#ai-security

총 2건 · 1/1 페이지

전체 24시간 7일 30일

Hacker News (front) · 2026-06-26 제목번역

2,000명이 내 AI 어시스턴트를 해킹하려 했을 때 일어난 일

What happened after 2,000 people tried to hack my AI assistant — Fernando Irarrázaval

<p>Article URL: <a href="https://www.fernandoi.cl/posts/hackmyclaw/">https://www.fernandoi.cl/posts/hackmyclaw/</a></p> <p>Comments URL: <a href="https://news.ycombinator.com/item?…

#ai-safety #ai-security #adversarial-attacks #vulnerability #hacking
Hacker News (front) · 2026-06-04 제목번역

취약한 앱을 직접 만들고 LLM이 해킹할 수 있는지 $1,500을 들여 테스트해봤다

I built a vulnerable app and spent $1,500 seeing if LLMs could hack it

<p>Article URL: <a href="https://kasra.blog/blog/i-spent-1500-seeing-if-llms-could-hack-my-app/">https://kasra.blog/blog/i-spent-1500-seeing-if-llms-could-hack-my-app/</a></p> <p>C…

#ai-security #security-testing #llm-hacking #vulnerability-assessment #red-teaming #penetration-testing