An Advanced Detection Framework for Embedded System Vulnerabilities
Bibliographic record
Abstract
Embedded systems serve as the foundation for modern computing in industrial, IoT, and defense applications. However, their increased adoption exposes them to security threats across multiple levels, from application software to operating systems and hardware. Traditional security mechanisms often focus on a single layer, missing cross-layer vulnerabilities that can be exploited by sophisticated attacks. This paper introduces a unified multi-layer vulnerability detection framework that integrates software, operating system, and hardware-level security analysis into a single LLAMA3-based deep learning model. The framework leverages a combined dataset consisting of source code vulnerabilities (C programming), Linux Kernel exploits (system calls), and Field-Programmable Gate Array (FPGA) hardware security risks in Hardware Description Languages (HDLs) such as Verilog and VHSIC Hardware Description Language (VHDL) and bitstream analysis. By merging these diverse vulnerability types into a single learning model, the framework is capable of detecting security threats across the entire embedded system stack. Applying static and dynamic analysis techniques across multiple layers, the proposed LLAMA3-based model achieves state-of-the-art detection accuracy across embedded system security domains. Experimental results demonstrate that the integrated framework outperforms existing layer-specific models, achieving 99.30% accuracy for software vulnerabilities, 99.16% accuracy for OS-level exploits, and 95.6% accuracy for hardware security threats.
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.
How this classification was reachedexpand
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".