中文
相关论文

相关论文: Sandlock: Confining AI Agent Code with Unprivilege…

200 篇论文

Confidential Computing (CC) has received increasing attention in recent years as a mechanism to protect user data from untrusted operating systems (OSes). Existing CC solutions hide confidential memory from the OS and/or encrypt it to…

密码学与安全 · 计算机科学 2024-12-06 Caihua Li , Seung-seob Lee , Lin Zhong

The systematic assessment of AI systems is increasingly vital as these technologies enter high-stakes domains. To address this, the EU's Artificial Intelligence Act introduces AI Regulatory Sandboxes (AIRS): supervised environments where AI…

计算机与社会 · 计算机科学 2025-10-10 Alessio Buscemi , Thibault Simonetto , Daniele Pagani , German Castignani , Maxime Cordy , Jordi Cabot

The increasing availability of cloud computing and scientific super computers brings great potential for making R accessible through public or shared resources. This allows us to efficiently run code requiring lots of cycles and memory, or…

密码学与安全 · 计算机科学 2014-02-05 Jeroen Ooms

The rapid advancement of Large Language Models (LLMs) is catalyzing a shift towards autonomous AI Agents capable of executing complex, multi-step tasks. However, these agents remain brittle when faced with real-world exceptions, making…

Cloud computing offers the economies of scale for computational resources with the ease of management, elasticity, and fault tolerance. To take advantage of these benefits, many enterprises are contemplating to outsource the middlebox…

密码学与安全 · 计算机科学 2019-10-18 Bohdan Trach , Alfred Krohmer , Sergei Arnautov , Franz Gregor , Pramod Bhatotia , Christof Fetzer

Software vulnerabilities in applications undermine the security of applications. By blocking unused functionality, the impact of potential exploits can be reduced. While seccomp provides a solution for filtering syscalls, it requires manual…

密码学与安全 · 计算机科学 2020-12-07 Claudio Canella , Mario Werner , Daniel Gruss , Michael Schwarz

With the development of Internet of Things (IoT), it is gaining a lot of attention. It is important to secure the embedded systems with low overhead. The Linux Seccomp is widely used by developers to secure the kernels by blocking the…

密码学与安全 · 计算机科学 2025-10-07 Dongyang Zhan , Zhaofeng Yu , Xiangzhan Yu , Hongli Zhang , Lin Ye , Likun Liu

Commodity applications contain more and more combinations of interacting components (user, application, library, and system) and exhibit increasingly diverse tradeoffs between isolation, performance, and programmability. We argue that the…

密码学与安全 · 计算机科学 2021-08-11 Bumjin Im , Fangfei Yang , Chia-Che Tsai , Michael LeMay , Anjo Vahldiek-Oberwagner , Nathan Dautenhahn

Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations…

人工智能 · 计算机科学 2025-02-10 Teun van der Weij , Felix Hofstätter , Ollie Jaffe , Samuel F. Brown , Francis Rhys Ward

Recent attacks have broken process isolation by exploiting microarchitectural side channels that allow indirect access to shared microarchitectural state. Enclaves strengthen the process abstraction to restore isolation guarantees. We…

密码学与安全 · 计算机科学 2019-08-30 Thomas Bourgeat , Ilia Lebedev , Andrew Wright , Sizhuo Zhang , Arvind , Srinivas Devadas

One single error can result in a total compromise of all security in today's large, monolithic software. Partitioning of software can help simplify code-review and verification, whereas isolated execution of software-components limits the…

密码学与安全 · 计算机科学 2017-06-16 Alexander Senier , Martin Beck , Thorsten Strufe

We introduce MPLSandbox, an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs). It can automatically identify the…

Isolation is a critical property for shared infrastructure to limit exposure and interference among simultaneous running workloads. Cloud providers use different isolation mechanisms such as full Virtual Machines, microVMs, Linux…

操作系统 · 计算机科学 2025-07-30 Anjali , Michael M. Swift

The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing…

人工智能 · 计算机科学 2026-05-19 Ashwin Aravind

Enclaves have emerged as a particularly compelling primitive to implement trusted execution environments: strongly isolated sensitive user-mode processes in a largely untrusted software environment. While the threat models employed by…

密码学与安全 · 计算机科学 2018-12-31 Ilia Lebedev , Kyle Hogan , Jules Drean , David Kohlbrenner , Dayeol Lee , Krste Asanović , Dawn Song , Srinivas Devadas

The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…

密码学与安全 · 计算机科学 2026-04-28 Richard Joseph Mitchell

Recent autonomous AI agents such as Codex, and Claude Code have made it increasingly practical for users to delegate complex tasks, including writing emails, executing code, issuing shell commands, and carrying out multi-step plans.…

人机交互 · 计算机科学 2026-04-21 Haomin Zhuang , Hanwen Xing , Xiangliang Zhang

While there exist many isolation mechanisms that are available to cloud service providers, including virtual machines, containers, etc., the problem of side-channel increases in importance as a remaining security vulnerability, particularly…

密码学与安全 · 计算机科学 2017-09-01 Read Sprabery , Konstantin Evchenko , Abhilash Raj , Rakesh B. Bobba , Sibin Mohan , Roy H. Campbell

Linux containers currently provide limited isolation guarantees. While containers separate namespaces and partition resources, the patchwork of mechanisms used to ensure separation cannot guarantee consistent security semantics. Even worse,…

密码学与安全 · 计算机科学 2021-02-16 William Findlay , David Barrera , Anil Somayaji

Collaborative AI experimentation in industry and academia requires environments that support rapid trials while maintaining controlled access, organisational isolation, and traceable workflows. Although interest in AI sandboxes is…