Meta Research
- LLM Security; twitter @llm_sec
Technical Reports
- GPT-4 Technical Report
- CodeT5+: Open Code Large Language Models for Code Understanding and Generation
- Tree of Thoughts: Deliberate Problem Solving with Large Language Models
LLM for Security
Fuzzing
- Large Language Models are Zero-Shot Fuzzers: Fuzzing Deep-Learning Libraries via Large Language Models
- Large Language Models are Edge-Case Fuzzers: Testing Deep Learning Libraries via FuzzGPT
- Large Language Models for Fuzzing Parsers (Registered Report)
- Universal Fuzzing via Large Language Models
Program Repair
- A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification
- InferFix: End-to-End Program Repair with LLMs over Retrieval-Augmented Prompts
- Frustrated with Code Quality Issues? LLMs can Help!
- Examining Zero-Shot Vulnerability Repair with Large Language Models
Code Analysis
Test Geenration
- Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction
- An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation