Measuring Impacts of Poisoning on Model Parameters and Embeddings for Large Language Models of Code

被引：0
|
作者：
University of Houston, Houston, United States [1 ]
机构：
来源：
AIware - Proc. ACM Int. Conf. AI-Powered Softw., Co-located: ESEC/FSE | 1600年 / 59-64期
关键词：
Backdoors - Embeddings - Language model - Large language model of code - Model embedding - Modeling parameters - Safe AI - Software development practices - Trojan detections - Trojans;
D O I：
1st ACM International Conference on AI-Powered Software, AIware 2024, co-located with the ACM International Conference on the Foundations of Software Engineering, FSE 2024
中图分类号：
学科分类号：
摘要：
41
引用
收藏
相关论文
共 50 条
  • [1] Measuring Impacts of Poisoning on Model Parameters and Embeddings for Large Language Models of Code
    Hussain, Aftab
    Rabin, Md Rafiqul Islam
    Alipour, Mohammad Amin
    PROCEEDINGS OF THE 1ST ACM INTERNATIONAL CONFERENCE ON AI-POWERED SOFTWARE, AIWARE 2024, 2024, : 59 - 64
  • [2] Improving Text Embeddings with Large Language Models
    Wang, Liang
    Yang, Nan
    Huang, Xiaolong
    Yang, Linjun
    Majumder, Rangan
    Wei, Furu
    PROCEEDINGS OF THE 62ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1: LONG PAPERS, 2024, : 11897 - 11916
  • [3] Text clustering with large language model embeddings
    Petukhova, Alina
    Matos-Carvalho, João P.
    Fachada, Nuno
    International Journal of Cognitive Computing in Engineering, 2025, 6 : 100 - 108
  • [4] Evolving code with a large language model
    Hemberg, Erik
    Moskal, Stephen
    O'Reilly, Una-May
    GENETIC PROGRAMMING AND EVOLVABLE MACHINES, 2024, 25 (02)
  • [5] CoLLM: Integrating Collaborative Embeddings Into Large Language Models for Recommendation
    Zhang, Yang
    Feng, Fuli
    Zhang, Jizhi
    Bao, Keqin
    Wang, Qifan
    He, Xiangnan
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2025, 37 (05) : 2329 - 2340
  • [6] Poisoning medical knowledge using large language models
    Yang, Junwei
    Xu, Hanwen
    Mirzoyan, Srbuhi
    Chen, Tong
    Liu, Zixuan
    Liu, Zequn
    Ju, Wei
    Liu, Luchen
    Xiao, Zhiping
    Zhang, Ming
    Wang, Sheng
    NATURE MACHINE INTELLIGENCE, 2024, 6 (10) : 1156 - 1168
  • [7] Large Language Models of Code Fail at Completing Code with Potential Bugs
    Tuan Dinh
    Zhao, Jinman
    Tan, Samson
    Negrinho, Renato
    Lausen, Leonard
    Zha, Sheng
    Karypis, George
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [8] Utility of word embeddings from large language models in medical diagnosis
    Yazdani, Shahram
    Henry, Ronald Claude
    Byrne, Avery
    Henry, Isaac Claude
    JOURNAL OF THE AMERICAN MEDICAL INFORMATICS ASSOCIATION, 2025, 32 (03) : 526 - 534
  • [9] Can large language models generate geospatial code?
    State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China
    不详
    arXiv, 1600,
  • [10] Code Comprehension: Review and Large Language Models Exploration
    Cui, Jielun
    Zhao, Yutong
    Yu, Chong
    Huang, Jiaqi
    Wu, Yuanyuan
    Zhao, Yu
    2024 IEEE 4TH INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING AND ARTIFICIAL INTELLIGENCE, SEAI 2024, 2024, : 183 - 187
12345