Mcp Servers

FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense

Federated Graph Neural Networks (FedGNNs) are highly vulnerable to backdoor poisoning, yet existing defenses typically rely on rule-based approaches that lack semantic understanding, making them vulnerable to stealthy triggers and harmful to benign structures. To solve this, we present FedLSG, the first framework that integrates large language models (LLMs) into federated graph backdoor defense. FedLSG introduces a graph and behavior to text grounding scheme that transforms local graph structures and client update...

arxiv · 원본 ID http://arxiv.org/abs/2607.19674v1

When HTTP 402 Meets the Blockchain: Risks on Emerging x402 Payments

x402 is an emerging payment protocol for Web APIs and autonomous AI agents. x402 extends HTTP 402 with a payment negotiation flow and delegates payment proof verification and on-chain settlement to third-party facilitators. As a result, facilitators serve as a shared payment infrastructure for many independent merchants. This centralizes trust and validation in one component, so a single flaw can affect many services. Despite rapid adoption by major vendors and economically meaningful mainnet activity, the securit...

arxiv · 원본 ID http://arxiv.org/abs/2607.19545v1

SynPre-FL: Synthetic data-driven pretraining integrated Federated Learning training framework

Federated learning (FL) offers a promising approach to privacy-preserving clinical risk prediction, but its deployment remains limited by restricted data sharing, client heterogeneity, class imbalance, and the lack of realistic tabular electronic health record (EHR) benchmarks. Synthetic data generation may alleviate data scarcity, yet its integration with federated optimisation has received limited systematic study. We propose SynPre-FL, a unified framework combining high-fidelity synthetic EHR generation with sy...

arxiv · 원본 ID http://arxiv.org/abs/2607.19524v1

ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D

As AI agents begin to automate AI R&D, we need ways to assess whether their outputs are safe to deploy, even when the agents themselves may be untrusted. AI control offers one such approach: rather than trusting the agent, it treats it as a potential adversary and uses a monitor to detect covert sabotage before deployment. We evaluate AI control for automated AI R&D with ResearchArena, a framework spanning four long-horizon tasks: safety post-training, capabilities post-training, CUDA-kernel optimization, and infe...

arxiv · 원본 ID http://arxiv.org/abs/2607.19321v1

PTSan: A Practical Memory Safety Sanitizer for C/C++ with Pointer-Object Authority

Memory safety errors remain the dominant source of severe vulnerabilities in C and C++. Pointer-based sanitizers provide stronger guarantees than location-based tools such as LLVM's ASan, but their overhead and compatibility limitations have constrained production use. We present PTSan, an LLVM sanitizer that makes pointer-based checking practical by storing an object identifier in each pointer's high bits and its bounds in a fixed-size runtime table. This representation trades a finite live-object budget for low...

arxiv · 원본 ID http://arxiv.org/abs/2607.19246v1

Squeezing the Most Out of Preemption for AoI Minimization: Single-source Case

In this work, we study a single-source single-server continuous-time status update system where the updates arrive according to a Poisson process and update service times are generally distributed. In our proposed setting, a preemption policy refers to one where a new update preempts the ongoing one with a probability depending on the age of the update in service. We first propose an analytical method to derive the average age of information (AoI) and average peak AoI (PAoI) for any such preemption policy. This an...

arxiv · 원본 ID http://arxiv.org/abs/2607.19216v1

Sarus: Privacy-Preserving Multi-Vendor Perception Fusion via Homomorphic Encryption

Cooperative perception enables autonomous vehicles (AVs) to improve situational awareness by aggregating detection outputs from multiple agents and sensing platforms, often via a shared fusion service in multi-vendor deployments. However, sharing such outputs at inference time exposes proprietary model behavior and sensitive environmental information, creating significant privacy and security concerns. In this paper, we present Sarus, a privacy-preserving framework for multi-vendor perception fusion via homomorphi...

arxiv · 원본 ID http://arxiv.org/abs/2607.19146v1

ANSI escape injection in MCP servers: Hidden from humans, visible to AI

hackernews · 원본 ID 48989006

CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization

Textual Collaborative Prompt Optimization (TCPO) extends Textgrad (Yuksekgonul et al., 2025) to a decentralized setting by allowing multiple clients to jointly improve prompts for large language models (LLMs) while keeping their data locally. Its reliance on free-form textual updating and aggregation introduces a new and largely unexplored attack surface, i.e., malicious instructions can be injected into local prompts and propagated through server-side prompt aggregation. Unlike conventional prompt injection attac...

arxiv · 원본 ID http://arxiv.org/abs/2607.18622v1

AGENTS4GEOS: agentic platform for open-source multi-physics simulation

Multi-physics simulations are essential for understanding and monitoring intricate subsurface processes such as CO2 storage. Their computational demands call for surrogate models and, for unstructured meshes, Graph Neural Networks (GNNs) are natural candidates. The main bottleneck in developing them is generating and managing the large, physically consistent simulation datasets required for training. To address this challenge, we present Agents4GEOS, an AI-agent framework built on the Model Context Protocol (MCP)...

arxiv · 원본 ID http://arxiv.org/abs/2607.18557v1

ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems

The Model Context Protocol (MCP) is an open-source standard that allows AI agents to connect to external tools, databases, and services. While this connectivity enables powerful agent capabilities, it also introduces multi-step attacks that existing per-call defenses cannot reliably detect. Attackers can compose individually benign tool invocations into malicious sequences that evade isolated inspection. This paper presents ChainWatch, a sequential detection framework for identifying multi-step attacks in MCP-base...

arxiv · 원본 ID http://arxiv.org/abs/2607.19432v1

DeusData/codebase-memory-mcp

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

github · 원본 ID 1166102148