Security Risks in Deep Learning Implementations
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). First posted on arXiv 29 Nov 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 4; 2023: 2; 2024: 1; 2025: 1.
12 papers.
- 2021Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attackscited by 49
- 2021Fall of Giants: How popular text-based MLaaS fall against a simple evasion attackcited by 13
- 2021Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspectivecited by 9
- 2025The Hidden Threat in Plain Text: Attacking RAG Data Loaderscited by 8
- 2023Your Attack Is Too DUMB: Formalizing Attacker Scenarios for Adversarial Transferabilitycited by 5
- 2022Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfirecited by 4
- 2021Widen The Backdoor To Let More Attackers Incited by 3
- 2022Captcha Attack: Turning Captchas Against Humanitycited by 2
- 2022Improving Deep Learning Model Robustness Against Adversarial Attack by Increasing the Network Capacitycited by 0
- 2022Empowering the trustworthiness of ML-based critical systems through engineering activitiescited by 0
- 2023ConFL: Constraint-guided Fuzzing for Machine Learning Frameworkcited by 0
- 2024A Survey of Trojan Attacks and Defenses to Deep Neural Networkscited by 0
- 2025The Hidden Threat in Plain Text: Attacking RAG Data Loaders7 Jul 2025
- 2024A Survey of Trojan Attacks and Defenses to Deep Neural Networks15 Aug 2024
- 2023ConFL: Constraint-guided Fuzzing for Machine Learning Framework11 Jul 2023
- 2023Your Attack Is Too DUMB: Formalizing Attacker Scenarios for Adversarial Transferability27 Jun 2023
- 2022Empowering the trustworthiness of ML-based critical systems through engineering activities30 Sep 2022
- 2022Improving Deep Learning Model Robustness Against Adversarial Attack by Increasing the Network Capacity24 Apr 2022
- 2022Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire28 Jan 2022
- 2022Captcha Attack: Turning Captchas Against Humanity11 Jan 2022
- 2021Widen The Backdoor To Let More Attackers In9 Oct 2021
- 2021Fall of Giants: How popular text-based MLaaS fall against a simple evasion attack13 Apr 2021
- 2021Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks18 Jan 2021
- 2021Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective8 Jan 2021