A Data Augmentation-based Defense Method Against Adversarial Attacks in Neural Networks

July 30, 2020 Β· Declared Dead Β· πŸ› International Conference on Algorithms and Architectures for Parallel Processing

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Yi Zeng, Han Qiu, Gerard Memmi, Meikang Qiu arXiv ID 2007.15290 Category cs.CR: Cryptography & Security Cross-listed cs.LG Citations 58 Venue International Conference on Algorithms and Architectures for Parallel Processing Last Checked 3 months ago
Abstract
Deep Neural Networks (DNNs) in Computer Vision (CV) are well-known to be vulnerable to Adversarial Examples (AEs), namely imperceptible perturbations added maliciously to cause wrong classification results. Such variability has been a potential risk for systems in real-life equipped DNNs as core components. Numerous efforts have been put into research on how to protect DNN models from being tackled by AEs. However, no previous work can efficiently reduce the effects caused by novel adversarial attacks and be compatible with real-life constraints at the same time. In this paper, we focus on developing a lightweight defense method that can efficiently invalidate full whitebox adversarial attacks with the compatibility of real-life constraints. From basic affine transformations, we integrate three transformations with randomized coefficients that fine-tuned respecting the amount of change to the defended sample. Comparing to 4 state-of-art defense methods published in top-tier AI conferences in the past two years, our method demonstrates outstanding robustness and efficiency. It is worth highlighting that, our model can withstand advanced adaptive attack, namely BPDA with 50 rounds, and still helps the target model maintain an accuracy around 80 %, meanwhile constraining the attack success rate to almost zero.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Cryptography & Security

Died the same way β€” πŸ‘» Ghosted