THESIS: What security risks are introduced by Generative AI in Software development?

AbstractManaging third-party dependencies is critical for software security, yet existing tools such as Dependabot treat all version updates and reported vulnerabilities as equally urgent. This lack of prioritization leads to alert fatigue and wasted developer effort. This thesis explores how AI can make dependency risk management more contextual and...

High level descriptionWith the rapid advancement of artificial intelligence, AI-driven communication tools such as chatbots, virtual assistants, and deepfake voice generators, are becoming increasingly indistinguishable from human interaction. While these technologies offer numerous benefits, they also pose significant risks by blurring the line between...

High level descriptionEffort and time estimation remain among the most challenging aspects of software engineering. Despite decades of research, human estimates are still often uncertain and inconsistent.With the rise of advanced AI assistants and code-generating tools such as GitHub Copilot, ChatGPT, Amazon CodeWhisperer, and similar systems, new...

High level descriptionWith the rising popularity of AI agents, Anthropic has developed a new protocol for LLM models to communicate with tools. The Model Context Protocol (MCP) is slowly becoming a standard for developing tools for LLMs and LLM Agents. In MCP there are no security or authentication methods, so exposing tools towards end users can be harmful...

High level descriptionThis project examines the application of artificial intelligence in translating change requests into automated test cases by referencing software interface descriptions, aiming to enhance verification coverage and overall software quality.Who are we looking for?Bachelor/Master of Science in Computer Science/EngineeringProject...

BackgroundIn today's digital landscape, services and offerings are increasingly composed of multiple interconnected applications and systems. This complexity makes it difficult to trace which services are tied to a specific customer identifier and to detect issues such as failed orders or recurring system errors.Traditionally, support and operations teams...

High level descriptionAI agents in Customer Success can streamline documentation by automatically capturing key insights from customer interactions and updating knowledge bases with accurate, easy-to-find content. They can analyze large sets of customer data to identify trends, summarize findings, and prepare structured updates. For monthly reporting, AI...

High level descriptionComponent reusability is essential for maintaining consistency and efficiency in modern software development organizations. Traditional npm packages (either public or private) have long been the standard approach for sharing code across projects, while shadcn's registry system represents a newer paradigm that focuses on code ownership...

High level descriptionThis project explores the application of artificial intelligence in software engineering to accelerate the formulation of change requests from initial business needs and enhance the precision of early-stage estimates.Who are we looking for?Bachelor/Master of Science in Computer Science/EngineeringProject descriptionUtilizing prompt...

High level descriptionModern data engineering faces unprecedented challenges as organizations increasingly deploy IoT devices and edge computing infrastructure that generate massive volumes of distributed data.Traditional centralized data processing approaches struggle with the latency, bandwidth, and reliability constraints inherent in edge-to-cloud data...