# Meta's AI Safety System Defeated by Simple Space Bar Hack 🔓

**URL:** <https://onehack.st/t/metas-ai-safety-system-defeated-by-simple-space-bar-hack/288061>\
**Category:** News & Articles\
**Created:** [August 1, 2024, 3:41am UTC](https://onehack.st/t/metas-ai-safety-system-defeated-by-simple-space-bar-hack/288061 "2024-08-01T03:41:38Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![TheJoker](https://onehack.st/user_avatar/onehack.st/thejoker/32/22660_2.png) [@TheJoker](https://onehack.st/u/TheJoker)\
**Post date:** [August 1, 2024, 3:41am UTC](https://onehack.st/t/metas-ai-safety-system-defeated-by-simple-space-bar-hack/288061/1 "2024-08-01T03:41:38Z")

</div>

**Summary:**

1. **Vulnerability in AI Guardrails** : Meta’s Prompt-Guard-86M, designed to detect harmful prompt injections in AI, is easily bypassed by adding spaces between letters and omitting punctuation.

2. **High Success Rate** : The bypass technique, discovered by Aman Priyanshu from Robust Intelligence, dramatically increased the success rate of prompt injections from under 3% to nearly 100%.

3. **Implications for AI Security** : This flaw highlights significant challenges in securing AI models against simple yet effective manipulations, raising concerns about the reliability of current AI safety measures.