Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Credible fusion of evidence in distributed system subject to cyberattacks

Chaoxiong Ma, Yan Liang

TL;DR

This work tackles credible evidence fusion in distributed systems facing cyberattacks, proposing a WAVCCME-based framework (CEFAC) that converts multi-source evidence into a distributed consensus problem. It introduces a privacy-preserving state-decomposition mechanism using Paillier encryption and a dedicated attacker identification/compensation strategy to exclude malicious evidence, all while maintaining convergence on directed graphs under strong robustness assumptions. Key contributions include proving WAVCCME as the fusion core, enabling distributed computation via KPPEEV and EVE sums, and integrating privacy and attacker-defense into a unified algorithm. Simulation results on high-conflict and cyberattack scenarios demonstrate improved accuracy and efficiency, with the ability to exclude attacker evidence and sustain credible fusion in distributed unmanned systems.

Abstract

Given that distributed systems face adversarial behaviors such as eavesdropping and cyberattacks, how to ensure the evidence fusion result is credible becomes a must-be-addressed topic. Different from traditional research that assumes nodes are cooperative, we focus on three requirements for evidence fusion, i.e., preserving evidence's privacy, identifying attackers and excluding their evidence, and dissipating high-conflicting among evidence caused by random noise and interference. To this end, this paper proposes an algorithm for credible evidence fusion against cyberattacks. Firstly, the fusion strategy is constructed based on conditionalized credibility to avoid counterintuitive fusion results caused by high-conflicting. Under this strategy, distributed evidence fusion is transformed into the average consensus problem for the weighted average value by conditional credibility of multi-source evidence (WAVCCME), which implies a more concise consensus process and lower computational complexity than existing algorithms. Secondly, a state decomposition and reconstruction strategy with weight encryption is designed, and its effectiveness for privacy-preserving under directed graphs is guaranteed: decomposing states into different random sub-states for different neighbors to defend against internal eavesdroppers, and encrypting the sub-states' weight in the reconstruction to guard against out-of-system eavesdroppers. Finally, the identities and types of attackers are identified by inter-neighbor broadcasting and comparison of nodes' states, and the proposed update rule with state corrections is used to achieve the consensus of the WAVCCME. The states of normal nodes are shown to converge to their WAVCCME, while the attacker's evidence is excluded from the fusion, as verified by the simulation on a distributed unmanned reconnaissance swarm.

Credible fusion of evidence in distributed system subject to cyberattacks

TL;DR

This work tackles credible evidence fusion in distributed systems facing cyberattacks, proposing a WAVCCME-based framework (CEFAC) that converts multi-source evidence into a distributed consensus problem. It introduces a privacy-preserving state-decomposition mechanism using Paillier encryption and a dedicated attacker identification/compensation strategy to exclude malicious evidence, all while maintaining convergence on directed graphs under strong robustness assumptions. Key contributions include proving WAVCCME as the fusion core, enabling distributed computation via KPPEEV and EVE sums, and integrating privacy and attacker-defense into a unified algorithm. Simulation results on high-conflict and cyberattack scenarios demonstrate improved accuracy and efficiency, with the ability to exclude attacker evidence and sustain credible fusion in distributed unmanned systems.

Abstract

Given that distributed systems face adversarial behaviors such as eavesdropping and cyberattacks, how to ensure the evidence fusion result is credible becomes a must-be-addressed topic. Different from traditional research that assumes nodes are cooperative, we focus on three requirements for evidence fusion, i.e., preserving evidence's privacy, identifying attackers and excluding their evidence, and dissipating high-conflicting among evidence caused by random noise and interference. To this end, this paper proposes an algorithm for credible evidence fusion against cyberattacks. Firstly, the fusion strategy is constructed based on conditionalized credibility to avoid counterintuitive fusion results caused by high-conflicting. Under this strategy, distributed evidence fusion is transformed into the average consensus problem for the weighted average value by conditional credibility of multi-source evidence (WAVCCME), which implies a more concise consensus process and lower computational complexity than existing algorithms. Secondly, a state decomposition and reconstruction strategy with weight encryption is designed, and its effectiveness for privacy-preserving under directed graphs is guaranteed: decomposing states into different random sub-states for different neighbors to defend against internal eavesdroppers, and encrypting the sub-states' weight in the reconstruction to guard against out-of-system eavesdroppers. Finally, the identities and types of attackers are identified by inter-neighbor broadcasting and comparison of nodes' states, and the proposed update rule with state corrections is used to achieve the consensus of the WAVCCME. The states of normal nodes are shown to converge to their WAVCCME, while the attacker's evidence is excluded from the fusion, as verified by the simulation on a distributed unmanned reconnaissance swarm.

Paper Structure

This paper contains 12 sections, 3 theorems, 31 equations, 11 figures, 1 table, 3 algorithms.

Table of Contents

  1. Introduction
  2. Problem formulation
  3. Distributed credible evidence fusion against cyberattacks
  4. Key to fusion: the WAVCCME
  5. Privacy-preserving WAVCCME consensus against cyberattacks
  6. Privacy protection strategy
  7. Attacker identification and attack compensation strategy
  8. Obtaining credible fusion result locally at the node
  9. Simulation and analysis
  10. Test on the fusion of high-conflict evidence
  11. Test on resistance to cyberattacks
  12. Conclusion

Key Result

Theorem 1

If one obtains $\boldsymbol{m}_{avg|A}$, it is equivalent to obtaining the fusion result of the evidence of all normal nodes according to Eqs.(eq:ICEF_Summary_1)-(eq:ICEF_Summary_4).

Figures (11)

  • Figure 1: The privacy-preserving strategy based on state decomposition.
  • Figure 2: The state decomposition and reconstruction strategy with weight encryption.
  • Figure 3: Probability density curves for the five categories
  • Figure 4: The pignistic probabilities of the fusion results for the five fusion methods.
  • Figure 5: Statistics on the frequency of recognition results of different fusion methods.
  • ...and 6 more figures

Theorems & Definitions (10)

  • Definition 2.1: $p$-fraction reachable set
  • Definition 2.2: $p$-fraction robust graph
  • Definition 2.3: Strongly $p$-fraction robust graph
  • Definition 2.4: $f$-fraction local cyberattacks model
  • Theorem 1
  • Proof 1
  • Theorem 2
  • Proof 2
  • Theorem 3
  • Proof 3