Abstract: The description relates to automated binary code summarization. In one example, a binary code summarization tool receives binary code and combines the received binary code with natural language in a prompt for a large language model (LLM). The binary code summarization tool receives a semantic summarization from the LLM relating to the received binary code and evaluates the new semantic summarization for malicious functionality in the received binary code.

Abstract: Aspects of the present disclosure relate to retrospective memory analysis. In examples, a historical archive of memory images for an execution environment is maintained. A historical memory image of the historical archive may be evaluated according to a current set of known issues, rather than issues that were known at the time of the memory capture. Accordingly, it may be possible to determine when the execution environment was last in a good environment condition. As another example, it may be possible to determine whether a now-known issue has since been resolved (e.g., such that the issue would not be identified in the current execution environment). Thus, as compared to contemporaneous issue identification techniques, aspects of the present disclosure may be applied to any number of execution environments to enable retrospective identification of now-known issues that were, at least at the time of a memory capture, not known.

Abstract: This disclosure describes an expert system that can be used to automatically understand the function of a binary. The expert system includes a large language model (LLM) to determine investigatory steps that are implemented by a suite of tools. One application is malware detection. The expert system uses the tools to gather data and manipulate the binary to gain greater understanding of its function. Data generated during the investigation can be stored and retrieved from a memory representation system. This involves the LLM designing an investigation plan based on both default choices and responses to the data gathered using the tools. The expert system can adjust the plan after each step. Translators use expert knowledge and understanding of tool functions to convert tool outputs into natural language prompts that can be meaningfully understood by the LLM and to convert natural language output by the LLM into calls to the tools.

Abstract: The description relates to automated binary code summarization. In one example, a binary code summarization tool receives binary code and combines the received binary code with natural language in a prompt for a large language model (LLM). The binary code summarization tool receives a semantic summarization from the LLM relating to the received binary code and evaluates the new semantic summarization for malicious functionality in the received binary code.

Abstract: Aspects of the present disclosure relate to retrospective memory analysis. In examples, a historical archive of memory images for an execution environment is maintained. A historical memory image of the historical archive may be evaluated according to a current set of known issues, rather than issues that were known at the time of the memory capture. Accordingly, it may be possible to determine when the execution environment was last in a good environment condition. As another example, it may be possible to determine whether a now-known issue has since been resolved (e.g., such that the issue would not be identified in the current execution environment). Thus, as compared to contemporaneous issue identification techniques, aspects of the present disclosure may be applied to any number of execution environments to enable retrospective identification of now-known issues that were, at least at the time of a memory capture, not known.

Abstract: Aspects of the present disclosure relate to retrospective memory analysis. In examples, a historical archive of memory images for an execution environment is maintained. A historical memory image of the historical archive may be evaluated according to a current set of known issues, rather than issues that were known at the time of the memory capture. Accordingly, it may be possible to determine when the execution environment was last in a good environment condition. As another example, it may be possible to determine whether a now-known issue has since been resolved (e.g., such that the issue would not be identified in the current execution environment). Thus, as compared to contemporaneous issue identification techniques, aspects of the present disclosure may be applied to any number of execution environments to enable retrospective identification of now-known issues that were, at least at the time of a memory capture, not known.

Abstract: Aspects of the present disclosure relate to retrospective memory analysis. In examples, a historical archive of memory images for an execution environment is maintained. A historical memory image of the historical archive may be evaluated according to a current set of known issues, rather than issues that were known at the time of the memory capture. Accordingly, it may be possible to determine when the execution environment was last in a good environment condition. As another example, it may be possible to determine whether a now-known issue has since been resolved (e.g., such that the issue would not be identified in the current execution environment). Thus, as compared to contemporaneous issue identification techniques, aspects of the present disclosure may be applied to any number of execution environments to enable retrospective identification of now-known issues that were, at least at the time of a memory capture, not known.