55AA Security Lab

We work on full lifecycle system security, cybersecurity LLMs, AI agents, and benchmarks, meta-science and translate related research into practical applications.

Contact us

News

Student Research Projects

100 Hypervisor Security SoK

Full lifecycle system securityEngineeringMaster's capstoneHiring for 2026-2027

This master's capstone project studies hypervisors from three connected angles: hypervisors used as security mechanisms, the security of hypervisors themselves, and the risks introduced by insecure hypervisor designs or deployments. The project aims to build a systematic knowledge base that clarifies threat models, isolation assumptions, vulnerability classes, measurement methods, and open research problems across commodity, cloud, embedded, and security-oriented virtualization systems.

103 Building a Recursive Self-Improvement Workflow for POC Generation

Cybersecurity LLMs, AI agents, and benchmarksEngineeringMaster's capstoneHiring for 2026-2027

This master's engineering project builds a recursive self-improvement workflow for proof-of-concept generation. Based on Magma, ground-truth bug benchmarks, and a workflow DSL, the project designs and evaluates an agentic pipeline that can generate POCs, execute them against known vulnerable targets, diagnose failures, revise its workflow, and accumulate reusable strategies over time. The goal is to turn benchmark-backed POC generation into a measurable engineering loop for studying how execution feedback can continuously improve security tools.

203 Defense in Depth for Sandboxes

Full lifecycle system securityResearchPhD projectHiring for 2026-2027

This PhD research project studies defense-in-depth architectures for process-based and VM-based sandboxes. The project investigates how sandbox escapes and policy bypasses emerge across system-call interfaces, shared resources, runtime services, and hardware boundaries, then develops layered defenses that combine behavioral monitoring at security-relevant interfaces, exploit prevention, and compartmentalization. It further explores techniques such as pattern matching, hardware-assisted enforcement, and hardware-software co-design to make sandboxed execution more resilient against both known attack patterns and previously unseen exploitation strategies.

Test different security governance approaches in synthetic scenarios

Cybersecurity from fundamentals to mastery — consolidating existing knowledge, collecting security intelligence, and improving signal-to-noise, for humans and AI

100 Hypervisor Security SoK

Full lifecycle system securityEngineeringMaster's capstoneHiring for 2026-2027

This master's capstone project studies hypervisors from three connected angles: hypervisors used as security mechanisms, the security of hypervisors themselves, and the risks introduced by insecure hypervisor designs or deployments. The project aims to build a systematic knowledge base that clarifies threat models, isolation assumptions, vulnerability classes, measurement methods, and open research problems across commodity, cloud, embedded, and security-oriented virtualization systems.

103 Building a Recursive Self-Improvement Workflow for POC Generation

Cybersecurity LLMs, AI agents, and benchmarksEngineeringMaster's capstoneHiring for 2026-2027

This master's engineering project builds a recursive self-improvement workflow for proof-of-concept generation. Based on Magma, ground-truth bug benchmarks, and a workflow DSL, the project designs and evaluates an agentic pipeline that can generate POCs, execute them against known vulnerable targets, diagnose failures, revise its workflow, and accumulate reusable strategies over time. The goal is to turn benchmark-backed POC generation into a measurable engineering loop for studying how execution feedback can continuously improve security tools.

203 Defense in Depth for Sandboxes

Full lifecycle system securityResearchPhD projectHiring for 2026-2027

This PhD research project studies defense-in-depth architectures for process-based and VM-based sandboxes. The project investigates how sandbox escapes and policy bypasses emerge across system-call interfaces, shared resources, runtime services, and hardware boundaries, then develops layered defenses that combine behavioral monitoring at security-relevant interfaces, exploit prevention, and compartmentalization. It further explores techniques such as pattern matching, hardware-assisted enforcement, and hardware-software co-design to make sandboxed execution more resilient against both known attack patterns and previously unseen exploitation strategies.

No published courses yet.

2026-09-19 Research Management Version 0.1

Research Project Process Management at 55AA Lab

The 55AA Lab research project management process covers 0-1 validation, cognitive alignment, investigation and validation, paper submission, outcome strengthening, and reflection and improvement.

We welcome different forms of sponsorship, including gifts, research grants, equipment donations, cloud and infrastructure credits, and support for student projects and open-source development. Sponsorship helps improve student support, build durable security research infrastructure, and keep our work and artifacts open to the community. Sponsors receive transparent updates on how funds are used and, with their permission, are acknowledged by name on our homepage.

Sponsors

No sponsors yet.