works on

From the 24 of 723 papers with an AI index.

most citedDeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

884 citations

Showing cs.CRShow all

7 papers · 1 filter

cs.CR20261 cited

More Granular, Less Trust: Enforcing Intra-Process Isolation with Arm CCA in an Untrusted Management Environment

Shiqi Liu, Zhouqi Jiang, Jie Wang +4

With the increasing adoption of confidential computing, security-sensitive applications are often deployed in confidential virtual machines (CVMs), which reduce reliance on third-p…

cs.CR2026

When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse

Yingtao Ren, Ziyi Zhao, Yiwei Fu +3

Retrieval-augmented generation (RAG) is indispensable for enhancing large language models. However, RAGs are increasingly susceptible to poisoning attacks, in which adversarial doc…

cs.CR2026

Prrr: Personal Random Rewards for Blockchain Reporting

Hongyin Chen, Yubin Ke, Xiaotie Deng +1

Smart contracts, the stateful programs running on blockchains, often rely on reports. Publishers are paid to publish these reports on the blockchain. Designing protocols that incen…

cs.CR2026

AccLock: Unlocking Identity with Heartbeat Using In-Ear Accelerometers

Lei Wang, Jiangxuan Shen, Xi Zhang +6

The widespread use of earphones has enabled various sensing applications, including activity recognition, health monitoring, and context-aware computing. Among these, earphone-base…

cs.CR2026

Mobile GUI Agents under Real-world Threats: Are We There Yet?

Guohong Liu, Jialei Ye, Jiacheng Liu +5

Recent years have witnessed a rapid development of mobile GUI agents powered by large language models (LLMs), which can autonomously execute diverse device-control tasks based on n…

cs.CR2025

Who Grants the Agent Power? Defending Against Instruction Injection via Task-Centric Access Control

Yifeng Cai, Ziming Wang, Zhaomeng Deng +6

AI agents capable of GUI understanding and Model Context Protocol are increasingly deployed to automate mobile tasks. However, their reliance on over-privileged, static permissions…