相关论文: SGX Switchless Calls Made Configless
This paper proposes a system, entitled Concealer that allows sharing time-varying spatial data (e.g., as produced by sensors) in encrypted form to an untrusted third-party service provider to provide location-based applications (involving…
In this paper, we consider a mixed-prompt scenario for a large language model (LLM) inference serving system that supports diverse applications with both short prompts and long prompts and heterogeneous SLOs for iteration time. To improve…
Compute Express Link (CXL) serves as a rising industry standard, delivering high-speed cache-coherent links to a variety of devices, including host CPUs, computational accelerators, and memory devices. It is designed to promote system…
Integrating GPUs into serverless computing platforms is crucial for improving efficiency. However, existing solutions for GPU-enabled serverless computing platforms face two significant problems due to coarse-grained GPU management: long…
MIX has recently been proposed as a new sensor scheme with better energy management for data-gathering in Wireless Sensor Networks. However, it is not known how it performs when some of the sensors carry out sinkhole attacks. In this paper,…
Modern SoCs integrate multiple CPU cores and Hardware Accelerators (HWAs) that share the same main memory system, causing interference among memory requests from different agents. The result of this interference, if not controlled well, is…
We present a security framework that strengthens distributed machine learning by standardizing integrity protections across CPU and GPU platforms and significantly reducing verification overheads. Our approach co-locates integrity…
Many-core systems require inter-core communication, and network-on-chips (NoCs) have been demonstrated to provide good scalability. However, not only the distributed structure but also the link switching on the NoCs have imposed a great…
Making threaded programs safe and easy to reason about is one of the chief difficulties in modern programming. This work provides an efficient execution model for SCOOP, a concurrency approach that provides not only data race freedom but…
We present SensiX++ - a multi-tenant runtime for adaptive model execution with integrated MLOps on edge devices, e.g., a camera, a microphone, or IoT sensors. SensiX++ operates on two fundamental principles - highly modular componentisation…
There exists a plethora of consensus protocols in literature. The reason is that there is no one-size-fits-all solution, since every protocol is unique and its performance is directly tied to the deployment settings and workload…
AI agents increasingly run untrusted code on developer machines: shell commands generated by language models, third-party scripts retrieved at runtime, and tool plugins of unknown provenance. Existing isolation mechanisms impose tradeoffs…
Distributed deep neural network training necessitates efficient GPU collective communications, which are inherently susceptible to deadlocks. GPU collective deadlocks arise easily in distributed deep learning applications when multiple…
Secure Multi-Party Computation (MPC) offers a practical foundation for privacy-preserving machine learning at the edge, with MPC commonly employed to support nonlinear operations. These MPC protocols fundamentally rely on Oblivious Transfer…
We present CYCLADES, a general framework for parallelizing stochastic optimization algorithms in a shared memory setting. CYCLADES is asynchronous during shared model updates, and requires no memory locking mechanisms, similar to…
Consumer machines are increasingly running large ML workloads such as large language models (LLMs), text-to-image generation, and interactive image editing. Unlike datacenter GPUs, consumer GPUs serve single-user, rapidly changing…
The run-time electromagnetic (EM) emanation of microprocessors presents a side-channel that leaks the confidentiality of the applications running on them. Many recent works have demonstrated successful attacks leveraging such side-channels…
In the quest for efficiency and performance, edge-computing providers eliminate isolation boundaries between tenants, such as strict process isolation, and instead let them compute in a more lightweight multi-threaded single-process design.…
The ever-rising computation demand is forcing the move from the CPU to heterogeneous specialized hardware, which is readily available across modern datacenters through disaggregated infrastructure. On the other hand, trusted execution…
Serverless edge computing adopts an event-based paradigm that provides back-end services on an as-used basis, resulting in efficient resource utilization. To improve the end-to-end latency and revenue, service providers need to optimize the…