A Model-Independent Trojan Attack on Deep Learning-Based FDIA Detection in Smart Grid Protection Systems
Bibliographic record
Abstract
Deep learning (DL) models have been proven to be highly effective in detecting false data injection attacks (FDIAs) in smart grids relying only on the measurements of the secured component. However, the vulnerability of these DL models to Trojan attacks poses significant security risks. This article introduces a model-independent Trojan attack (MITA) targeting DL models used for FDIA detection in critical smart grid components, such as transformer differential relays (TDRs). MITA injects a carefully crafted trigger signal into the TDR’s measurements, which evades detection by DL-based FDIA detection methods, causing FDIAs to be misclassified as faults. This leads to unnecessary tripping of the attacked TDR, potentially compromising grid reliability. Key features of MITA include model independence, enabling it to target diverse DL architectures without retraining, high success rates exceeding 99%, and stealthiness. The attack is validated against multiple DL models trained to detect FDIAs on TDRs using FDIA and fault scenarios generated in a realistic OPAL-RT environment. Our results show that MITA maintains the original model’s performance in the absence of the trigger while significantly misclassifying FDIAs as faults when the trigger is present. These results highlight the threat Trojan attacks can cause on industrial smart grid systems.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".