.png){kind=icon}
返回
Testing the limits: exploring adversarial techniques in AI models
.png){kind=icon}
PRE
AI
DOI：10.7717/peerj-cs.3330.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The rising adoption of artificial intelligence and machine learning in critical sectors underscores the pressing need for robust systems capable of withstanding adversarial threats. While deep learning architectures have revolutionized tasks such as image recognition, their susceptibility to adversarial techniques remains an open challenge. This article evaluates the impact of various adversarial methods, including the fast gradient sign method, projected gradient descent, DeepFool, and Carlini & Wagner, on five neural network models: a fully connected neural network, LeNet, Simple convolutional neural network (CNN), MobileNetV2, and VGG11. Using the EVAISION tool explicitly developed for this research, these attacks were implemented and analyzed based on accuracy, F1-score, and misclassification rate. The results revealed varying levels of vulnerability across the tested models, with simpler architectures occasionally outperforming more complex ones. These findings emphasize the importance of selecting the most appropriate adversarial technique for a given architecture and customizing the associated attack parameters to achieve optimal results in each scenario.
Keyword:
Adversarial attacks
Misclassification
Cybersecurity
期刊
IF:
2.5
论文数:
3.4K
被引数:
6.9K
机构
引用论文
Taxonomy and Recent Advance of Game Theoretical Approaches in Adversarial Machine Learning: A Survey
PREAI
分享收藏Digital Health: The Cybersecurity for AI-Based Healthcare Communication数字健康: 基于AI的医疗保健通信的网络安全.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏FGMD: A robust detector against adversarial attacks in the IoT networkFGMD: 针对物联网网络中对抗性攻击的强大检测器
PREAI
分享收藏
Evaluating the Robustness of Deep Learning Models against Adversarial Attacks: An Analysis with FGSM, PGD and CW评估深度学习模型对对抗性攻击的鲁棒性: 基于FGSM、PGD和CW的分析OAAI
OAAI分享收藏
查看更多内容