Metraipolis › archive › dc_47df82ceb76c
JITterFlip: Uncovering Fault Attack Surfaces in JIT-Compiled LLM Serving — arXiv:2608.29745
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29745
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:25:41.504Z
- SHA-256 of the archived text
0c65064fe061059f095450fa1d2dba0f1c3f968712d11abd6ed1b7f0bda6ca28- Stable URL of this page
https://metraipolis.com/documento/dc_47df82ceb76c
How to cite
JITterFlip: Uncovering Fault Attack Surfaces in JIT-Compiled LLM Serving — arXiv:2608.29745 — arXiv (en), https://arxiv.org/abs/2608.29745 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_47df82ceb76c (Metraipolis archive dc_47df82ceb76c, sha256 0c65064fe061059f095450fa1d2dba0f1c3f968712d11abd6ed1b7f0bda6ca28)
BibTeX
@misc{dc47df82ceb76c,
title = {JITterFlip: Uncovering Fault Attack Surfaces in JIT-Compiled LLM Serving — arXiv:2608.29745},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29745},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_47df82ceb76c; sha256 0c65064fe061059f095450fa1d2dba0f1c3f968712d11abd6ed1b7f0bda6ca28},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29745. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
LLMs are widely deployed through cloud-hosted inference services, where Just-in-Time (JIT) compilation is used to reduce recurring framework and GPU-launch overhead. JIT serving introduces a host-side control plane that selects compiled artifacts and orchestrates their execution on the GPU. Meanwhile, the shared cloud setting has motivated a growing body of bit-flip attacks (BFAs) against LLM/DNN inference. Most existing BFAs target model parameters or weights and require model-specific knowledge. A smaller body of work reduces this dependency by faulting executable code, yet still corrupts code that directly implements model computation, limiting their attack effect to inference depletion. We present JITterFlip, the first BFA targeting the host-side JIT serving control plane of GPU-based LLM inference. By faulting CPU-resident serving decisions rather than model computation, JITterFlip enables both gibberish output generation and a correct-output sponge attack. To identify exploitable targets in a large JIT compiler stack, JITterFlip develops a decision-guided fault-vulnerable code analysis. Across four text and multimodal LLM workloads, the identified vulnerable code faults exhibit cross-model transferability, produce gibberish outputs with PPL ratios of $15.45\times$ to $2.48{\times}10^{6}\times$, and demonstrate correct-output sponge attacks with latency amplification of $2.03\times$ to $181.90\times$. JITterFlip also bypasses recent BFA defenses for LLMs while retaining both attack effects. Last, we demonstrate end-to-end Rowhammer attacks across four LLMs: a single bit flip in CPU-resident branch code propagates across the CPU-GPU boundary to disrupt GPU-executed inference without direct access to GPU memory, reaching up to $7.23{\times}10^{6}\times$ PPL amplification or $124.97\times$ latency amplification while preserving the exact generated output.
Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CR).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2608.29745 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T08:10:59.871Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).