arXiv Machine Learning July 3, 2026 By Yinpeng Wu, Yitong Chen, Lixiang Wang, Jinyu Gu, Zhichao Hua, Yubin Xia

FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

Read the original on arXiv Machine Learning →

arXiv:2603. 09046v3 Announce Type: replace-cross Abstract: Device-side Large Language Models (LLMs) have witnessed explosive growth, offering higher privacy and availability compared to cloud-side LLMs.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 3

FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

arXiv:2606. 23370v2 Announce Type: replace-cross Abstract: Device-side Large Language Models (LLMs) have grown explosively, offering stronger privacy and higher availability than their cloud-side counterparts.

By Yinpeng Wu, Yitong Chen, Lixiang Wang, Jinyu Gu, Zhichao Hua, Yubin Xia

llms safety

arXiv Machine Learning

Jul 16

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge

arXiv:2607. 13088v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly moving from research settings into the wild, deployed on enterprise infrastructure, personal devices, and edge platforms.

By Ren-Yi Huang, Mingchen Li, Dumindu Samaraweera, Morris Chang

llms efficiency safety

arXiv AI

Sep 15

SpliTEE: Improving LLM Inference on Trusted Hardware with Differentially Private GPU Outsourcing

SpliTEE extends the split‑inference architecture of Slalom to large language models by protecting intermediate GPU computations with differential privacy rather than encryption. The authors show that masking intermediate representations is essential, as a prompt‑reconstruction attack can recover prompts with about 80% accuracy. Their global sensitivity analysis bounds the noise needed, and they demonstrate that SpliTEE on Intel TDX achieves near‑double the speed of fully CPU‑based inference and outperforms encryption‑based Slalom while maintaining higher accuracy.

By Shashie Dilhara Batan Arachchige, Robin Carpentier, Hassan Jameel Asghar, Dali Kaafar

llms efficiency safety

arXiv AI

Jul 16

Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models

arXiv:2607. 13093v1 Announce Type: cross Abstract: On-device LLM inference faces a trilemma of response latency, limited hardware resources and user privacy.

By Yi Li, Chen Li, Jiexiong Liu

llms rag efficiency safety

arXiv Machine Learning

Sep 2

mzCache: On-Device LLM Memory Management under Multitasking

arXiv:2609.01338v1 Announce Type: cross Abstract: On-device mobile Large Language Model (LLM) inference is gaining significant attention. However, mobile devices operate in highly dynamic multitaskin...

By Hongseung Yu, Minsung Kim, Jongseok Park, Kyunghan Lee

llms efficiency

arXiv AI

4d ago

Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents

arXiv:2605.01970v4 Announce Type: replace-cross Abstract: Memory systems enable otherwise stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. Th...

By Debeshee Das, Julien Piet, Darya Kaviani, Luca Beurer-Kellner, Florian Tram\`er, David Wagner

llms rag agents multimodal benchmarks safety

One email a morning, machine-written

Related stories

FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation

Securing LLMs in the Wild: Privacy and Security Challenges at the Edge

SpliTEE: Improving LLM Inference on Trusted Hardware with Differentially Private GPU Outsourcing

Efficient and Privacy Aware Edge Cloud Collaborative Inference for Large Language Models

mzCache: On-Device LLM Memory Management under Multitasking

Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses in LLM Agents