All articles
Share

Identifying Malicious Intent in Security Policy Violations

Human Decision Risk
February 10, 2026
Humanix
Title
SHARE
SHARE
SHARE

What is feature engineering

In practice, feature engineering is both science and a bit of witchcraft. It often involves both iteration and experimentation to uncover hidden patterns and relationships within the data. For instance, a data scientist might transform raw sales data into features such as average purchase value, purchase frequency, or customer lifetime value, which can significantly boost the performance of a churn prediction model. By thoughtfully engineering features, practitioners can provide machine learning models with the most informative inputs, ultimately leading to better accuracy and more robust predictions.

What’s more?

  • Incorporate more and more data sources
  • Feature engineering platform

What is data engineering

As we mentioned above, feature engineering is certainly a subset of data engineering. It involves the ingestion of data from a source, applying a series of transformations, and making the final result available to be queried by a model for training purposes. You can construct feature engineering pipelines to resemble data engineering pipelines, having schedules, specific source and sink destinations, and availability for querying. However, this configuration would only really apply once you have surpassed the experimentation stage and determined a need for a consistent flow of new feature data.

What is feature engineering

Image description

1. Functions

Functionally, there is nothing to differentiate data vs features - data points (link). Where feature engineering and data engineering really differ is in the objectives and motivations for constructing the pipelines. In general, data engineering serves a broader, more unified purpose than feature engineering. Data engineering platforms are constructed to be flexible and universal, ingesting various types and sources of data into a unified storage location where any number of transformations and use cases can be applied. The intent of a well constructed fact table or gold layer in a data lake is to provide a single source of truth that answers many different questions, produces many reports, and can be consumed by many downstream customers.

2. Practise

And in practice, an organization’s data engineering team will be responsible for the curation and maintenance of all data pipelines, not just those that relate to machine learning. These pipelines may power BI dashboards used by C-Suite, auditing reports that feed payroll, or event logs that show a user’s history of actions within the application.

Feature engineering, on the other hand, serves a specific purpose, finding the tailored inputs and columns that will generate the best predictive results for a machine learning model. Data scientists and machine learning engineers are not tasked with developing a universal data model that will ingest all data points throughout an organization, they just need to select, curate, and clean the data needed to power their models.

3. Machine learning

Now, as machine learning teams grow and begin to incorporate more and more data sources into their models, their feature engineering platform may start to resemble a larger data engineering platform in the tools and methodologies they employ. But, the intent is not to establish flexible data models that can be used throughout the organization - it is simply to power their machine learning models.

Every day, employees bypass security controls. Most share passwords to meet deadlines, skip approval processes during emergencies, or disable safeguards that slow critical work. But hidden among these operational workarounds, attackers exploit the same gaps. One violation helps the business, the other enables breach. Your detection systems must distinguish between them.

The Dangerous Ambiguity of Policy Violations

Security teams face an uncomfortable truth: strict compliance would bring business operations to a halt. Employees develop workarounds because policies often conflict with operational reality. These informal processes become organizational knowledge. Everyone knows which approvals can wait, which verifications to skip during crunch time, which shared accounts exist despite policy.

Attackers study these patterns. Through reconnaissance and social engineering, they discover which controls employees routinely bypass. They craft attacks that mimic legitimate workarounds, knowing security teams hesitate to flag familiar violations.

The challenge isn't detecting policy violations. It’s determining intent when the same action could indicate helpfulness or harm.

Effective detection requires behavioral context that distinguishes operational necessity from malicious exploitation.

Patterns That Reveal Malicious Intent

Malicious policy violations create distinct patterns when aggregated. Violation progression provides the clearest signal. Attackers test boundaries incrementally, starting with minor bypasses before major exploitation. Employees seeking efficiency maintain consistent workaround patterns while attackers escalate systematically.

Timing and frequency suggest intent. Operational workarounds cluster around predictable business events such as quarterly reports, system migrations, audit preparations. Malicious violations occur opportunistically, often outside normal patterns, targeting moments of reduced oversight. Weekend access bypasses by accounts normally active only weekdays support investigation.

Communication context provides additional clarity. Policy violations following suspicious emails, unusual phone calls, or help desk interactions suggest social engineering. When employees suddenly use workarounds they've never needed before manipulation likely occurred.

Outcome correlation separates legitimate from malicious activity. Operational workarounds resolve tasks then cease. Malicious violations enable further compromise such as data exfiltration following access bypass, privilege escalation after authentication workaround.

Each violation represents a stepping stone rather than an endpoint.

Building Contextual Detection Capabilities

Use voice analysis to differentiate legitimate calls from those using persuasion techniques. Emergency access procedures, approval delegation systems, and shared service accounts all represent both operational realities and attack opportunities.

Use voice-based analysis methods. Recognizing normal patterns of conversation can help differentiate legitimate calls from those that use persuasion and deception techniques.

Deploy UEBA to establish violation baselines. Understanding normal workaround patterns by department and role enables detection of anomalous bypasses. When finance regularly shares credentials during month-end but engineering suddenly starts, context suggests investigation.

Correlate violations with downstream activity. Link policy bypasses with subsequent actions: data access, system changes, authentication attempts. This correlation transforms isolated violations into visible attack chains.

Strategic insight: Use detection findings to improve policy design. Frequently bypassed controls indicate friction requiring remediation. Reduce legitimate workarounds and malicious actors lose camouflage.

Policy violations will continue because perfect compliance remains operationally impossible. Organizations that analyze behavioral context can detect malicious exploitation while understanding which policies need renovation.

Recommended Actions

Immediate steps: Identify your top five most-bypassed security controls. Monitor these specifically for unusual patterns or users.

Implementation resources:

  • NIST Cybersecurity Framework's "Anomalies and Events" detection guidelines
  • MITRE ATT&CK framework's privilege escalation techniques
  • Carnegie Mellon's insider threat detection patterns
  • UEBA platforms for behavioral baseline establishment
  • Industry-specific compliance violation analysis guides

Enter your work email and we'll reach out to schedule the demo

Oops! Something went wrong while submitting the form.