Model Releases
Security in LLM-Assisted Coding: A Systematic Literature Review
arXiv:2610.15482v1 Announce Type: cross Abstract: Large Language Models accelerate software development but introduce severe security vulnerabilities. This systematic review investigates security risk
arXiv:2610.15482v1 Announce Type: cross Abstract: Large Language Models accelerate software development but introduce severe security vulnerabilities. This systematic review investigates security risks in automated coding, benchmark limitations, and the role of human developers. Findings indicate that models frequently generate insecure code and faulty patches due to training data biases. Additionally, the models themselves are susceptible to direct attacks. Current evaluation methods suffer from data contamination and lack robust security metrics. Consequently, human oversight remains essential. Safer integration of automation will require more security-aware model architectures, stronger security-specific benchmarks, and more effective human-AI collaboration frameworks to mitigate these systemic risks.
Related
- Poster: Rethinking Security in LLM Code Generation through Real-World Risk Scenarios
- Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
- Exploring Automated Vulnerability Identification in JavaScript Code Using Large Language Models
- Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports
Source: arXiv cs.AI | 2026-10-15