Open and completed research requests

Modern LLM coding assistants have evolved into tool-using agents that can read repositories, execute commands, modify infrastructure, and trigger external side effects, expanding the attack surface far beyond classic prompt misuse. This project will produce a deep technical survey that systematizes prompt-injection and related agentic risks across runtime execution and offline codebase design, with a focus on coding, CI/CD, MCP, RAG, and plugin ecosystems. The survey will pair threat taxonomy with defense taxonomy, clearly separating prevention, detection, containment, observability, and recovery controls, and distinguishing model-level mitigations from mandatory architectural controls. It will deliver practical secure workflows, configuration patterns, red-team suites, and a maturity model for teams moving from basic assistants to production-grade semi-autonomous engineering agents. The expected impact is a concrete, implementation-oriented reference that helps organizations deploy AI-assisted development safely without relying on prompt-only security assumptions.

Decision-makers in engineering, policy, economics, and operations often face trade-offs among conflicting objectives, yet method selection remains fragmented across disciplines. This project will produce a structured survey of mathematical methods that support multi-objective decisions, comparing their assumptions, computational behavior, and practical effectiveness. The approach combines a transparent literature-screening protocol with a common evaluation framework spanning solution quality, interpretability, robustness, and scalability. The expected impact is a decision-oriented reference that helps researchers and practitioners choose appropriate methods for specific problem settings and constraints.

LLM-assisted “vibe coding” accelerates software delivery but introduces new attack surfaces beyond traditional secure SDLC risks. This project will build a practical threat model focused on agentic and copilot-style coding workflows, including prompt injection, context poisoning, supply-chain abuse, and secret leakage. We will evaluate mitigation layers spanning prompt hygiene, permissioning, provenance controls, and CI policy gates. The expected impact is a reproducible security playbook and benchmark that organizations can apply to reduce incident likelihood without losing developer productivity.