Recent Research Signals

Found 1 result

Filtering papers...

Paper	Possible Impact	Features	Possible Business Area
The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search Cryptography and Security	Breaks AI safety by tricking it with hidden questions.	IBM Code 2 Countries	Natural Language Processing (76%)	Score: 4 4 days ago