| Popis: |
Code Reuse Attacks (CRA) represent a type of control flow hijacking that attackers exploit to manipulate the standard program execution path, resulting in abnormal processor behaviors. In response to the security concern, proposals for Control Flow Integrity (CFI) verification have emerged. The CFI scheme diligently monitors program jumps during execution, effectively restraining abnormal program execution and robustly safeguarding against CRA. This paper provides a comprehensive analysis and synthesis of the current state of hardware-based CFI implementations. In this survey, we initially discuss common attack methods and variations of predominant CRA, elucidating the general procedural steps intrinsic to such attacks. We delve into the protective capacities inherent in contemporary hardware-based CFI implementations. By conducting a thorough examination and organization of diverse research endeavors on hardware-based CFI, we systematically classify CFI based on implementation methodologies, including label verification, instruction encryption, stack edge detection, instruction tracing, sensitive data isolation, and basic block validation. We provide comprehensive explanations and critical evaluations for each category followed by comparative analyses while offering personal insights on the evolution of hardware-based CFI. |
