3D Guard-Layer: An Integrated Agentic AI Safety System for Edge Artificial Intelligence
By Eren Kurshan (Princeton University), Yuan Xie (Hong Kong University), Paul Franzon (North Carolina State University)
Abstract
AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety mechanisms, security vulnerabilities and challenges have become increasingly prevalent in this domain, posing a significant barrier to the practical deployment and safety of AI systems. This paper proposes an agentic AI safety architecture that leverages 3D to integrate a dedicated safety layer. It introduces an adaptive AI safety infrastructure capable of dynamically learning and mitigating attacks against the AI system. The system leverages the inherent advantages of co-location with the edge computing hardware to continuously monitor, detect and proactively mitigate threats to the AI system. The integration of local processing and learning capabilities enhances resilience against emerging network-based attacks while simultaneously improving system reliability, modularity, and performance, all with minimal cost and 3D integration overhead.
To read the full article, click here
Related Chiplet
- Integrated voltage regulator (IVR) chiplet
- High-performance connectivity chiplets
- eFPGA Chiplet
- DPIQ Tx PICs
- IMDD Tx PICs
Related Technical Papers
- CHICO-Agent: An LLM Agent for the Cross-layer Optimization of 2.5D and 3D Chiplet-based Systems
- Generative Design of Liquid-Cooling Channels for Thermal Management of 2.5D and 3D Integrated Advanced Packaging
- System-Technology Co-Optimization for Dense Edge Architectures using 3D Integration and Non-Volatile Memory
- CarbonPATH: Carbon-aware pathfinding and architecture optimization for chiplet-based AI systems
Latest Technical Papers
- Chiplet-Based Techniques for Scalable and Memory-Aware Multiscalar Multiplication on Hardware Platforms
- A Time-Encoded Analog Photonic Interposer for Energy-Efficient Integration of Analog Vision Sensors and Analog Accelerators
- Self-Activated Direct Bonding with a Highly Polar Atomic-Layer-Deposited Film for 3D Integration
- FLINT: Efficiently Leveraging High Bandwidth Flash for Capacity-Scalable LLM Inference Acceleration
- Beacon: LLM Multi-Agent Driven Hardware Design Space Exploration for Heterogeneous Multi-Chiplet Deep Learning Accelerators