LM-Fix: Lightweight Bit-Flip Detection and Rapid Recovery Framework for Language Models
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Bit-flip attacks threaten the reliability and security of Language Models (LMs) by altering internal parameters and compromising output integrity. Recent studies show that flipping only a few bits in model parameters can bypass safety mechanisms and jailbreak the model. Existing detection approaches for DNNs and CNNs are not suitable for LMs, as the massive number of parameters significantly increases timing and memory overhead for software-based methods and chip area overhead for hardware-based methods. In this work, we present LM-Fix, a lightweight LM-driven detection and recovery framework that leverages the model's own capabilities to identify and recover faults. Our method detects bit-flips by generating a single output token from a predefined test vector and auditing the output tensor of a target layer against stored reference data. The same mechanism enables rapid recovery without reloading the entire model. Experiments across various models show that LM-Fix detects more than 94% of single-bit flips and nearly 100% of multi-bit flips, with very low computational overhead <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(\approx 1 \%- 7.7 {\%}$</tex> at TVL <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$=200$</tex> across models). Recovery achieves more than <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$100 \times$</tex> speedup compared to full-model reload, which is critical in edge devices. LM-Fix can handle bit-flips affecting any part of the model's computation, including memory, cache, and arithmetic operations. Evaluation against recent LM-specific bit-flip attacks confirms its robustness and practical value for real-world deployment.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.005 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it