper, we propose a method, SMART, to attack acti…

Action RecognitionAdversarial AttackTime SeriesTime Series Analysis