A new backdoor technique called TSBH uses reverse tree search to create malicious chain-of-thought data and injects it in two stages to hijack LLM reasoning upon trigger activation.
It disregards the fundamental rights of individuals to be free from harm and violates the ethical standards of human interaction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor
A new backdoor technique called TSBH uses reverse tree search to create malicious chain-of-thought data and injects it in two stages to hijack LLM reasoning upon trigger activation.