English
Related papers

Related papers: Sandlock: Confining AI Agent Code with Unprivilege…

200 papers

Rust is a modern systems language focused on performance and reliability. Complementing Rust's promise to provide "fearless concurrency", developers frequently exploit asynchronous message passing. Unfortunately, arbitrarily ordering…

Programming Languages · Computer Science 2022-02-03 Zak Cutner , Nobuko Yoshida , Martin Vassor

Sandboxing restricts what applications do, and prevents exploited processes being abused; yet relatively few applications get sandboxed: why? We report a usability trial with 7 experienced Seccomp developers exploring how they approached…

Operating Systems · Computer Science 2025-06-13 Maysara Alhindi , Joseph Hallett

Traditional cluster designs were originally server-centric, and have evolved recently to support hardware acceleration and storage disaggregation. In applications that leverage acceleration, the server CPU performs the role of orchestrating…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-09-25 Seo Jin Park , Ramesh Govindan , Kai Shen , David Culler , Fatma Özcan , Geon-Woo Kim , Hank Levy

Software sandboxing or software-based fault isolation (SFI) is a lightweight approach to building secure systems out of untrusted components. Mozilla, for example, uses SFI to harden the Firefox browser by sandboxing third-party libraries,…

Cryptography and Security · Computer Science 2021-11-19 Matthew Kolosick , Shravan Narayan , Evan Johnson , Conrad Watt , Michael LeMay , Deepak Garg , Ranjit Jhala , Deian Stefan

The integration of Large Language Models (LLMs) into mobile and software development workflows faces a persistent tension among three demands: semantic awareness, developer productivity, and data privacy. Traditional cloud-based tools offer…

Software Engineering · Computer Science 2025-12-10 Liao Hu , Qiteng Wu , Ruoyu Qi

Running off-site software middleboxes at third-party service providers has been a popular practice. However, routing large volumes of raw traffic, which may carry sensitive information, to a remote site for processing raises severe security…

Cryptography and Security · Computer Science 2019-10-17 Huayi Duan , Cong Wang , Xingliang Yuan , Yajin Zhou , Qian Wang , Kui Ren

Microprocessors enable aggressive hardware virtualization by means of which multiple processes temporally execute on the system. These security-critical and ordinary processes interact with each other to assure application progress.…

Cryptography and Security · Computer Science 2020-01-28 Hamza Omar , Omer Khan

Modern software engineers operate across 5-10 disconnected tools daily: GitHub, GitLab, Jira, Slack, calendar applications, CI dashboards, AI coding assistants, and container platforms. This fragmentation creates cognitive overhead that…

Software Engineering · Computer Science 2026-04-21 Happy Bhati

Public key infrastructure (PKI) is a certificate-based technology that helps in authenticating systems identities. HTTPS/TLS relies mainly on PKI to minimize fraud over the Internet. Nowadays, websites utilize CDNs to improve user…

Cryptography and Security · Computer Science 2022-07-20 Hisham Galal , Mohammad Mannan , Amr Youssef

Technology is becoming increasingly pervasive. At present, the system components working together to provide functionality, be they purely software or with a physical element, tend to operate within silos, bound to a particular application…

Computers and Society · Computer Science 2017-10-19 Raluca Diaconu , Jean Bacon , Jie Deng , Jatinder Singh

Many enterprises are increasingly adopting Artificial Intelligence (AI) to make internal processes more competitive and efficient. In response to public concern and new regulations for the ethical and responsible use of AI, implementing AI…

Artificial Intelligence · Computer Science 2025-10-01 Paula Reyero Lobo , Kevin Johnson , Bill Buchanan , Matthew Shardlow , Ashley Williams , Samuel Attwood

Application compartmentalization and privilege separation are our primary weapons against ever-increasing security threats and privacy concerns on connected devices. Despite significant progress, it is still challenging to privilege…

Cryptography and Security · Computer Science 2023-06-27 Zahra Tarkhani , Anil Madhavapeddy

Software transactional memory implementations which allow transactions to work on inconsistent states of shared data, risk to cause application visible errors such as memory access violations or endless loops. Hence, many implementations…

Distributed, Parallel, and Cluster Computing · Computer Science 2014-09-23 Holger Machens

AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool permissions introduce security risks such as indirect prompt injection and tool misuse. We…

Cryptography and Security · Computer Science 2026-01-21 Roy Betser , Shamik Bose , Amit Giloni , Chiara Picardi , Sindhu Padakandla , Roman Vainshtein

For safety reasons, unprivileged users today have only limited ways to customize the kernel through the extended Berkeley Packet Filter (eBPF). This is unfortunate, especially since the eBPF framework itself has seen an increase in scope…

Operating Systems · Computer Science 2023-08-16 Soo Yee Lim , Xueyuan Han , Thomas Pasquier

CaMeL (Capabilities for Machine Learning) introduces a capability-based sandbox to mitigate prompt injection attacks in large language model (LLM) agents. While effective, CaMeL assumes a trusted user prompt, omits side-channel concerns,…

Cryptography and Security · Computer Science 2025-05-30 Krti Tallam , Emma Miller

We propose xRAC to permit users to run special applications on managed hosts and to grant them access to protected network resources. We use restricted application containers (RACs) for that purpose. A RAC is a virtualization container with…

Networking and Internet Architecture · Computer Science 2023-01-25 Frederik Hauser , Mark Schmidt , Michael Menth

Embodied Large Language Models (LLMs) enable AI agents to interact with the physical world through natural language instructions and actions. However, beyond the language-level risks inherent to LLMs themselves, embodied LLMs with…

Robotics · Computer Science 2026-03-03 Xinyu Huang , Qiang Yang , Leming Shen , Zijing Ma , Yuanqing Zheng

Agents are now used widely in the process of software development, but building production-ready software engineering agents is a complex task. Deploying software agents effectively requires flexibility in implementation and…

Hardware support for trusted execution in modern CPUs enables tenants to shield their data processing workloads in otherwise untrusted cloud environments. Runtime systems for the trusted execution must rely on an interface to the untrusted…

Operating Systems · Computer Science 2020-01-22 Christian Priebe , Divya Muthukumaran , Joshua Lind , Huanzhou Zhu , Shujie Cui , Vasily A. Sartakov , Peter Pietzuch