Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Mitigating Timing-Based Attacks in Real-Time Cyber-Physical Systems

Arkaprava Sain, Sunandan Adhikary, Soumyajit Dey

TL;DR

Real-time CPS face timing-side-channel risks due to deterministic schedules. SecureRT mitigates this by computing bounded, delay-aware perturbations to victim control task releases and applying them online via a PFP-d scheduler, reducing the Attack Effective Window while preserving safety and control performance. The approach combines worst-case response-time analysis, a delay-aware controller synthesis, and MILP-based optimization to minimize AEW overlap with untrusted tasks. Experimental results on automotive-like task sets and a real-time Linux platform demonstrate substantial reductions in attack opportunities with acceptable control quality, highlighting practical security gains for real-time CPS.

Abstract

Real-time cyber-physical systems depend on deterministic task execution to guarantee safety and correctness. Unfortunately, this determinism can unintentionally expose timing information that enables adversaries to infer task execution patterns and carry out timing-based attacks targeting safety-critical control tasks. While prior defenses aim to obscure schedules through randomization or isolation, they typically neglect the implications of such modifications on closed-loop control behavior and real-time feasibility. This work studies the problem of securing real-time control workloads against timing inference attacks while explicitly accounting for both schedulability constraints and control performance requirements. We present a scheduling-based mitigation approach that introduces bounded timing perturbations to control task executions in a structured manner, reducing adversarial opportunities without violating real-time guarantees. The framework jointly considers worst-case execution behavior and the impact of execution delays on control performance, enabling the system to operate within predefined safety and performance limits. Through experimental evaluation on representative task sets and control scenarios, the proposed approach demonstrates that exposure to timing-based attacks can be significantly reduced while preserving predictable execution and acceptable control quality.

Mitigating Timing-Based Attacks in Real-Time Cyber-Physical Systems

TL;DR

Real-time CPS face timing-side-channel risks due to deterministic schedules. SecureRT mitigates this by computing bounded, delay-aware perturbations to victim control task releases and applying them online via a PFP-d scheduler, reducing the Attack Effective Window while preserving safety and control performance. The approach combines worst-case response-time analysis, a delay-aware controller synthesis, and MILP-based optimization to minimize AEW overlap with untrusted tasks. Experimental results on automotive-like task sets and a real-time Linux platform demonstrate substantial reductions in attack opportunities with acceptable control quality, highlighting practical security gains for real-time CPS.

Abstract

Real-time cyber-physical systems depend on deterministic task execution to guarantee safety and correctness. Unfortunately, this determinism can unintentionally expose timing information that enables adversaries to infer task execution patterns and carry out timing-based attacks targeting safety-critical control tasks. While prior defenses aim to obscure schedules through randomization or isolation, they typically neglect the implications of such modifications on closed-loop control behavior and real-time feasibility. This work studies the problem of securing real-time control workloads against timing inference attacks while explicitly accounting for both schedulability constraints and control performance requirements. We present a scheduling-based mitigation approach that introduces bounded timing perturbations to control task executions in a structured manner, reducing adversarial opportunities without violating real-time guarantees. The framework jointly considers worst-case execution behavior and the impact of execution delays on control performance, enabling the system to operate within predefined safety and performance limits. Through experimental evaluation on representative task sets and control scenarios, the proposed approach demonstrates that exposure to timing-based attacks can be significantly reduced while preserving predictable execution and acceptable control quality.
Paper Structure (14 sections, 1 theorem, 21 equations, 10 figures, 2 tables, 1 algorithm)

This paper contains 14 sections, 1 theorem, 21 equations, 10 figures, 2 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. Residue-based Anomaly Detector
  4. Attack Model
  5. Methodology
  6. Peak Job-level Delay Derivation using RTA
  7. Response Time Analysis of Victim Task
  8. Response Time Analysis of lower priority Non-victim Tasks
  9. Peak Job-level Delay and Overall System Schedulability
  10. Maximum Delay Bound for Control Tasks
  11. Formulation of the Optimization Problem
  12. Runtime Algorithm for SecureRT Framework
  13. Experimental Evaluation
  14. Conclusion and Future Work

Key Result

Lemma 1

Given a uniprocessor system scheduled with PFP, let $\tau_v$ be a victim control task and $\tau_{v,k}$ denote its $k$-th job, released at time $r'_{v,k}$ with a delay $\delta$. The total interference $I(k)$ from the carry-in jobs of $hp(\tau_v)$ that were released before $r'_{v,k}$ and are still exe

Figures (10)

  • Figure 1: Overview of the System Model
  • Figure 2: Attack Effective Window
  • Figure 3: Overview of the SecureRT framework
  • Figure 4: Interference faced by victim $\tau_v$ from $hp(\tau_v)$
  • Figure 5: Task schdule with job-level delay $\delta =6$
  • ...and 5 more figures

Theorems & Definitions (5)

  • Definition 1: Job-Level Delay
  • Lemma 1
  • proof
  • Definition 2: Maximum Admissible Delay
  • Example 1