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