Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit Flips
cs.CL
Submitted: 2026-08-26
Updated: 2026-08-26
Comments: 9 pages, 3 figures; Accepted at EMNLP 2026
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- Mixtral of Experts
- MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs
- Steering MoE LLMs via Expert (De)Activation
- Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
- BDFA: A Blind Data Adversarial Bit-flip Attack on Deep Neural Networks
- SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization
- Uncovering In-DRAM RowHammer Protection Mechanisms: A New Methodology, Custom RowHammer Patterns, and Implications
- gpt-oss-120b & gpt-oss-20b Model Card
- Qwen3 Technical Report
- BadMoE: Backdooring Mixture-of-Experts LLMs via Optimizing Routing Triggers and Infecting Dormant Experts
- Breaking the Loop: Detecting and Mitigating Denial-of-Service Vulnerabilities in Large Language Models
- TrojViT: Trojan Insertion in Vision Transformers
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering