← Back to all news
arXiv Computation and Language By Huakang Lin, Tiancheng Zheng, Mingxuan Sun, Tianhong Xu, Fan Zhang, Yunsi Fei, Ruyi Ding

Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips

Read the original on arXiv Computation and Language →

The paper introduces the Groundhog Bit-Flip Attack (GBFA), a novel denial-of-service attack targeting Mixture-of-Experts (MoE) large language models (LLMs). By flipping specific routing-layer bits that activate certain experts, GBFA can cause models to generate excessively long outputs—up to a 5912% increase in token usage—while largely preserving semantic content. The attack requires deactivating fewer than four experts on average across four real-world MoE-based LLMs, exposing a significant robustness vulnerability in these architectures.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

Related stories

arXiv Machine Learning
5d ago

Characterizing Recoverable Expert-Utilization Signatures in Fine-Tuned Mixture-of-Experts LLMs

The paper investigates a new security vulnerability in fine‑tuned Mixture‑of‑Experts large language models, termed structural memorization, where the model not only memorizes training data but also the internal routing pathways used during fine‑tuning. The authors demonstrate that these memorized expert pathways can be recovered from the model’s unconditional generation using only routing and output logits, even without access to the fine‑tuning data. They further show that this vulnerability is amplified in distributed deployments and that traditional membership inference metrics fail to detect it, proposing composite metrics that improve detection of memorized routing structures.

By Fei Wang, Baochun Li, Bo Li
llmsroboticsfine-tuning
More like this →