Patents by Inventor Mei Wang

Mei Wang has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20260350169
    Abstract: A genetic algorithm is implemented to generate prompts that evade content filters of generative artificial intelligence (AI) systems. The genetic algorithm applies grammar operations to mutate candidate prompts, communicates the candidate prompts to generative AI systems, and selects candidate prompts that successfully evade content filters according to corresponding responses. A disambiguation model that corrects grammar in prompts is tested on the selected prompts to determine if grammar is properly corrected. Once tested, the disambiguation model is deployed in an ensemble with a classifier that outputs verdicts for prompts with grammar corrected by the disambiguation model.
    Type: Application
    Filed: June 30, 2026
    Publication date: November 5, 2026
    Inventors: Yu Fu, Mei Wang
  • Patent number: 12774337
    Abstract: The present disclosure provides anti-FGFR2b antibodies or antigen-binding fragments thereof, isolated polynucleotides encoding the same, pharmaceutical compositions comprising the same, and the uses thereof.
    Type: Grant
    Filed: December 23, 2020
    Date of Patent: October 27, 2026
    Assignee: DIZAL PHARMACEUTICAL CO., LTD.
    Inventors: Mei Wang, Qiuli Guo, Yu Bai, Zhenfan Yang, Xiaolin Zhang
  • Publication number: 20260330016
    Abstract: A prompt injection detection system intercepts queries to a generative artificial intelligence (AI) system and generates a response to the query with a first large language model (LLM). A second LLM is then instructed to determine a number of intents of the query, a true question the query is asking, whether the response is responsive to the true question the query is asking, and an explanation for the response being responsive or non-responsive to the true question. If the response is non-responsive to the true question of the query, the detection system blocks the query from being communicated/input to the generative AI system and flags the query as potentially being associated with a token smuggling prompt injection attack.
    Type: Application
    Filed: July 26, 2024
    Publication date: October 22, 2026
    Inventors: Yu Fu, Chien-Hua Lu, Mei Wang, Shengming Xu, Bo Qu
  • Publication number: 20260332609
    Abstract: An indication of a potential network threat and one or more network entries associated with the potential network threat are received. One or more example network exploit content associated with the potential network threat are identified. At least a portion of the one or more network entries and at least a portion of the identified one or more example network exploit content are analyzed using a large language model to determine a large language model output associated with whether the potential network threat is a false positive threat. The large language model output is utilized to provide a computer security analysis result.
    Type: Application
    Filed: April 21, 2025
    Publication date: October 22, 2026
    Inventors: Lin Li, Yu Fu, Chao Lei, Mei Wang
  • Publication number: 20260332636
    Abstract: A security feed normalizer aggregates and normalizes threat intelligence data across security feeds and extracts threat descriptors of cybersecurity threats from the aggregated/normalized data. A first large language model (LLM) determines whether each threat descriptor is informative, i.e., comprises sufficient information for reproducing/generating network traffic of the corresponding cybersecurity threat. For informative threat descriptors, a second LLM generates network traffic for the corresponding cybersecurity threats. The generated network traffic is used for subsequent remediation of corresponding threats.
    Type: Application
    Filed: June 29, 2026
    Publication date: October 22, 2026
    Inventors: Abisheik Ganesan, Zhibin Zhang, Qi Deng, Yu Fu, Mei Wang
  • Publication number: 20260318846
    Abstract: The present disclosure discloses an optical path defining element, comprising a mounting base, a first reflective structure, and a second reflective structure, wherein the mounting base has an obliquely arranged mounting surface and an elongated hole, the elongated hole runs through the mounting base from the mounting surface and divides the mounting surface into a first mounting surface and a second mounting surface, the first mounting surface and the second mounting surface are respectively configured to mount the first reflective structure and the second reflective structure, the first reflective structure and the second reflective structure reflect light incident from an incident light source to the side edge of the object to be detected, and the light passes through the elongated hole to a detection camera after being reflected by the side edge of the object to be detected.
