Security Risks in Deep Learning Implementations

2017/11/29 by Qixue Xiao, Xiao, Qixue, Kang Li +5 · 2 citations
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Security and Verification in Computing

paper · pdf · doi:10.48550/arxiv.1711.11008

openalex publication_date 2017/11/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Advance in deep learning algorithms overshadows their security risk in software implementations. This paper discloses a set of vulnerabilities in popular deep learning frameworks including Caffe, TensorFlow, and Torch. Contrast to the small code size of deep learning models, these deep learning frameworks are complex and contain heavy dependencies on numerous open source packages. This paper considers the risks caused by these vulnerabilities by studying their impact on common deep learning applications such as voice recognition and image classifications. By exploiting these framework implementations, attackers can launch denial-of-service attacks that crash or hang a deep learning application, or control-flow hijacking attacks that cause either system compromise or recognition evasions. The goal of this paper is to draw attention on the software implementations and call for the community effort to improve the security of deep learning frameworks.

Cited by

• The Hidden Threat in Plain Text: Attacking RAG Data Loaders
• Shredder: Learning Noise Distributions to Protect Inference Privacy

Related

• On Security Weaknesses and Vulnerabilities in Deep Learning Systems
• Security of Deep Learning Methodologies: Challenges and Opportunities
• Secure Deep Learning Engineering: A Software Quality Assurance Perspective
• Deep Learning Model Security: Threats and Defenses
• Improving Deep Learning Model Robustness Against Adversarial Attack by Increasing the Network Capacity