A handful of weight-bit flips (as few as 12) can bias LLM outputs toward a target entity or stance, with limited effect on non-target tasks and output distributions.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Decision-Level Hijacking: Injecting Cognitive Bias into Large Language Models via Bit-Flip Attacks
A handful of weight-bit flips (as few as 12) can bias LLM outputs toward a target entity or stance, with limited effect on non-target tasks and output distributions.