3 citations · 3 across the 3 of their papers we have counts for
4 papers · 1 filter
TranScope: What the Software Hides About LLM Training Data, the Hardware Reveals at Scale, and Accelerators Magnify
Joshua Kalyanapu, Darsh Asher, Kaushal Mhapsekar +5
Membership is the root privacy primitive in machine learning: to date, no hardware-based out-of-distribution detection on black-box models has been demonstrated against constant-ti…
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…
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…
THOR: A Non-Speculative Value Dependent Timing Side Channel Attack Exploiting Intel AMX
Farshad Dizani, Azam Ghanbari, Joshua Kalyanapu +2
The rise of on-chip accelerators signifies a major shift in computing, driven by the growing demands of artificial intelligence (AI) and specialized applications. These accelerator…