    Type: Application
    Filed: November 7, 2023
    Publication date: October 15, 2026
    Inventors: Dong Yan, Chang Li, Rui Hong, Mei Wang, Fei Xu, Haifeng Bian, Wenlong Xiao, Zetong Li, Dongdong Xue, Xiaoyi Gu, Jie Han
  • Publication number: 20260312978
    Abstract: Techniques for detecting anomalous network behavior in operational technology (OT) network traffic are disclosed. In some embodiments, a system, a process, and/or a computer program product for detecting anomalous OT behavior includes receiving, from a firewall that monitors OT network traffic, OT event data generated from a plurality of traffic sessions associated with one or more OT devices; grouping the OT event data according to successive time intervals; generating, for each time interval, an interval feature vector comprising categorical OT protocol features and dynamic network behavior features extracted from the OT event data; applying an anomaly detection model to the interval feature vector to obtain an anomaly score for the time interval; determining, based on a comparison of the anomaly score with a threshold, that the OT network traffic associated with the time interval corresponds to anomalous OT behavior; and performing an action in response to the anomalous OT behavior.
    Type: Application
    Filed: June 18, 2026
    Publication date: October 8, 2026
    Inventors: Ke Tian, Aveek Kumar Das, Derick Liang, Rahul Rajewar, Gong Cheng, Mei Wang
  • Publication number: 20260306525
    Abstract: Combination therapy glucocorticoids and ginsenoside The invention relates to a ginsenoside formulation comprising a PPT-type ginsenoside at least partly incorporated in a micelle, preferably at least partly incorporated in an outer layer of the micelle, said micelle having a molecular weight of at least 10.000 Da and a ginsenoside for use in a method of prevention or treatment of a side-effect of glucocorticoid (GC) treatment, said method comprising administering a ginsenoside to a subject that is suffering from, or at risk of suffering from, one or more side-effect(s) of GC treatment. The invention also relates to a combination of a glucocorticoid (GC) and a ginsenoside for use in a method of prevention or treatment of an inflammatory disease, wherein said method comprises administering a GC and a PPT-type ginsenoside in a particular molar ratio.
    Type: Application
    Filed: May 8, 2024
    Publication date: October 8, 2026
    Inventors: Mahmoud HALIMA, Annemarie Henrietta MEIJER, Mei WANG, Marcel Johannes Maria SCHAAF, Henricus Adriaan Anna Jacobus KORTHOUT, Albert VAN DUIJN, Frederik Pius VAN HORSSEN
  • Publication number: 20260291965
    Abstract: Data packets transmitted to and from an IoT device are obtained and at least one of the data packets are analyzed using deep packet inspection to identify transaction data from payload of the at least one of the data packets. An event log is generated for the IoT device from the transaction data, the event log, at least in part, used to generate a historical record for the IoT device. The IoT device into a device profile based on the historical record for the IoT device. The event log is updated in real-time to indicate current operation of the IoT device. Abnormal device behavior of the IoT device is determined using the event log and the device profile. The device profile is updated to indicate the abnormal device behavior of the IoT device.
    Type: Application
    Filed: March 19, 2025
    Publication date: September 24, 2026
    Inventors: Gong Cheng, Pui-Chuen Yip, Zhiwei Xiao, Ran Xia, Mei Wang
  • Publication number: 20260287566
    Abstract: The present disclosure provides a method for quantitative analysis of loads inside and outside a carbon nanotube, including the following steps: (1) placing a carbon nanotube loaded with metal catalyst particles in a tube furnace, and vacuuming the tube furnace; (2) annealing and end-capping; (3) calcining to obtain a calcined carbon nanotube, adding the calcined carbon nanotube to a reactor, adding dilute sulfuric acid to the reactor, and heating and stirring to obtain a metal sulfate solution, and an end-capped carbon nanotube having metal catalyst particles loaded inside; (4) determining a nickel load inside the carbon nanotube by ICP-MS; and (5) determining a content of metal ions in the metal sulfate solution by EDTA complexometric titration.
