Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Building Secure UAV Navigation with FHE-aware Knowledge Distillation

Arjun Ramesh Kaushik, Charanjit Jutla, Nalini Ratha

TL;DR

This paper proposes an innovative approach that leverages Knowledge Distillation to enhance the practicality of secure UAV navigation and underscores the feasibility of processing encrypted data for UAV navigation tasks, emphasizing security alongside performance efficiency and timely processing.

Abstract

In safeguarding mission-critical systems, such as Unmanned Aerial Vehicles (UAVs), preserving the privacy of path trajectories during navigation is paramount. While the combination of Reinforcement Learning (RL) and Fully Homomorphic Encryption (FHE) holds promise, the computational overhead of FHE presents a significant challenge. This paper proposes an innovative approach that leverages Knowledge Distillation to enhance the practicality of secure UAV navigation. By integrating RL and FHE, our framework addresses vulnerabilities to adversarial attacks while enabling real-time processing of encrypted UAV camera feeds, ensuring data security. To mitigate FHE's latency, Knowledge Distillation is employed to compress the network, resulting in an impressive 18x speedup without compromising performance, as evidenced by an R-squared score of 0.9499 compared to the original model's score of 0.9631. Our methodology underscores the feasibility of processing encrypted data for UAV navigation tasks, emphasizing security alongside performance efficiency and timely processing. These findings pave the way for deploying autonomous UAVs in sensitive environments, bolstering their resilience against potential security threats.

Towards Building Secure UAV Navigation with FHE-aware Knowledge Distillation

TL;DR

This paper proposes an innovative approach that leverages Knowledge Distillation to enhance the practicality of secure UAV navigation and underscores the feasibility of processing encrypted data for UAV navigation tasks, emphasizing security alongside performance efficiency and timely processing.

Abstract

In safeguarding mission-critical systems, such as Unmanned Aerial Vehicles (UAVs), preserving the privacy of path trajectories during navigation is paramount. While the combination of Reinforcement Learning (RL) and Fully Homomorphic Encryption (FHE) holds promise, the computational overhead of FHE presents a significant challenge. This paper proposes an innovative approach that leverages Knowledge Distillation to enhance the practicality of secure UAV navigation. By integrating RL and FHE, our framework addresses vulnerabilities to adversarial attacks while enabling real-time processing of encrypted UAV camera feeds, ensuring data security. To mitigate FHE's latency, Knowledge Distillation is employed to compress the network, resulting in an impressive 18x speedup without compromising performance, as evidenced by an R-squared score of 0.9499 compared to the original model's score of 0.9631. Our methodology underscores the feasibility of processing encrypted data for UAV navigation tasks, emphasizing security alongside performance efficiency and timely processing. These findings pave the way for deploying autonomous UAVs in sensitive environments, bolstering their resilience against potential security threats.

Paper Structure

This paper contains 14 sections, 2 equations, 11 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Threat Model
  3. FHE basics
  4. Related Work
  5. Proposed Method
  6. Input Adaptations for FHE
  7. Knowledge Distillation
  8. Convolutional Layer
  9. Activation functions
  10. Flattening layer
  11. Fully-Connected Layer
  12. OpenAI Gym Library
  13. Results
  14. Conclusion

Figures (11)

  • Figure 1: Overview: In an ordinary scenario the UAV is vulnerable to attacks, as the attacker can directly steal the information. FHE-encrypted input and inference prevent this. But, currently, FHE is computationally infeasible.
  • Figure 2: An overview of the need for an FHE optimized model.
  • Figure 3: We propose a smaller model through Knowledge Distillation to suit FHE needs while maintaining security and accuracy.
  • Figure 4: Types of Homomorphic Encryption (HE) and their features.
  • Figure 5: Architecture overview of our framework implementing the Actor-Critic algorithm.
  • ...and 6 more figures