Related papers: Grimlock: Guarding High-Agency Systems with eBPF a…
Mobile Graphical User Interface (GUI) agents have demonstrated strong capabilities in automating complex smartphone tasks by leveraging multimodal large language models (MLLMs) and system-level control interfaces. However, this paradigm…
Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious…
Since its debut, SGX has been used in many applications, e.g., secure data processing. However, previous systems usually assume a trusted enclave and ignore the security issues caused by an untrusted enclave. For instance, a vulnerable (or…
Communication encryption is crucial in computer technology, but existing algorithms struggle with balancing cost and security. We propose EncGPT, a multi-agent framework using large language models (LLM). It includes rule, encryption, and…
Large Language Model (LLM) agents provide powerful automation capabilities, but they also create a substantially broader attack surface than traditional applications due to their tight integration with non-deterministic models and…
Large language models (LLMs) increasingly act as autonomous agents, using tools to execute code, read and write files, and access networks, creating novel security risks. To mitigate these risks, agents are commonly deployed and evaluated…
As generative artificial intelligence evolves, autonomous agent networks present a powerful paradigm for interactive covert communication. However, because agents dynamically update internal memories via environmental interactions, existing…
The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion tools such as GitHub Copilot operated…
System call filtering is a widely used security mechanism for protecting a shared OS kernel against untrusted user applications. However, existing system call filtering techniques either are too expensive due to the context switch overhead…
As large language models (LLMs) advance, ensuring AI safety and alignment is paramount. One popular approach is prompt guards, lightweight mechanisms designed to filter malicious queries while being easy to implement and update. In this…
Agentic AI systems increasingly execute consequential actions on behalf of human principals, delegating tasks through multi-step chains of autonomous agents. No existing standard addresses a fundamental accountability gap: verifying that…
Large language model(LLM)-driven multi-agent systems(MAS) coordinate specialized agents through predefined interaction topologies and have shown promise for complex tasks such as competition-level code generation. Recent studies demonstrate…
Cloud computing is an opened and distributed network that guarantees access to a large amount of data and IT infrastructure at several levels (software, hardware...). With the increase demand, handling clients' needs is getting increasingly…
Fog and edge computing require adaptive control schemes that can handle partial observability, severe latency requirements, and dynamically changing workloads. Recent research on Agentic AI (AAI) increasingly integrates reasoning systems…
Tool-using LLM agents must act on untrusted webpages, emails, files, and API outputs while issuing privileged tool calls. Existing defenses often mediate trust at the granularity of an entire tool invocation, forcing a brittle choice in…
As autonomous AI agents increasingly populate the Internet, a novel security challenge arises: "Is this entity an AI agent?" It is a new entity-type verification problem with no established solution. We formalize the problem through a…
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…
Enterprise software engineering is shifting away from deterministic CRUD/REST architectures toward AI-native systems where large language models act as cognitive orchestrators. This transition introduces a critical security tension:…
Large language models (LLMs) have proven to be very capable, but access to frontier models currently relies on inference providers. This introduces trust challenges: how can we be sure that the provider is using the model configuration they…
Agentic computing systems, while immensely capable, raise serious security, privacy, and safety concerns. A key issue is that the full set of functionalities offered by these systems, combined with their probabilistic execution flows, is…