DyAdvDefender: An instance-based online machine learning model for perturbation-trial-based black-box adversarial defense

Li, Miles Q.; Fung, Benjamin C. M.; Charland, Philippe

doi:10.1016/j.ins.2022.04.032

Cited by 3 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As previous defense methods are static and cannot dynamically adapt to adversarial attacks, Li et al [11] proposed the first instance-based online machine learning dynamic defense method against black-box attacks. Extensive experiments are conducted on image and malware datasets, and effects significantly outperform existing SOTA defense methods.…”

Section: Related Workmentioning

confidence: 99%

“…It is urgent to detect black-box attacks based on the DL malware detector. The stateful detection method has been used in computer vision [11,23,24,27], but it has not been attempted in malware black-box attacks which generate real adversarial samples. Therefore, we designed the MalDBA framework to detect query-based black-box attacks.…”

Section: Motivationmentioning

confidence: 99%

“…The existing optimal defense methods are stateless detection methods such as adversarial retraining and distillation, which detect whether the input sample is benign or malicious without judging whether there is an adversarial attack [8,9]. Existing malware stateful detection methods are implemented in the feature space, which requires data preprocessing and feature extraction [10,11]. At present, there is no malware stateful detection strategy implemented in the problem space.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

MalDBA: Detection for Query-Based Malware Black-Box Adversarial Attacks

et al. 2023

View full text Add to dashboard Cite

The increasing popularity of Industry 4.0 has led to more and more security risks, and malware adversarial attacks emerge in an endless stream, posing great challenges to user data security and privacy protection. In this paper, we investigate the stateful detection method for artificial intelligence deep learning-based malware black-box attacks, i.e., determining the presence of adversarial attacks rather than detecting whether the input samples are malicious or not. To this end, we propose the MalDBA method for experiments on the VirusShare dataset. We find that query-based black-box attacks produce a series of highly similar historical query results (also known as intermediate samples). By comparing the similarity among these intermediate samples and the trend of prediction scores returned by the detector, we can detect the presence of adversarial samples in indexed samples and thus determine whether an adversarial attack has occurred, and then protect user data security and privacy. The experimental results show that the attack detection rate can reach 100%. Compared to similar studies, our method does not require heavy feature extraction tasks or image conversion and can be operated on complete PE files without requiring a strong hardware platform.

show abstract

Section: Related Workmentioning

confidence: 99%