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.
Reinhardt, Ali Saidi, Arkaprava Basu, Joel Hestness, Derek R
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
CHIA is an open-source framework for agentic AI-driven hardware/software co-design using CHIA loops as directed cyclic graphs, a tool library, and features for reliable experimentation, shown via five case studies.
Proposes Distributed Persistence Domain and Persistent CXL Switch to enable low-latency persistence operations at CXL switch level while maintaining crash consistency in disaggregated memory.
Eidola is a gem5 extension that emulates cycle-level peer-to-peer GPU writes via real-application timing profiles to simulate traffic and synchronization in multi-GPU AI systems.
KingsGuard adds hardware data-flow tracking and checks to TEE enclaves to prevent sensitive data leakage from vulnerabilities while supporting intentional declassification.
GreenMalloc applies NSGA-II with a rand_malloc proxy to discover allocator configurations that reduce average heap usage by up to 4.1% across workloads when evaluated in gem5, with no runtime penalty and a 0.25% efficiency gain.
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.