Related papers: Sandlock: Confining AI Agent Code with Unprivilege…
Current large language model agent frameworks prioritize autonomy but lack the governability mechanisms required for enterprise deployment. High-risk write operations proceed without independent review, complex tasks lack acceptance…
Large language models (LLMs) have evolved from simple chatbots into autonomous agents capable of performing complex tasks such as editing production code, orchestrating workflows, and taking higher-stakes actions based on untrusted inputs…
Isolating sensitive state and data can increase the security and robustness of many applications. Examples include protecting cryptographic keys against exploits like OpenSSL's Heartbleed bug or protecting a language runtime from native…
Heterogeneous hardware and dynamic workloads worsen long-standing OS bottlenecks in scalability, adaptability, and manageability. At the same time, advances in machine learning (ML), large language models (LLMs), and agent-based methods…
Contemporary AI governance frameworks rely heavily on post hoc oversight, policy guidance, and behavioral alignment techniques, yet these mechanisms become fragile as systems gain autonomy, speed, and operational opacity. This paper…
Due to cost benefits, supply chains of integrated circuits (ICs) are largely outsourced nowadays. However, passing ICs through various third-party providers gives rise to many security threats, like piracy of IC intellectual property or…
Real-time embedded platforms with resource constraints can take the benefits of mixed-criticality system where applications with different criticality-level share computational resources, with isolation in the temporal and spatial domain. A…
Reading or writing outside the bounds of a buffer is a serious security vulnerability that has been exploited in numerous occasions. These attacks can be prevented by ensuring that every buffer is only accessed within its specified bounds.…
LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets where the analyst can build and instrument the code. In practice the work is split among…
Agentic AI coding editors driven by large language models have recently become more popular due to their ability to improve developer productivity during software development. Modern editors such as Cursor are designed not just for code…
The recent progress of artificial intelligence(AI) has shown great potentials for alleviating human burden in various complex tasks. From the view of software engineering, AI techniques can be seen in many fundamental aspects of…
The integration of Large Language Models (LLMs) into software engineering has revolutionized code generation, enabling unprecedented productivity through promptware and autonomous AI agents. However, this transformation introduces…
Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-world execution environments are far from ideal: pop-ups,…
Microcode is an abstraction layer used by modern x86 processors that interprets user-visible CISC instructions to hardware-internal RISC instructions. The capability to update x86 microcode enables a vendor to modify CPU behavior in-field,…
Efficient cloud computing relies on in-process isolation to optimize performance by running workloads within a single process. Without heavy-weight process isolation, memory safety errors pose a significant security threat by allowing an…
Software fault isolation (SFI) is a popular way to sandbox untrusted software. A key component of SFI is the verifier that checks the untrusted code is written in a subset of the machine language that guarantees it never reads or writes…
In modern software development, multiple software components, often sourced from different contributors, including AI assistants, are combined to create a cohesive system. Although these components might each be individually safe, their…
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current…
This paper presents SplitBox, a scalable system for privately processing network functions that are outsourced as software processes to the cloud. Specifically, providers processing the network functions do not learn the network policies…
The rise of AI agents powered by Large Language Models (LLMs) presents critical challenges: how to securely execute and migrate these agents across heterogeneous environments while protecting sensitive user data, maintaining availability…