Related papers: SUDP: Secret-Use Delegation Protocol for Agentic S…
With the fast development of large language models (LLMs), LLM-driven Web Agents (Web Agents for short) have obtained tons of attention due to their superior capability where LLMs serve as the core part of making decisions like the human…
Individual Differential Privacy (iDP) promises users control over their privacy, but this promise can be broken in practice. We reveal a previously overlooked vulnerability in sampling-based iDP mechanisms: while conforming to the iDP…
AI agents have become increasingly adept at complex tasks such as coding, reasoning, and multimodal understanding. However, building generalist systems requires moving beyond individual agents to collective inference -- a paradigm where…
Large language model (LLM) agents face a structural tension: cloud agents provide strong reasoning but expose user data, while on-device agents preserve privacy at the cost of overall capability. Existing device-cloud designs treat this…
We present the design and validation of Stoppable Secondary Use (StopSec), a privacy-preserving protocol with the capability to identify a secondary user (SU) causing interference to a primary user (PU) and to act quickly to stop the…
This work introduces security for unsourced random access (URA) by employing physical layer security techniques. To achieve confidentiality, the proposed system opportunistically exploits intrinsic features of feedback-aided URA without…
The increasing demand for software development has driven interest in automating software engineering (SE) tasks using Large Language Models (LLMs). Recent efforts extend LLMs into multi-agent systems (MAS) that emulate collaborative…
The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It…
In recent years, Session Initiation Protocol (SIP) has become widely used in current internet protocols. It is a text-based protocol much like Hyper Text Transport Protocol (HTTP) and Simple Mail Transport Protocol (SMTP). SIP is a strong…
Data privacy is critical in instilling trust and empowering the societal pacts of modern technology-driven democracies. Unfortunately, it is under continuous attack by overreaching or outright oppressive governments, including some of the…
Large Language Model (LLM) agents have achieved rapid adoption and demonstrated remarkable capabilities across a wide range of applications. To improve reasoning and task execution, modern LLM agents would incorporate memory modules or…
Modern applications often operate on data in multiple administrative domains. In this federated setting, participants may not fully trust each other. These distributed applications use transactions as a core mechanism for ensuring…
Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a first-class architectural object. This paper names that boundary the…
Traditional AI reasoning techniques have been used successfully in many domains, including logistics, scheduling and game playing. This paper is part of a project aimed at investigating how such techniques can be extended to coordinate…
Network library APIs have historically been developed with the emphasis on data movement, placement, and communication semantics. Many communication semantics are available across a large variety of network libraries, such as send-receive,…
As multi-agent systems evolve to encompass increasingly diverse and specialized agents, the challenge of enabling effective collaboration between heterogeneous agents has become paramount, with traditional agent communication protocols…
Large language models (LLMs) exhibit strong performance on self-contained programming tasks. However, they still struggle with repository-level software engineering (SWE), which demands (1) deep codebase navigation with effective context…
Recent trend towards cloud computing paradigm, smart devices and 4G wireless technologies has enabled seamless data sharing among users. Cloud computing environment is distributed and untrusted, hence data owners have to encrypt their data…
Enterprise AI backends increasingly admit heterogeneous execution requests across model deployment, inference, evaluation, data movement, and agentic workflows. In many systems, those requests arrive in service-specific shapes, which makes…
Recent advancements in dialogue policy planning have emphasized optimizing system agent policies to achieve predefined goals, focusing on strategy design, trajectory acquisition, and efficient training paradigms. However, these approaches…