Deep Learning Under Siege: Identifying Security Vulnerabilities and Risk Mitigation Strategies
It addresses security challenges for widespread DL adoption, but appears incremental as it builds on existing risk analysis.
The paper tackles security vulnerabilities in deep learning models deployed in production, identifying current and future risks and proposing mitigation strategies with metrical evaluations.
With the rise in the wholesale adoption of Deep Learning (DL) models in nearly all aspects of society, a unique set of challenges is imposed. Primarily centered around the architectures of these models, these risks pose a significant challenge, and addressing these challenges is key to their successful implementation and usage in the future. In this research, we present the security challenges associated with the current DL models deployed into production, as well as anticipate the challenges of future DL technologies based on the advancements in computing, AI, and hardware technologies. In addition, we propose risk mitigation techniques to inhibit these challenges and provide metrical evaluations to measure the effectiveness of these metrics.