.png){kind=icon}
返回
Making models more secure: An efficient model stealing detection method
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compeleceng.2024.109266.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Reduced distinguishability significantly challenges the detection of Model Stealing (MS). Existing methods for identifying MS attacks exhibit key limitations: (1) Sample -level detection methods that use fixed feature thresholds often inadvertently include benign samples or overlook malicious ones; (2) Distribution -level detection methods with static divergence benchmarks may misclassify benign query samples that deviate from these benchmarks This paper introduces GuardNet, an innovative model stealing detection method. By combining boundary features with inter-sample distance features, GuardNet more precisely identifies malicious sample pairs and employs distribution divergences to adjust decision thresholds, thus enhancing its detection capabilities. The method incorporates a variational autoencoder to reconstruct query samples and uses the Wasserstein distance between pre- and post-reconstruction samples as a measure of distribution divergences, effectively minimizing the influence of distribution shifts on benign query samples. Experimental results indicate that this approach significantly reduces the number of adversarial queries and markedly decreases false positives.
Keyword:
Model stealing detection
Model stealing attack
Security and privacy
Machine Learning asa Service
期刊
C
IF:
4.9
论文数:
6.7K
被引数:
1.3W
机构
引用论文
Defending against adversarial attacks using spherical sampling-based variational auto-encoder.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Enhanced Object Detection With Deep Convolutional Neural Networks for Advanced Driving Assistance基于深度卷积神经网络的增强型目标检测，用于高级驾驶辅助
OAAI
OAAI分享收藏
没有更多内容
没有更多内容