From the 1 of 12 linked papers with an AI index.
12 papers
Emulated Integrity Replica: Enabling Self-Healing on FPGA SoCs via Hierarchical Twins
Arsalan Ali Malik, Ali Suvizi, Guru Venkataramani +1
The paper introduces Emulated Integrity Replica (EIR), a hierarchical digital‑twin framework for FPGA SoCs that uses idle processor cycles to run lightweight behavioral and detaile…
No TPU Left Behind: Retrofitting Side-Channel Protection into Edge TPUs
Ashley Kurian, Anuj Dubey, Modini Ayyagari +1
Side-channel attacks can recover neural network parameters from physical signals, even on commercial edge accelerators. Existing defenses require changes to hardware, instruction s…
FeatureBleed: Inferring Private Enriched Attributes From Sparsity-Optimized AI Accelerators
Darsh Asher, Farshad Dizani, Joshua Kalyanapu +3
Backend enrichment is now widely deployed in sensitive domains such as product recommendation pipelines, healthcare, and finance, where models are trained on confidential data and…
Preemption-Enhanced Benchmark Suite for FPGAs
Arsalan Ali Malik, John Buchanan, Aydin Aysu
Field-Programmable Gate Arrays (FPGAs) have become essential in cloud computing due to their reconfigurability, energy efficiency, and ability to accelerate domain-specific workloa…
CRAFT: Characterizing and Root-Causing Fault Injection Threats at Pre-Silicon
Arsalan Ali Malik, Harshvadan Mihir, Aydin Aysu
Fault injection attacks (FIA) pose significant security threats to embedded systems as they exploit weaknesses across multiple layers, including system software, instruction set ar…
GATEBLEED: Exploiting On-Core Accelerator Power Gating for High Performance & Stealthy Attacks on AI
Joshua Kalyanapu, Farshad Dizani, Darsh Asher +4
As power consumption from AI training and inference continues to increase, AI accelerators are being integrated directly into the CPU. Intel's Advanced Matrix Extensions (AMX) is o…