Biblio

Safety- and security-critical developers have long recognized the importance of applying a high degree of scrutiny to a system’s (or subsystem’s) I/O messages. However, lack of care in the development of message-handling components can lead to an increase, rather than a decrease, in the attack surface. On the DARPA Cyber-Assured Systems Engineering (CASE) program, we have focused our research effort on identifying cyber vulnerabilities early in system development, in particular at the Architecture development phase, and then automatically synthesizing components that mitigate against the identified vulnerabilities from high-level specifications. This approach is highly compatible with the goals of the LangSec community. Advances in formal methods have allowed us to produce hardware/software implementations that are both performant and guaranteed correct. With these tools, we can synthesize high-assurance “building blocks” that can be composed automatically with high confidence to create trustworthy systems, using a method we call Security-Enhancing Architectural Transformations. Our synthesis-focused approach provides a higherleverage insertion point for formal methods than is possible with post facto analytic methods, as the formal methods tools directly contribute to the implementation of the system, without requiring developers to become formal methods experts. Our techniques encompass Systems, Hardware, and Software Development, as well as Hardware/Software Co-Design/CoAssurance. We illustrate our method and tools with an example that implements security-improving transformations on system architectures expressed using the Architecture Analysis and Design Language (AADL). We show how message-handling components can be synthesized from high-level regular or context-free language specifications, as well as a novel specification language for self-describing messages called Contiguity Types, and verified to meet arithmetic constraints extracted from the AADL model. Finally, we guarantee that the intent of the message processing logic is accurately reflected in the application binary code through the use of the verified CakeML compiler, in the case of software, or the Restricted Algorithmic C toolchain with ACL2-based formal verification, in the case of hardware/software co-design.

Experienced developers of safety-critical and security-critical systems have long emphasized the importance of applying the highest degree of scrutiny to a system's I/O boundaries. From a safety perspective, input validation is a traditional “best practice.” For security-critical architecture and design, identification of the attack surface has emerged as a primary analysis technique. One of our current research focus areas concerns the identification of and mitigation against attacks along that surface, using mathematically-based tools. We are motivated in these efforts by emerging application areas, such as assured autonomy, that feature a high degree of network connectivity, require sophisticated algorithms and data structures, are subject to stringent accreditation/certification, and encourage hardware/software co-design approaches. We have conducted several experiments employing a state-of-the-art toolchain, due to Russinoff and O'Leary, and originally designed for use in floating-point hardware verification, to determine its suitability for the creation of safety-critical/security-critical input filters. We focus first on software implementation, but extending to hardware as well as hardware/software co-designs. We have implemented a high-assurance filter for JSON-formatted data used in an Unmanned Aerial Vehicle (UAV) application. Our JSON filter is built using a table-driven lexer/parser, supported by mathematically-proven lexer and parser table generation technology, as well as verified data structures. Filter behavior is expressed in a subset of Algorithmic C, which defines a set of C++ header files providing support for hardware design, including the peculiar bit widths utilized in that discipline, and enables compilation to both hardware and software platforms. The Russinoff-O'Leary Restricted Algorithmic C (RAC) toolchain translates Algorithmic C source to the Common Lisp subset supported by the ACL2 theorem prover; once in ACL2, filter behavior can be mathematically verified. We describe how we utilize RAC to translate our JSON filter to ACL2, present proofs of correctness for its associated data types, and describe validation and performance results obtained through the use of concrete test vectors.