Related papers: Constraining Host-Level Abuse in Self-Hosted Compu…
Protected-module architectures (PMAs) have been proposed to provide strong isolation guarantees, even on top of a compromised system. Unfortunately, Intel SGX -- the only publicly available high-end PMA -- has been shown to only provide…
Fully homomorphic encryption (FHE) and trusted execution environments (TEE) are two approaches to provide confidentiality during data processing. Each approach has its own strengths and weaknesses. In certain scenarios, computations can be…
Trusted Execution Environments (TEEs) suffer from performance issues when executing certain management instructions, such as creating an enclave, context switching in and out of protected mode, and swapping cached pages. This is especially…
In TrustZone-assisted TEEs, the trusted OS has unrestricted access to both secure and normal world memory. Unfortunately, this architectural limitation has opened an aisle of exploration for attackers, which have demonstrated how to…
Protecting sensitive information in data-driven collaborations, such as AI training, while meeting the diverse requirements of multiple mutually distrusted stakeholders, is both crucial and challenging. This paper presents Styx, a novel…
We present enclawed, a hard-fork hardening framework built on the OpenClaw AI assistant gateway. enclawed targets deployments that need attestable peer trust, deny-by-default external connectivity, signed-module loading, and a…
Computer-using agents (CUAs), which can autonomously control computers to perform multi-step actions, might pose significant safety risks if misused. However, existing benchmarks mainly evaluate LMs in chatbots or simple tool use. To more…
Intel has introduced a trusted computing technology, Intel Software Guard Extension (SGX), which provides an isolated and secure execution environment called enclave for a user program without trusting any privilege software (e.g., an…
Large Language Models (LLMs) deployed on mobile devices offer benefits like user privacy and reduced network latency, but introduce a significant security risk: the leakage of proprietary models to end users. To mitigate this risk, we…
The ever-rising computation demand is forcing the move from the CPU to heterogeneous specialized hardware, which is readily available across modern datacenters through disaggregated infrastructure. On the other hand, trusted execution…
With the proliferation of Trusted Execution Environments (TEEs) such as Intel SGX, a number of cloud providers will soon introduce TEE capabilities within their offering (e.g., Microsoft Azure). Although the integration of SGX within the…
Computer-use agents (CUAs) promise to automate complex tasks across operating systems (OS) and the web, but remain vulnerable to indirect prompt injection. Current evaluations of this threat either lack support realistic but controlled…
Dynamic partial reconfiguration enables multi-tenancy in cloud-based FPGAs, which presents security challenges for tenants, IPs, and data. Malicious users can exploit FPGAs for remote side-channel attacks (SCAs), and shared on-chip…
Autonomous AI agents built on open-source runtimes such as OpenClaw expose every available tool to every session by default, regardless of the task. A summarization task receives the same shell execution, subagent spawning, and credential…
AI agents increasingly run untrusted code on developer machines: shell commands generated by language models, third-party scripts retrieved at runtime, and tool plugins of unknown provenance. Existing isolation mechanisms impose tradeoffs…
Always-on AI agents (OpenClaw, Hermes Agent) run as a single persistent process under the owner's identity, folding messaging, memory, self-authored skills, scheduling, and shell into one authority boundary. This configuration opens what we…
Trusted Execution Environments (TEEs) have emerged at the forefront of edge computing to combat the lack of trust between system components. Field Programmable Gate Arrays (FPGAs) are commonly used as edge computers but were not created…
Irregular codes are bottlenecked by memory and communication latency. Decoupled access/execute (DAE) is a common technique to tackle this problem. It relies on the compiler to separate memory address generation from the rest of the program,…
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…
The transition of Large Language Models (LLMs) from passive code generators to autonomous agents introduces significant safety risks, specifically regarding destructive commands and inconsistent system states. Existing commercial solutions…