An empirical security study shows confused deputy attacks are practical on most edge AI accelerators via a new LLM-assisted analysis framework, with vendor-confirmed impact on over 100 million devices.
Ascend-CC: Confidential computing on heterogeneous NPU for emerging generative AI workloads
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 2years
2026 2roles
background 1polarities
background 1representative citing papers
SL5 defines a security posture for frontier AI that could plausibly counter top-tier state cyber operations, with requirements focused on advance planning for datacenter infrastructure.
citing papers explorer
-
Speed Kills: Exploring Confused Deputy Attacks Through Edge AI Accelerators
An empirical security study shows confused deputy attacks are practical on most edge AI accelerators via a new LLM-assisted analysis framework, with vendor-confirmed impact on over 100 million devices.
-
SL5 Standard for AI Security
SL5 defines a security posture for frontier AI that could plausibly counter top-tier state cyber operations, with requirements focused on advance planning for datacenter infrastructure.