A Comprehensive Review of Adversarial Attacks on Machine Learning

This research provides a comprehensive overview of adversarial attacks on AI and ML models, exploring various attack types, techniques, and their potential harms. We also delve into the business implications, mitigation strategies, and future research directions. To gain practical insights, we employ the Adversarial Robustness Toolbox (ART) [1] library to simulate these attacks on real-world use cases, such as self-driving cars. Our goal is to inform practitioners and researchers about the challenges and opportunities in defending AI systems against adversarial threats. By providing a comprehensive comparison of different attack methods, we aim to contribute to the development of more robust and secure AI systems.

cs.CR Adversarial Robustness in Machine Learning Advanced Malware Detection Techniques Computer Science

Source

Paper

References (13)

01Making an Invisibility Cloak: Real World Adversarial Attacks on Object DetectorsZuxuan Wu, Ser-Nam Lim, L. Davis et al.2019 · European Conference on Computer Vision · 327 citations In Library

023D Segmentation with Exponential Logarithmic Loss for Highly Unbalanced Object SizesKen C. L. Wong, Mehdi Moradi, Hui Tang et al.2018 · International Conference on Medical Image Computing and Computer-Assisted Intervention · 210 citations In Library

03Adversarial Robustness Toolbox v1.0.0Maria-Irina Nicolae, M. Sinn, Minh-Ngoc Tran et al.2018 · 573 citations In Library

04Towards Deep Learning Models Resistant to Adversarial AttacksA. Ma̧dry, Aleksandar Makelov, Ludwig Schmidt et al.2017 · International Conference on Learning Representations · 15k citations In Library

05Delving into Transferable Adversarial Examples and Black-box AttacksYan-Po Liu, Xinyun Chen, Chang Liu et al.2016 · International Conference on Learning Representations · 2.0k citations In Library

06Towards Evaluating the Robustness of Neural NetworksNicholas Carlini, D. Wagner2016 · IEEE Symposium on Security and Privacy · 10k citations In Library

07Explaining and Harnessing Adversarial ExamplesI. Goodfellow, Jonathon Shlens, Christian Szegedy2014 · International Conference on Learning Representations · 23k citations In Library

08Intriguing properties of neural networksChristian Szegedy, Wojciech Zaremba, I. Sutskever et al.2013 · International Conference on Learning Representations · 17k citations In Library

09Discovering Attributable Signals in Adversarial ML Attack2021 · arxiv.org

10Reconciling modern machine learning practice and the bias-variance trade-off2019 · arxiv.org/pdf/1812

11Limitations of Preprocessing Defenses : Preprocessing techniques, such as those employed in our research, can be effective in mitigating certain types of attacks

12Evolving Attack Techniques

Scroll for more · 1 remaining