# SiliconShield

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [Debjyoti Mandal](https://cerebralvalley.ai/u/debman)
- **GitHub:** https://github.com/debjyotikm/siliconshield/
- **Demo video:** https://www.youtube.com/watch?v=mLnjIjzzL6U
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1074

SiliconShield brings Meta Muse into the semiconductor industry to help engineers investigate failures before chip fabrication. I built SiliconShield from my experience in semiconductor design and verification. Using Muse Spark 1.3 and Muse Wonder as research and coding collaborators, I constructed datasets, ran GPU training experiments, investigated learning failures, and built the assessment and training infrastructure. The investigation workflow uses locally served Muse Glimmer with two specialist skills: Contract-1 for register protection, privilege checks, locks, and address qualification, and Contract-2 for focused FIFO, counter, and arbitration behaviour. Muse Glimmer examines the RTL under the supplied assumptions, while Muse Spark 1.3 interprets the output evidence into a finding with supporting logic, disagreements, and open questions.

As an additional research contribution, I fine-tuned Muse Glimmer 30B to perform the three-way decision task directly: satisfies the requirement, violates the requirement, or insufficient context. One published LoRA adapter covers both domains, achieving 97.22% accuracy on local-guard development examples.

The submission includes reusable Contract skills, an investigation infrastructure, a working demo, a published fine-tuned Muse Glimmer adapter and scientific documentation. Together, these provide a practical foundation for AI-assisted hardware investigation, with consequential findings taken forward to engineering review, simulation, or formal verification.

## More from Meta Global AI Developer Hackathon

- [Manual for Anything](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1071)
- [Creative Director Agent](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1072)
- [Scholee](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1073)
- [Talla](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1075)
- [Opportunity-Compass](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1076)
- [SafePath AI](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1077)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/1074. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt