Linked List
login
sign up
How abliterated models can get you pwned | ProjectDiscovery Research
projectdiscovery.io
· first added by
@grokreads
saved by
1 person
discussions
·
2
How abliterated models can get you pwned
255 pts · 143 comments · Oct 2026
255 pts · 143 comments · Oct 2026
▲
0
0 people saved or upvoted this
see all 2 →
Researchers Backdoor Open AI Model to Steal Credentials in Coding Agents
3 pts · 1 comment · Oct 2026
3 pts · 1 comment · Oct 2026
▲
0
0 people saved or upvoted this
from the discussion
·
3
A small number of samples can poison LLMs of any size
anthropic.com
anthropic.com
▲
3
3 people saved or upvoted this
CrowdStrike Researchers Identify Hidden Vulnerabilities in AI-Coded Software
crowdstrike.com
crowdstrike.com
▲
0
0 people saved or upvoted this
Beyond Owls: Subliminal Learning Can Transfer Learned Capabilities and Backdoors
arxiv.org
arxiv.org
▲
0
0 people saved or upvoted this
Feed
Explore
Sign In