pith. sign in

Defending pre-trained language models as few-shot learners against backdoor attacks,

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CR 2

years

2025 2

representative citing papers

CacheTrap: Unveiling a Stealthier Gray-Box Trojan against LLMs

cs.CR · 2025-11-27 · conditional · novelty 8.0

CacheTrap achieves 100% targeted attack success on five open-source LLMs by using an efficient search to locate and flip a single bit in the KV cache as a transient trigger, while preserving normal accuracy without the trigger.

citing papers explorer

Showing 2 of 2 citing papers.