@llm_sec : * People ask LLMs to write code * LLMs recommend imports that don't actually exist * Attackers work out what these imports' names are, and create & upload them with malicious payloads * People using LLM-written code then auto-add malware themselves vulcan.io/blog/ai-halluc… • TwiCopy

LLM Security

@llm_sec

+ Follow

Research, papers, jobs, and news on large language model security.

Got something relevant? DM / tag @llm_sec

ID: 1649129451815596032

linkhttp://llmsec.net calendar_today20-04-2023 19:14:47

825 Tweet

9,9K Followers

296 Following

LLM Security

@llm_sec

2 years ago

* People ask LLMs to write code * LLMs recommend imports that don't actually exist * Attackers work out what these imports' names are, and create & upload them with malicious payloads * People using LLM-written code then auto-add malware themselves vulcan.io/blog/ai-halluc…

thumb_up_off_alt7,7K

chat_bubble_outline83

repeat2,2K

shareShare