SAM: Foreseeing Inference-Time False Data Injection Attacks on ML-enabled Medical Devices
Bibliographic record
Abstract
The increasing use of machine learning (ML) in medical systems necessitates robust security measures to mitigate potential threats. Current research often overlooks the risk of adversaries injecting false inputs through peripheral devices at inference time, leading to mispredictions in patients' conditions. These risks are hard to foresee and mitigate during the design phase since the system is assembled by end users at the time of use. To address this gap, we introduce SAM, a technique that enables security analysts to perform System Theoretic Process Analysis for Security (STPA-Sec) on ML-enabled medical devices during the design phase. SAM models the medical system as a control structure, with the ML engine as the controller and peripheral devices as potential points for false data injection. It interfaces with state-of-the-art vulnerability databases and Large Language Models (LLMs) to automate the discovery of vulnerabilities and generate a list of possible attack paths. We demonstrate the usefulness of SAM through case studies on two FDA-cleared medical devices: a blood glucose management system and a bone mineral density measurement software. SAM allows security analysts to expedite the security assessment of ML-enabled medical devices at the design phase. This proactive approach mitigates potential patient harm and reduces costs associated with post-deployment security measures.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.034 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.005 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".