Adversarial Threats and Defense Mechanisms in Machine Learning-Based SQL Injection Detection: A Security Analysis
Bibliographic record
Abstract
QL injection (SQLi) is a type of cyber attack where malicious code is inserted into a SQL query through an input field in a web application. This exploit targets vulnerabilities in the application’s software that allows unsanitized or improperly validated user inputs to be executed as part of a database query. As a result, an attacker can gain unauthorized access to the database, retrieve, modify, or delete data, bypass authentication mechanisms, or perform other malicious actions. In Artificial Intelligence (AI), Machine Learning (ML) techniques are used to automatically detect SQL injections before they reach the web application. However, machine learning techniques are themselves vulnerable to attacks. We conduct an in-depth security analysis of a highly realistic threat model, experimentally demonstrating the effectiveness of poisoning and evasion attacks on a machine learning-based SQL injection detector. We then propose a defense mechanism tailored to the ML algorithm, and designed to protect the system against such attacks. This research highlights the consequences of inadequate management of AI technology in this field.
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 | 0.001 | 0.003 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 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".