Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Detecting Sentiment Steering Attacks on RAG-enabled Large Language Models

Isha Andrade, Shalaka S Mahadik, Mithun Mukherjee, Pranav M Pawar, Raja Muthalagu

Abstract

The proliferation of large-scale IoT networks has been both a blessing and a curse. Not only has it revolutionized the way organizations operate by increasing the efficiency of automated procedures, but it has also simplified our daily lives. However, while IoT networks have improved convenience and connectivity, they have also increased security risk due to unauthorized devices gaining access to these networks and exploiting existing weaknesses with specific attack types. The research proposes two lightweight deep learning (DL)-based intelligent intrusion detection systems (IDS). to enhance the security of IoT networks: the proposed convolutional neural network (CNN)-based IDS and the proposed long short-term memory (LSTM)-based IDS. The research evaluated the performance of both intelligent IDSs based on DL using the CICIoT2023 dataset. DL-based intelligent IDSs successfully identify and classify various cyber threats using binary, grouped, and multi-class classification. The proposed CNN-based IDS achieves an accuracy of 99.34%, 99.02% and 98.6%, while the proposed LSTM-based IDS achieves an accuracy of 99.42%, 99.13%, and 98.68% for binary, grouped, and multi-class classification, respectively.

Detecting Sentiment Steering Attacks on RAG-enabled Large Language Models

Abstract

The proliferation of large-scale IoT networks has been both a blessing and a curse. Not only has it revolutionized the way organizations operate by increasing the efficiency of automated procedures, but it has also simplified our daily lives. However, while IoT networks have improved convenience and connectivity, they have also increased security risk due to unauthorized devices gaining access to these networks and exploiting existing weaknesses with specific attack types. The research proposes two lightweight deep learning (DL)-based intelligent intrusion detection systems (IDS). to enhance the security of IoT networks: the proposed convolutional neural network (CNN)-based IDS and the proposed long short-term memory (LSTM)-based IDS. The research evaluated the performance of both intelligent IDSs based on DL using the CICIoT2023 dataset. DL-based intelligent IDSs successfully identify and classify various cyber threats using binary, grouped, and multi-class classification. The proposed CNN-based IDS achieves an accuracy of 99.34%, 99.02% and 98.6%, while the proposed LSTM-based IDS achieves an accuracy of 99.42%, 99.13%, and 98.68% for binary, grouped, and multi-class classification, respectively.
Paper Structure (15 sections, 7 figures, 6 tables)

This paper contains 15 sections, 7 figures, 6 tables.

Table of Contents

  1. Introduction
  2. Motivation
  3. Contribution
  4. Related work
  5. Research methodology
  6. Dataset and data preprocessing
  7. Architecture of Proposed DL-based IDS
  8. Proposed CNN-based IDS
  9. Proposed LSTM-based IDS
  10. Results and Discussion
  11. Binary classification
  12. Grouped classification
  13. Multi-class classification
  14. Summary
  15. Conclusion

Figures (7)

  • Figure 1: Example of large-scale IoT and its features
  • Figure 2: Feature importance graph isha1
  • Figure 3: Architecture of proposed CNN-based IDS
  • Figure 4: Architecture of proposed LSTM-based IDS
  • Figure 5: Accuracy of Binary classification
  • ...and 2 more figures