LLM의 취약점에 대한 설명, 방지법 등을 시나리오별로 설명
LLM01:2023 - Prompt Injections
LLM02:2023 - Data Leakage
LLM03:2023 - Inadequate Sandboxing
LLM04:2023 - Unauthorized Code Execution
LLM05:2023 - SSRF Vulnerabilities
LLM06:2023 - Overreliance on LLM-generated Content
LLM07:2023 - Inadequate AI Alignment
LLM08:2023 - Insufficient Access Controls
LLM09:2023 - Improper Error Handling
LLM10:2023 - Training Data Poisoning
https://owasp.org/www-project-top-10-for-large-language-model-applications/descriptions/
https://owasp.org/www-project-top-10-for-large-language-model-applications/descriptions/
OWASP Top 10 List for Large Language Models version 0.1 This is a draft list of important vulnerability types for Artificial Intelligence (AI) applications built on Large Language Models (LLMs) Description: Bypassing filters or manipulating the LLM using c
owasp.org
'03.Security' 카테고리의 다른 글
| 네트워크 보안 - NDR(Network Detection and Response) (0) | 2025.04.25 |
|---|---|
| LLM - 보안 - 탈옥(Jailbreaking) (0) | 2025.04.25 |
| 개인정보 - 비식별 - 비정형 데이터 가명처리 (0) | 2025.04.24 |
| 개인정보 - 비식별 - 가명정보 처리 (0) | 2025.04.24 |
| 가상화 - 망분리 - 규제완화 (0) | 2025.04.24 |
