2020/03/06 by Sean Saito, Jin Wang, Saito, Sean +1
Computer Science · Mathematics · Psychology · #Adversarial Robustness in Machine Learning #Adversarial system #Anomaly Detection Techniques and Applications #Artificial intelligence #Artificial neural network #Code (set theory) #Cognitive science #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Cryptography and Security (cs.CR) #Deep neural networks #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Intuition #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Programming language #Psychology #cs.CR #cs.CV #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.2003.05748
published in arXiv (Cornell University) (Cornell University) · 2 pages, 2 figures; Accepted at MLSys 2020 First Workshop on Secure and Resilient Autonomy
arxiv created 2020/03/06 · openalex publication_date 2020/03/06 · arxiv updated 2020/03/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/06
We investigate the problem of identifying adversarial attacks on image-based neural networks. We present intriguing experimental results showing significant discrepancies between the explanations generated for the predictions of a model on clean and adversarial data. Utilizing this intuition, we propose a framework which can identify whether a given input is adversarial based on the explanations given by the model. Code for our experiments can be found here: https://github.com/seansaito/Explaining-Away-Attacks-Against-Neural-Networks.