Related papers: Constraining Host-Level Abuse in Self-Hosted Compu…
Security and privacy concerns in computer systems have grown in importance with the ubiquity of connected devices. TEEs provide security guarantees based on cryptographic constructs built in hardware. Intel software guard extensions (SGX),…
Preventing abuse of web services by bots is an increasingly important problem, as abusive activities grow in both volume and variety. CAPTCHAs are the most common way for thwarting bot activities. However, they are often ineffective against…
Trusted Execution Environments (TEEs) are gradually adopted by major cloud providers, offering a practical option of \emph{confidential computing} for users who don't fully trust public clouds. TEEs use CPU-enabled hardware features to…
Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…
Autonomous browsing agents powered by large language models (LLMs) are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface.…
Remote attestation (RA) authenticates code running in trusted execution environments (TEEs), allowing trusted code to be deployed even on untrusted hosts. However, trust relationships established by one component in a distributed…
Integrity is critical for maintaining system security, as it ensures that only genuine software is loaded onto a machine. Although confidential virtual machines (CVMs) function within isolated environments separate from the host, it is…
Modern AI agents routinely depend on secrets such as API keys and SSH credentials, yet the dominant deployment model still exposes those secrets directly to the agent process through environment variables, local files, or forwarding…
In modern computer systems, user processes are isolated from each other by the operating system and the hardware. Additionally, in a cloud scenario it is crucial that the hypervisor isolates tenants from other tenants that are co-located on…
Trusted Execution Environments (TEEs) (e.g., Intel SGX and ArmTrustZone) aim to protect sensitive computation from a compromised operating system, yet real deployments remain vulnerable to microarchitectural leakage, side-channel attacks,…
OpenClaw has rapidly established itself as a leading open-source autonomous agent runtime, offering powerful capabilities including tool integration, local file access, and shell command execution. However, these broad operational…
In most split-tunnel VPN/ZTNA deployments, installing an internal route authorizes the entire device, not a specific application, to use it. An unprivileged malicious process can therefore reach internal services by reusing routes intended…
Large language models are increasingly used as natural-language interfaces to enterprise software, but their direct use as system operators remains unsafe. Model errors can propagate into unauthorized actions, malformed requests,…
Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, and the risks grow dramatically as agents engage in multi-turn conversations and scale…
As an essential technology underpinning trusted computing, the trusted execution environment (TEE) allows one to launch computation tasks on both on- and off-premises data while assuring confidentiality and integrity. This article provides…
Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…
Process attestation systems verify that a continuous physical process, such as human authorship, actually occurred, rather than merely checking system state. These systems face a fundamental dependability challenge: the evidence collection…
The adversarial model presented by trusted execution environments (TEEs) has prompted researchers to investigate unusual attack vectors. One particularly powerful class of controlled-channel attacks abuses page-table modifications to…
Backdoor attacks on language models pose a significant threat to AI safety, where models behave normally on most inputs but exhibit harmful behavior when triggered by specific patterns. Detecting such backdoors through mechanistic…
Constructing a Trusted Execution Environment (TEE) on Field Programmable Gate Array System on Chip (FPGA-SoC) in Cloud can effectively protect users' private intel-lectual Property (IP) cores. In order to facilitate the wide-spread…