English
Related papers

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

200 papers

The growing use of third-party hardware accelerators (e.g., FPGAs, ASICs) for deep neural networks (DNNs) introduces new security vulnerabilities. Conventional model-level backdoor attacks, which only poison a model's weights to misclassify…

Cryptography and Security · Computer Science 2026-03-17 Sanskar Amgain , Daniel Lobo , Atri Chatterjee , Swarup Bhunia , Fnu Suya

Developers and data scientists often struggle to write command-line inputs, even though graphical interfaces or tools like ChatGPT can assist. The solution? "ai-cli," an open-source system inspired by GitHub Copilot that converts natural…

Software Engineering · Computer Science 2023-09-14 Diomidis Spinellis

The rapid emergence of open-source, locally hosted intelligent agents marks a critical inflection point in human-computer interaction. Systems such as OpenClaw demonstrate that Large Language Model (LLM)-based agents can autonomously…

Artificial Intelligence · Computer Science 2026-03-13 Rui Liu , Tao Zhe , Dongjie Wang , Zijun Yao , Kunpeng Liu , Yanjie Fu , Huan Liu , Jian Pei

Policy Cards are introduced as a machine-readable, deployment-layer standard for expressing operational, regulatory, and ethical constraints for AI agents. The Policy Card sits with the agent and enables it to follow required constraints at…

Artificial Intelligence · Computer Science 2025-10-29 Juraj Mavračić

Virtualization is frequently used to isolate untrusted processes and control their access to sensitive resources. However, isolation usually carries a price in terms of less resource sharing and reduced inter-process communication. In an…

Operating Systems · Computer Science 2019-01-24 Paul Ratazzi , Ashok Bommisetti , Nian Ji , Wenliang Du

As usage of generative AI tools skyrockets, the amount of sensitive information being exposed to these models and centralized model providers is alarming. For example, confidential source code from Samsung suffered a data leak as the text…

Cryptography and Security · Computer Science 2024-10-01 Manil Shrestha , Yashodha Ravichandran , Edward Kim

Go is a production-level statically typed programming language whose design features explicit message-passing primitives and lightweight threads, enabling (and encouraging) programmers to develop concurrent systems where components interact…

Programming Languages · Computer Science 2017-03-01 Julien Lange , Nicholas Ng , Bernardo Toninho , Nobuko Yoshida

AI IDEs and coding agents compress discovery, fetch, workspace open, installation, and execution into one low-observability loop. Existing defenses such as provenance frameworks, package and repository firewalls, runtime protection, and…

Cryptography and Security · Computer Science 2026-04-09 Jepson Taylor , Chris Brousseau , Jordan Hildebrandt , Kelli Quinn

The widening availability of hardware-based trusted execution environments (TEEs) has been accelerating the adaptation of new applications using TEEs. Recent studies showed that a cloud application consists of multiple distributed software…

Cryptography and Security · Computer Science 2022-12-23 Joongun Park , Seunghyo Kang , Sanghyeon Lee , Taehoon Kim , Jongse Park , Youngjin Kwon , Jaehyuk Huh

The continued improvements in language model capability have unlocked their widespread use as drivers of autonomous agents, for example in coding or computer use applications. However, the core of these systems has not changed much since…

Machine Learning · Computer Science 2026-05-13 Guinan Su , Yanwu Yang , Xueyan Li , Jonas Geiping

Heterogeneous Internet of Things (IoT) systems suffer from fragmentation across hardware architectures, networking stacks, and data serialization formats. Existing standards (such as MQTT, COAP, and DDS) rely on address-bound, imperative…

Networking and Internet Architecture · Computer Science 2026-05-26 Yeison David Mejia Mosquera

Today's monolithic kernels often implement a small, fixed set of policies such as disk I/O scheduling policies, while exposing many parameters to let users select a policy or adjust the specific setting of the policy. Ideally, the…

Operating Systems · Computer Science 2015-10-20 Yan Cui , Quan Chen , Junfeng Yang

An agentic-AI runtime issues tool calls, sends messages, and actuates devices on behalf of an LLM. Catching the four ways an action can diverge from its audit record -- F1 gate-bypass, F2 audit-forgery, silent host failure, F4 wrong-target,…

Cryptography and Security · Computer Science 2026-05-05 Alfredo Metere

In this paper, we propose a new approach to building synchronization primitives, dubbed "lwlocks" (short for light-weight locks). The primitives are optimized for small memory footprint while maintaining efficient performance in low…

Operating Systems · Computer Science 2011-09-14 Nitin Garg , Ed Zhu , Fabiano C. Botelho

This paper introduces language-based agent control (LBAC), a new programming model for agentic applications that brings techniques from programming languages and language-based security to the problem of agent control. In conventional…

Programming Languages · Computer Science 2026-05-14 Timothy Zhou , Loris D'Antoni , Nadia Polikarpova

The cloud computing landscape has evolved significantly in recent years, embracing various sandboxes to meet the diverse demands of modern cloud applications. These sandboxes encompass container-based technologies like Docker and gVisor,…

Cryptography and Security · Computer Science 2024-05-27 Debopriya Roy Dipta , Thore Tiemann , Berk Gulmezoglu , Eduard Marin , Thomas Eisenbarth

In this paper, we propose a blockchain-based computing verification protocol, called EntrapNet, for distributed shared computing networks, an emerging underlying network for many internet of things (IoT) applications. EntrapNet borrows the…

Cryptography and Security · Computer Science 2021-05-04 Chong Li , Lei Zhang , Serbiao Fang

As an emerging technique for confidential computing, trusted execution environment (TEE) receives a lot of attention. To better develop, deploy, and run secure applications on a TEE platform such as Intel's SGX, both academic and industrial…

Cryptography and Security · Computer Science 2021-09-07 Weijie Liu , Hongbo Chen , XiaoFeng Wang , Zhi Li , Danfeng Zhang , Wenhao Wang , Haixu Tang

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…

Cryptography and Security · Computer Science 2025-09-23 Brendan Murphy , Dillon Bowen , Shahrad Mohammadzadeh , Tom Tseng , Julius Broomfield , Adam Gleave , Kellin Pelrine

The adoption of Vision-Language Models (VLMs) in embodied AI agents, while being effective, brings safety concerns such as jailbreaking. Prior work have explored the possibility of directly jailbreaking the embodied agents through…

Cryptography and Security · Computer Science 2025-11-21 Chunyang Li , Zifeng Kang , Junwei Zhang , Zhuo Ma , Anda Cheng , Xinghua Li , Jianfeng Ma
‹ Prev 1 8 9 10 Next ›