    Type: Application
    Filed: January 16, 2024
    Publication date: September 24, 2026
    Applicant: Jiangsu University
    Inventors: Bingliang ZHOU, Xiujuan LIU, Anthony DICHIARA, Nanqing LIU, Mei WANG
  • Publication number: 20260267311
    Abstract: A collision detection system for a five-axis CNC machine tool, an electronic device, and a storage medium are provided, which relate to the field of numerical control machine tools. The five-axis CNC machine tool collision detection system includes: a machine tool tree construction module, a coordinate system transformation module, a joint parameter calculation module, a motion simulation module, and a collision detection module. The system sets inner nodes and outer nodes according to a machine tool structure and obtains offsets; calculates homogeneous transformation matrices; reads a numerical control program and calculates joint parameters of the machine tool; performs motion simulation; and calculates absolute coordinates of surface points of links of two joints during the motion simulation to perform collision detection between two sets of meshes.
    Type: Application
    Filed: March 3, 2026
    Publication date: September 10, 2026
    Inventors: Mei WANG, Shuyan GAO, Tao HUANG, Yuxiao PAN, Wenqiang YAN, Xiaoming ZHANG, Han DING
  • Publication number: 20260259991
    Abstract: A testing environment provisioning service obtains configuration information for an AI application based on monitoring its deployment environment to determine an initial configuration thereof. Configuration information included in the initial configuration includes configuration information for the language model(s) used by the AI application, a prompt template(s) used by the AI application, and a configuration of a content filter that interfaces with the language model(s). The service monitors the deployment environment for changes to this initial configuration by periodically obtaining additional configuration information for the deployment environment and evaluating the additional configuration information against initial configuration. When a substantial change to the initial configuration is detected, the testing service updates the initial configuration and provisions a testing environment with a language model(s) and any content filter configured according to the updated configuration.
    Type: Application
    Filed: February 28, 2025
    Publication date: September 3, 2026
    Inventors: Jay Chien An Chen, Chien-Hua Lu, Bo Qu, Wenjun Hu, Ali Islam, Mei Wang
  • Patent number: 12723091
    Abstract: Provided are anti-FGFR2b antibodies or antigen-binding fragments thereof, isolated polynucleotides encoding the same, pharmaceutical compositions comprising the same, and the uses thereof.
    Type: Grant
    Filed: December 23, 2020
    Date of Patent: September 1, 2026
    Assignee: DIZAL (JIANGSU) PHARMACEUTICAL CO., LTD.
    Inventors: Mei Wang, Qiuli Guo, Yu Bai, Zhenfan Yang, Xiaolin Zhang
  • Publication number: 20260252260
    Abstract: A semiconductor device, a memory, a system and a method of data processing are disclosed in the present disclosure. An example semiconductor device includes a logic die and a plurality of memory dies which are stacked, the logic die comprises a plurality of data processing units each comprising a serial-parallel conversion circuit and an interface circuit. The interface circuit is configured to output the second readout data to a processor and receive first write data with a bit width of N from the processor and transmit the first write data to the serial-parallel conversion circuit. The serial-parallel conversion circuit is configured to parallelize the first write data to obtain second write data with a bit width of M and transmit the second write data to the at least one of the memory dies, wherein M and N are positive integers, and M/N is greater than or equal to 2.
    Type: Application
    Filed: August 25, 2025
    Publication date: August 27, 2026
    Inventors: Chunyuan HOU, Zongliang HUO, Jiawei CHEN, Mei WANG, Wenjie MU
  • Publication number: 20260252464
    Abstract: A testing framework conducts a dialogue with a multi-modal foundation model to determine how to interact with an application via a user interaction emulator tool based on images captured from the UI of the application. Initially, the testing framework will capture an image of the application UI. The testing framework then prompts the foundation model to explain how to interact with the application to achieve a function of the application given the captured image. The testing framework derives commands from the model response for running the user interaction emulator tool and captures an image of the application UI after the interaction and again prompts the foundation model to determine whether the function was successfully performed or to explain a failure. The testing framework continues the dialogue with successive prompts for interaction with the application informed by the explanation of preceding failure.
    Type: Application
    Filed: February 21, 2025
    Publication date: August 27, 2026
    Inventors: Yu Fu, Lin Li, Wenjun Hu, Mei Wang
  • Publication number: 20260246802
    Abstract: Various techniques for LLM powered detection reasoning solutions are disclosed. In some embodiments, a system, a process, and/or a computer program product for an LLM powered detection reasoning solution includes monitoring network traffic at a security platform, wherein the security platform generates a sample based on the monitored network traffic; sending the sample to a security service to generate a Large Language Model (LLM) powered detection and reason, wherein the LLM is prompted to automatically generate a malware or benign verdict and a reason for explaining the verdict; and reporting the LLM powered detection and reason.
