# Security Risks in Deep Learning Implementations

arXiv: https://arxiv.org/abs/1711.11008 · HTML: https://mlsanity.com/paper/1711.11008/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2017.

## Built on by (most cited first, 12 of 12)

- [Red Alarm for Pre-trained Models: Universal Vulnerability to Neuron-Level Backdoor Attacks](https://mlsanity.com/paper/2101.06969/) (2021)
- [Fall of Giants: How popular text-based MLaaS fall against a simple evasion attack](https://mlsanity.com/paper/2104.05996/) (2021)
- [Towards a Robust and Trustworthy Machine Learning System Development: An Engineering Perspective](https://mlsanity.com/paper/2101.03042/) (2021)
- [The Hidden Threat in Plain Text: Attacking RAG Data Loaders](https://mlsanity.com/paper/2507.05093/) (2025)
- [Your Attack Is Too DUMB: Formalizing Attacker Scenarios for Adversarial Transferability](https://mlsanity.com/paper/2306.15363/) (2023)
- [Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire](https://mlsanity.com/paper/2201.12211/) (2022)
- [Widen The Backdoor To Let More Attackers In](https://mlsanity.com/paper/2110.04571/) (2021)
- [Captcha Attack: Turning Captchas Against Humanity](https://mlsanity.com/paper/2201.04014/) (2022)
- [Improving Deep Learning Model Robustness Against Adversarial Attack by Increasing the Network Capacity](https://mlsanity.com/paper/2204.11357/) (2022)
- [Empowering the trustworthiness of ML-based critical systems through engineering activities](https://mlsanity.com/paper/2209.15438/) (2022)
- [ConFL: Constraint-guided Fuzzing for Machine Learning Framework](https://mlsanity.com/paper/2307.05642/) (2023)
- [A Survey of Trojan Attacks and Defenses to Deep Neural Networks](https://mlsanity.com/paper/2408.08920/) (2024)

## 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.