BitFlipScope: Scalable Fault Localization and Recovery for Bit-Flip Corruptions in LLMs

Computer Science > Distributed, Parallel, and Cluster Computing [Submitted on 18 Dec 2025 (v1), last revised 14 Apr 2026 (this version, v2)] BitFlipScope: Scalable Fault Localization and Recovery for Bit-Flip Corruptions in LLMs Muhammad Zeeshan Karamat, Sadman Saif, Christiana Chamon Garcia Large Language Models (LLMs) deployed in practical and safety-critical settings are increasingly susceptible to bit-flip faults caused by hardware degradation, cosmic radiation, or deliberate fault-injection attacks such as Rowhammer. These faults silently corrupt internal parameters and can lead to unpredictable or dangerous model behavior. Localizing these corruptions is essential: without identifying the affected region, it is impossible to diagnose the source of degradation, apply targeted corrective measures, or restore model functionality without resorting to costly fine-tuning or full retraining. This work introduces BitFlipScope, a scalable, software-based framework for identifying fault-affected regions within transformer architectures under two deployment scenarios. When a clean reference model is available, BitFlipScope performs differential analysis of outputs, hidden states, and internal activations for detecting anomalous behavior indicative of corruption to pinpoint or localize faults. When no reference model exists, it uses residual-path perturbation and loss-sensitivity profiling to infer the fault-impacted region directly from the corrupted model. In both settings, the framework not only enables effective fault diagnosis but also supports lightweight performance recovery without fine-tuning, offering a practical path to restoring corrupted models. Together, these capabilities make BitFlipScope an important step toward trustworthy, fault-resilient LLM deployment in hardware-prone and adversarial environments. Comments: Accepted at the IEEE International Symposium on Hardware Oriented Security and Trust (HOST) 2026 Subjects: Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR); Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2512.22174 [cs.DC]   (or arXiv:2512.22174v2 [cs.DC] for this version)   https://doi.org/10.48550/arXiv.2512.22174 Focus to learn more Submission history From: Muhammad Zeeshan Karamat [view email] [v1] Thu, 18 Dec 2025 20:35:29 UTC (532 KB) [v2] Tue, 14 Apr 2026 19:51:27 UTC (573 KB) Access Paper: HTML (experimental) view license Current browse context: cs.DC < prev   |   next > new | recent | 2025-12 Change to browse by: cs cs.AI cs.AR cs.CR cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)