Results for “services”

The Guardian Haiti Jelle Krings

Giving birth in the shadow of Haiti’s gang violence – photo essay

As fighting intensifies in Port-au-Prince, only a fraction of its maternity services remain, and they are under constant threat Eight months pregnant, Françoise, 45, arrives early in the morning at a deserted school in Bel Air. The hillside neighbourhood in Port-au-Prince has been controlled by gangs since a violent takeover in 2019. Schools have closed, electricity has been cut off and food is scarce. Gunfights can erupt at any time. Françoise having a Doppler ultrasound in…

Read at The Guardian Haiti

Journal articles (OpenAlex) Zahid Memon, Asma Ummad, Amina Olabi et al. · The International Journal of Health Planning and Management Geopolitics

Health System Resilience and Afghan Refugee Health in Pakistan: An Exploratory Study of Challenges and Pathways to Inclusion

Pakistan has hosted Afghan refugees for more than four decades, in one of the world's most protracted displacements of people. Afghan refugees receive health services through United Nations High Commissioner for Refugees (UNHCR) and non-governmental organisation (NGO) supported programmes alongside public sector facilities at every tier. They remain excluded from key national health protection programmes such as the Sehat Sahulat Programme. Understanding the system-level…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yedidel Louck SI

Protocol-Level Attacks on Agentic Commerce Platforms: A Cross-Platform Taxonomy, AIP-Bench, and Unified Defense

Agentic commerce platforms let AI agents autonomously discover services, move payments, and wield user credentials on their users' behalf, and they already handle real money. Their security has so far been studied almost entirely at the level of the AI model, through prompt injection and misalignment. We show that the more consequential risks lie one layer down, in the protocol between agents and commerce services. There, vulnerabilities are structural : exploitation is…

Read at arXiv (research papers)

arXiv (research papers) Om Narayan SI

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…

Read at arXiv (research papers)

arXiv (research papers) Rabimba Karanjai SI

Context Contamination in LLM Analysis of Network Security Logs: Poison with Passive Prompt Injection and Mitigation Evaluation

Large Language Models are increasingly deployed in Security Operations Centers for log analysis tasks including summarization, alert triage, and threat investigation. These systems ingest logs from external-facing services and process network logs as natural language contexts to generate security insights. We demonstrate that this architectural pattern introduces a critical vulnerability: adversaries can embed prompt injection payloads in log-generating fields that persist…

Read at arXiv (research papers)

Journal articles (OpenAlex) Tran Thi Xuan Anh, Tuan Minh Le · Sustainability Accounting Management and Policy Journal Geopolitics

Vietnam’s digital financial inclusion and its impact on provincial and regional poverty reduction

Purpose This study aims to investigate the potential of digital inclusive finance (DIF) to contribute to poverty alleviation in Vietnam, with the aim of supporting the country’s pursuit of the United Nations’ Sustainable Development Goals, as well as the strategic objectives set forth by the Vietnamese Government and Communist Party. The study explores how increased access and usage of digital financial services can be leveraged to drive progress toward reducing poverty and…

Read at Journal articles (OpenAlex)

The Guardian Cuba Geopolitics

Will Trump invade Cuba? – podcast

Since Donald Trump threatened to ‘take’ Cuba, the Caribbean island has been on edge. Escalating US sanctions and an oil blockade has crippled essential services, plunged the country into blackouts and ground life for its 10 million people to a near halt. Nour Haydar speaks with Ruaridh Nicoll about what life is like on the ground in Havana – and if US military intervention could be next

Read at The Guardian Cuba

arXiv (research papers) Yuanai Xie SI

Beyond Wireless Security: Covert Communications in Large Language Model-enabled Edge Networks

Large language model (LLM)-enabled edge networks (LLMENs) offer mobile users high-quality and low-latency AI-generated content services in the 6G era. However, unlike typical edge networks, LLMENs present unique security challenges due to the inherent complexity of LLMs, their high computational overhead, and continuous interactions with users. Specifically, both frequent user interactions (i.e., queries and responses) over wireless channels and potential electromagnetic…

Read at arXiv (research papers)

arXiv (research papers) Peizhi Niu SI

Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens

Claw-like AI agents (e.g., OpenClaw) are always-on processes with persistent access to credentials, files, tools, and external services. They take on system-level responsibilities -- installing packages, maintaining state, scheduling subtasks, and mediating I/O -- making security failures far more severe than in other agents. Yet existing benchmarks focus on model responses and tool calls, leaving cross-component failure modes largely unmeasured. We adopt a computer-system…

Read at arXiv (research papers)

Journal articles (OpenAlex) Nguyen Thanh Quang · Information Development Geopolitics

National digital data governance in developing countries: An institutional capability framework and its illustrative relevance to Vietnam

National digital transformation increasingly depends on governments’ ability to govern data as a strategic public resource across agencies, sectors, and administrative levels. This challenge is especially important in developing countries, where digital platforms, national databases, and online public services may expand faster than the institutional capability required to govern data coherently. Existing studies have examined open data, interoperability, metadata…

Read at Journal articles (OpenAlex)

arXiv (research papers) Saeid Jamshidi SI

Security Engineering of OpenClaw: Analyzing Attack Surface Expansion and Trust-Boundary Violations

Agentic large language model (LLM) systems can now execute actions, not only produce text. When model outputs trigger privileged operations such as shell commands, browser automation, or external tool calls, the security problem shifts from alignment alone to system configuration and structural design. We analyze OpenClaw, a self-hosted multi-agent system in which LLM outputs can execute commands and interact with tools and services. We measure compromise probability…

