公开(公告)号：US20230236868A1

公开(公告)日：2023-07-27

申请号：US18157379

申请日：2023-01-20

Applicant: Google LLC

Inventor： Hao Zhou ,  Mahesh Pisal ,  Kenneth L. Hofsass ,  Timothy Dylan Peacock

IPC: G06F9/455

CPC classification number: G06F9/45558 ,  G06F2009/45583 ,  G06F2009/4557 ,  G06F2009/45587

Abstract: A virtual machine malware detection service caches contents that correspond to operating system registries. By caching the content of important registers, the malware detector is able to efficiently traverse virtual machine memory contents to identify important operating system properties. Examples of such operating system properties include a list of running processes. The malware detector replaces agent-based threat detection for compute endpoints. The malware detector detects cryptocurrency miners and malware by scanning guest virtual machine (VM) memories. The guest VM memory may be scanned according to the guest physical address. According to some examples, the memories of guest user processes may be scanned one by one, using the page table address for each guest process to efficiently locate its memory.

公开(公告)号：US20240362093A1

公开(公告)日：2024-10-31

申请号：US18231606

申请日：2023-08-08

Applicant: GOOGLE LLC

Inventor： Hao Zhou ,  Jamie Hall ,  Xinying Song ,  Sahitya Potluri ,  Yu Du ,  Heng-Tze Cheng ,  Quoc Le ,  Ed H. Chi

IPC: G06F9/54 ,  G06F16/242

CPC classification number: G06F9/547 ,  G06F16/243

Abstract: At least utilizing a custom corpus of documents to condition a large language model (LLM) when generating a response to a user query. In some implementations, a user query associated with a client device is received. An API query for an external application is generated by an LLM based on the user query. The external application has access to a custom corpus of documents comprising a plurality of documents. The external application is queried using the API query. Data representative of one or more documents in the custom corpus of documents is received from the external application in response to the API query. The LLM generates a response to the query that is conditioned on the data representing one or more of the documents in the custom corpus of documents received from the external application. The response to the user query is caused to be rendered on the client device.

公开(公告)号：US20240289395A1

公开(公告)日：2024-08-29

申请号：US18528142

申请日：2023-12-04

Applicant: Google LLC

Inventor： Hao Zhou ,  Shrestha Basu Mallick ,  Trevor Strohman ,  Patricia Luisa Romero Domingo ,  Amirhossein Kiani ,  Yu Du ,  Xinying Song ,  Heng-Tze Cheng ,  Quoc V. Le ,  Ed Huai-Hsin Chi ,  Christopher Jamie Maclean Hall

IPC: G06F16/9532 ,  G06F16/955 ,  G06F40/40

CPC classification number: G06F16/9532 ,  G06F16/955 ,  G06F40/40

Abstract: Implementations relate to helping a large language model generate factual responses to prompts that request factual content is disclosed. The large language model may receive a prompt context, a plurality of encoded context passages as input. The large language model is trained to determine whether or not to utilize the encoded context passages in generating the response. Implementations also relate to different methods of fine-tuning the responses generated by the large language model through query refinements, response re-writes, and evaluation of factual accuracy.