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