    Type: Application
    Filed: April 10, 2026
    Publication date: August 20, 2026
    Inventors: Zhibin Zhang, Yu Fu, Yuwen Dai, Qian Feng, Zhemin Su, Mei Wang
  • Patent number: 12704303
    Abstract: A gas-liquid separation device includes a first cylinder, a second cylinder, a heat exchange assembly and a gas-liquid separation assembly. The gas-liquid separation device defines a first cavity and a second cavity. The first cavity includes a space between the first cylinder and the second cylinder. The second cavity includes an inner cavity of the second cylinder. The gas-liquid separation assembly is at least partially located in the second cavity. An inner cavity of the gas-liquid separation assembly is in communication with the first cavity and the second cavity. At least part of the heat exchange assembly is located in the first cavity. The gas-liquid separation device includes a first pipe portion. A pipe cavity of the first pipe portion communicates with the second cavity and an outer space of the first cylinder. A thermal management system having the gas-liquid separation device is also disclosed.
    Type: Grant
    Filed: December 27, 2023
    Date of Patent: August 11, 2026
    Assignee: ZHEJIANG SANHUA INTELLIGENT CONTROLS CO., LTD.
    Inventors: Haimin Shi, Chaochao Cao, Mei Wang
  • Publication number: 20260228251
    Abstract: A prompt reinforcement tool (“tool”) compares benign sample prompts to determine common and differing content across the prompts. The tool prompts a LLM to identify system prompt components from the common prompt content and identify user inputs and additional inputs from the differing prompt content. The tool also prompts the LLM to extract prompt components based on the response samples. The prompt reinforcement tool updates an application agnostic prompt template and generates an application tailored prompt template. To update, the tool removes irrelevant sections and populates remaining/preserved sections of the application agnostic prompt template that correspond to the identified system prompt components and the extracted prompt components. The tool then inserts, adjacent to template sections for user input and additional input, placeholders for a secure wrapper and inserts a guardrail instruction to isolate any commands or instructions that may be in the user input or additional input.
    Type: Application
    Filed: January 31, 2025
    Publication date: August 6, 2026
    Inventors: Jay Chien An Chen, Chien-Hua Lu, Sahil Mehta, Jaimin Pankajkumar Patel, Sergey Sviridov, Mei Wang
  • Patent number: 12701138
    Abstract: A security feed normalizer aggregates and normalizes threat intelligence data across security feeds and extracts threat descriptors of cybersecurity threats from the aggregated/normalized data. A first large language model (LLM) determines whether each threat descriptor is informative, i.e., comprises sufficient information for reproducing/generating network traffic of the corresponding cybersecurity threat. For informative threat descriptors, a second LLM generates network traffic for the corresponding cybersecurity threats. The generated network traffic is used for subsequent remediation of corresponding threats.
    Type: Grant
    Filed: October 17, 2024
    Date of Patent: August 4, 2026
    Assignee: Palo Alto Networks, Inc.
    Inventors: Abisheik Ganesan, Zhibin Zhang, Qi Deng, Yu Fu, Mei Wang
  • Publication number: 20260222442
    Abstract: A system facilitates multi-session, multi-aspect analysis of conversations between users and applications that leverage language models (“generative AI applications”). The system retrieves conversation logs for conversations carried out between users and a generative AI application(s) and sorts the conversation logs by conversation. The system analyzes the conversations in multiple aspects for various use cases: security, analytics, and organizational compliance. In the security analysis, the system analyzes the queries and responses of each conversation to determine if the conversation includes a multi-turn attack. For the analytics and organization compliance use cases, the system evaluates how end users are using the generative AI application(s) across conversations to provide customers with additional insights, such as the spread of subject matter areas for which employees are using the generative AI application(s).
    Type: Application
    Filed: January 30, 2025
    Publication date: July 30, 2026
    Inventors: Anand Oswal, Xu Zou, Yu Fu, Mei Wang