Title: Autonomous LLM Silicon Red-Teaming & Hardware Exploitation Challenge
Part of the GREAT Workshop @ DAC 2026 — Long Beach, CA | July 26, 2026
As Large Language Models (LLMs) and multi-agent frameworks advance from simple coding assistants to fully autonomous engineering agents, a critical security boundary is crossed: Can AI break silicon security before it even hits the fab?
This attack-only challenge focuses on utilizing autonomous LLM agentic flows to exploit, reverse-engineer, and compromise chip designs across the entire hardware lifecycle — from high-level RTL down to the physical gate-level netlist.
Participants will act as the red-team, developing and deploying agentic systems that interface with hardware design tools and simulators to autonomously attack silicon targets:
- Identifying security flaws in hardware designs
- Injecting functional Hardware Trojans
- Defeating netlist obfuscation schemes
Finalists will be required to showcase a live operational dashboard during the finals that visualizes the LLM’s real-time reasoning, tool-use calls, and exploit-success telemetry.
The competition is open to researchers and engineers from both academia and industry, bridging the gap between chip designers and LLM agentic flow developers.
Register Here: https://forms.gle/uczGvoiWLUHwv1X56
Workshop Details: https://63dac.conference-program.com/presentation/?id=WKSHP104&sess=sess198
Timeline
- May 23 — Challenge Launch
- June 29 — 2-Page Abstract & Qualification Submission Deadline
- July 8 — Finalists Notification
- July 9 — Phase 2 / Live Dashboard Environment Release
- July 15 — Phase 2 Final Code & Dashboard Freeze
- July 26 — Challenge Finals @ DAC 2026, Long Beach, CA
Submission Guidelines
Phase 1 — Qualification (due June 15)
Submit a 2-page abstract describing:
- Your agentic system architecture (LLM backbone, tool-use framework, orchestration approach)
- Attack strategies and target vulnerability classes
- Preliminary results or proof-of-concept demonstrations
- Team composition and relevant background
Submission Link: https://forms.gle/uczGvoiWLUHwv1X56
Phase 2 — Finals (code freeze July 15)
Finalists will receive the Phase 2 environment on June 25. Final submissions include:
- Full agentic system codebase
- Evaluation results on provided benchmark targets
- Live operational dashboard (required for on-site demonstration)
Live Dashboard Requirement: Finalists must present a real-time dashboard at DAC 2026 that visualizes the LLM’s reasoning trace, tool invocations, and exploit-success telemetry as the agent runs.
Grading Criteria
- Attack success rate — How reliably does the agent exploit or compromise target designs?
- Autonomy — Minimal human intervention; the agent drives the full attack pipeline
- Generality — Performance across multiple target designs and attack categories
- Dashboard quality — Clarity and informativeness of the live operational dashboard
- Innovation — Novel agentic architectures, prompting strategies, or tool integrations
Organizers
JV Rajendran, Texas A&M University
Stephen Muttathil, Texas A&M University
Part of the GREAT Workshop @ DAC 2026, co-located with the AHA! Challenge and the Hardware IP Redaction Challenge.