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
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
AcOrch achieves 2.31x average speedup over MindSporeGL for sampling-based GNN training on Ascend 910B by mapping tasks to AIC/AIV units and CPU cores with two-level pipelining.
NeutronSparse coordinates heterogeneous NPU engines with sparsity-aware partitioning and locality-aware tile reuse to accelerate SpMM, reporting 1.26x-7.78x gains over NPU baselines and 1.03x-3.07x over GPU libraries.
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.
-
AcOrch: Accelerating Sampling-based GNN Training under CPU-NPU Heterogeneous Environments
AcOrch achieves 2.31x average speedup over MindSporeGL for sampling-based GNN training on Ascend 910B by mapping tasks to AIC/AIV units and CPU cores with two-level pipelining.
-
NeutronSparse: Coordinating Heterogeneous Engines for Sparse Matrix Multiplication on NPUs
NeutronSparse coordinates heterogeneous NPU engines with sparsity-aware partitioning and locality-aware tile reuse to accelerate SpMM, reporting 1.26x-7.78x gains over NPU baselines and 1.03x-3.07x over GPU libraries.
-
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.