ChatGPT for Vulnerability Detection, Classification, and Repair: How Far Are We?Part 1. Title & SourceTitle: ChatG

The Devil is in the Tails: How Long-Tailed Code  Distributions Impact Large Language ModelsPart1. title&SourceTitl

Natural Attack for Pre-trained Models of CodePart 1. Title & SourceTitle: Natural Attack for Pre-trained Models of

Code Security Vulnerability Repair Using Reinforcement Learning with Large Language ModelsPart 1: 标题 & 作者标题: 基于强化学

[Large Language Models for Code: Security Hardening and Adversarial Testing]Paper Summary (What) Main takeaway: This p

[LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework

Large Language Models for Code Analysis: Do LLMs Really Do Their Job? The paper evaluates the effectiveness of large

[Large Language Model for Vulnerability Detection and Repair: Literature Review and the Road Ahead]Paper summaryTLD

BERT: Pre-training of Deep Bidirectional Transformers for Language UnderstandingPaper | Talk Part1. 标题&作者Pre-trai

ML知识点汇总1.LSTM 原理分析 2.预训练思想有了图像领域预训练的引入，我们在此给出预训练的思想：任务 A 对应的模型 A 的参数不再是随机初始化的，而是通过任务 B 进行预先训练得到模型 B，然后利用模型 B 的参数对模型 A