What if a Security Operations Center (SOC) could respond to a cyberattack in seconds, without waiting for a human analyst? That speed could be valuable, but a wrong decision could also disrupt critical services. How can an autonomous SOC know when it is safe to act, and when it should stop?
This master’s thesis is part of ‘Project Lights Out: can the lights go out in the SOC?’. You will explore how a SOC can detect, investigate and respond to cyberattacks with increasing autonomy. What can the system handle on its own, and when should a security professional step in? Your research helps uncover how a SOC can operate reliably and autonomously, and where human expertise remains essential.
As Security Operations Centers move towards greater autonomy, security decisions that were previously reviewed by human analysts may be made and executed by AI-driven systems. These decisions can have significant consequences, ranging from unnecessary account lockouts to the disruption of critical business services.
The ability of an autonomous agent to investigate an incident or recommend a response does not necessarily mean that its decisions are sufficiently reliable or safe to execute without human approval. Agents may rely on incomplete or misleading evidence, misjudge the consequences of an action, express unjustified confidence or be manipulated by adversarial inputs.
A key challenge in autonomous SOC operations is therefore determining when a decision is sufficiently supported by evidence, when additional verification is required and when human intervention is necessary.
While reasoning and automation capabilities are important, this master’s thesis focuses specifically on the mechanisms that make autonomous decisions safe enough to execute. These include verification procedures, uncertainty assessment, explainability, human oversight, fail-safe behaviour, rollback mechanisms and resistance to adversarial manipulation.
The Assignment
Design and evaluate a framework or prototype mechanism that assesses whether autonomous SOC decisions can be safely executed.
The solution should evaluate relevant evidence, uncertainty, potential impact and action-specific risks, and determine whether a proposed action should be allowed, subjected to additional verification, escalated to a human operator or rejected.
Validate the approach using representative SOC scenarios, including incomplete evidence, incorrect recommendations, high-impact response actions and adversarial inputs. Evaluate how effectively the proposed safeguards prevent unsafe actions, support justified autonomous execution and balance safety with operational efficiency.
The objective is not to develop a complete autonomous investigation agent, but to establish and validate the conditions and mechanisms under which autonomous SOC decisions can be trusted and safely executed.
About Info Support
Info Support specializes in custom software, data/AI solutions, management, and training and is active in the Finance, Industry, Agriculture, Food & Retail, Mobility & Public, and Healthcare sectors. We provide solid and innovative solutions for complex and critical software issues. Our headquarters are located in Veenendaal (NL) and Mechelen (BE). At present, approximately 500 employees are employed by Info Support.
Info Support’s working method is characterized by a number of core values: solidity, integrity, craftsmanship, and passion. These core values are intertwined in our work and the way we interact with each other.
To ensure that all employees are always up to date with the latest developments, Info Support has an in-house IT Academy that eagerly satisfies the hunger for more or different knowledge and skills.
B2 language proficiency in Dutch is required.























