activity
20242026
most citedAuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors

2 citations · 3 across the 4 of their papers we have counts for

collaborators
Showing 2024Show all

1 paper · 1 filter

cs.CR2024★ 1 cited

Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs

Sara Price, Arjun Panickssery, Sam Bowman +1

Backdoors are hidden behaviors that are only triggered once an AI system has been deployed. Bad actors looking to create successful backdoors must design them to avoid activation d…