skip to main content

Title: Dynamic analysis methods for detecting anomalies in asynchronously interacting systems

Detecting modifications to digital system designs, whether malicious or benign, is problematic due to the complexity of the systems being analyzed. Moreover, static analysis techniques and tools can only be used during the initial design and implementation phases to verify safety and liveness properties. It is computationally intractable to guarantee that any previously verified properties still hold after a system, or even a single component, has been produced by a third-party manufacturer. In this paper we explore new approaches for creating a robust system design by investigating highly-structured computational models that simplify verification and analysis. Our approach avoids the need to fully reconstruct the implemented system by incorporating a small verification component that dynamically detects for deviations from the design specification at run-time. The first approach encodes information extracted from the original system design algebraically into a verification component. During run-time this component randomly queries the implementation for trace information and verifies that no design-level properties have been violated. If any deviation is detected then a pre-specified fail-safe or notification behavior is triggered. Our second approach utilizes a partitioning methodology to view liveness and safety properties as a distributed decision task and the implementation as a proposed protocol that solvesmore » this task. Thus the problem of verifying safety and liveness properties is translated to that of verifying that the implementation solves the associated decision task. We develop upon results from distributed systems and algebraic topology to construct a learning mechanism for verifying safety and liveness properties from samples of run-time executions.« less
 [1] ;  [1] ;  [2]
  1. Sandia National Lab. (SNL-CA), Livermore, CA (United States)
  2. Max Planck Society, Garching (Germany). Max Planck Inst. for Mathematics
Publication Date:
OSTI Identifier:
Report Number(s):
DOE Contract Number:
Resource Type:
Technical Report
Research Org:
Sandia National Lab. (SNL-CA), Livermore, CA (United States); Max Planck Institute for Mathematics,, Bonn, Germany
Sponsoring Org:
USDOE National Nuclear Security Administration (NNSA)
Country of Publication:
United States