Read at arXiv (research papers)

arXiv (research papers) Hiskias Dingeto SI

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls. Existing benchmarks under-measure the threat: most cover only a handful of integrations with the same attack payload replayed across runs, and open-source guards are trained on chat-style data rather than tool-response…

Read at arXiv (research papers)

Journal articles (OpenAlex) Sezgin ELBAY · Journal of Balkan and Near Eastern Studies Geopolitics

Statecraft After Liberalism: Türkiye’s Statist Turn and Structural Transformation on the Balkan—Near Eastern Periphery, 1923–1939

This study investigates Türkiye’s structural transformation between 1923 and 1939, with emphasis on the statist turn after the erosion of interwar liberalism. Sector-disaggregated historical series are analysed using a mixed design: MANOVA to test joint shifts in agriculture, industry, services; ynthetic ontrol (with timing, donor and log-scale robustness) to estimate a counterfactual path for real GDP per capita; PCA with change-point detection to identify latent drivers…

Read at Journal articles (OpenAlex)

arXiv (research papers) Dongxu Yang SI

Device Context Protocol: A Compact, Safety-First Architecture for LLM-Driven Control of Constrained Devices

Large language models are increasingly used as orchestrators of external tools via the Model Context Protocol (MCP), but MCP is built for software services with megabytes of memory and does not descend to the microcontrollers that dominate the long tail of physical devices. Recent work (IoT-MCP) ports MCP to edge gateways at 74 KB peak memory; this still excludes the smallest commodity MCUs and, critically, does not address the safety problem of giving an unreliable caller…

Read at arXiv (research papers)

Journal articles (OpenAlex) Lisa J. Wheildon, Asher Flynn, Abby Wild · International Journal for Crime Justice and Social Democracy Geopolitics

Screaming Underwater: Survivor Activism, Co-production and the Limits of Formal Engagement in Gender-Based Violence Policy

Survivors of gender-based violence (GBV) are increasingly engaged in the co-production of public policies and services, yet marginalised survivors remain largely excluded from shaping the decisions that affect them most. Drawing on in-depth interviews with 11 survivor advocates and activists from First Nations, culturally and racially marginalised, LGBTQI+ and disability communities in Australia, this article examines what works for survivors in terms of driving policy…

Read at Journal articles (OpenAlex)

arXiv (research papers) Zixuan Chen SI

IterInject: Indirect Prompt Injection Against LLM Agents via Feedback-Guided Iterative Optimization

LLM-based agents are increasingly deployed for complex tasks requiring planning, tool use, and interaction with external services. Their reliance on untrusted external content exposes them to indirect prompt injection (IPI), in which adversarial instructions embedded in retrieved data hijack agent behavior. Existing attacks rely on static payloads that cannot adapt to agent-specific defenses; even recent adaptive methods lack structured feedback to guide optimization. We…

Read at arXiv (research papers)

Journal articles (OpenAlex) Julieta Alejandra Belmar Prieto, Mauricio Fuentes-Alburquenque, Kátia Andrade et al. · Culture Health & Sexuality Geopolitics

Sexual health care perspectives and practices among Haitian migrants in Chile

Sexual health has been defined as a human right and a key component of human well-being. In contexts of migration, its exercise is influenced by life trajectories, access barriers, and cultural factors that shape perceptions and care practices. In Chile, sexual health care for members of the Haitian population—a recently arrived group with a distinct language—poses communicative and cultural challenges for the provision of equitable and appropriate services. This study…

Read at Journal articles (OpenAlex)

arXiv (research papers) Zi Liang SI

Mobius Injection: From One-Shot Prompt Injection to Sustained Resource Exhaustion in AI Agent Infrastructure

Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastructures. While prior research has extensively examined the security of LLMs and agents in isolation, the systemic risk of the agent acting as a disruptive "hub" within the user-agent-service chain remains largely overlooked. In this work, we expose a novel threat paradigm by introducing Mobius…

Read at arXiv (research papers)

arXiv (research papers) Tejasvi C. Addagada SI

Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B

Deploying large language models in financial-services and agentic settings requires safety classifiers that simultaneously handle prompt injection, regulatory compliance, and general harm, a combination no existing open guardrail addresses in a single inference pass. Semalith v1.4 is a 184M-parameter DeBERTa-v3-base classifier performing simultaneous three-axis safety classification including prompt injection, general harm, and financial-services regulatory compliance, in a…

Read at arXiv (research papers)

CSIS Asia Maritime Transparency Initiative Aristyo Rizka Darmawan South China Sea

How Indonesia Can Legally Increase Revenue from the Malacca Strait

Key takeaways Under international law, Indonesia has the obligation to ensure transit passage in the Malacca Strait; imposing a fee on vessels passing through the strait is illegal. However, Indonesia can maximize its strategic location by improving port infrastructure for maritime services, including bunker supply, ship-to-ship transfers, underwater hull cleaning, and crew services, which currently

Read at CSIS Asia Maritime Transparency Initiative

arXiv (research papers) Xiaohang Yu SI

SUDP: Secret-Use Delegation Protocol for Agentic Systems

Agentic systems now act with user secrets for APIs, messaging platforms, and cloud services. Today's agent runtimes typically implement authorization by exposure: enabling action means placing a reusable secret, or a reusable artifact derived from it, inside the runtime, so a transient prompt-injection or tool-side compromise becomes durable account compromise. Existing defenses cover adjacent pieces such as secret storage, scoped delegation, sender-constrained tokens, and…

Read at arXiv (research papers)

arXiv (research papers) Alfredo Metere SI

enclawed: A Configurable, Sector-Neutral Hardening Framework for Single-User AI Assistant Gateways

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 tamper-evident audit trail -- typically regulated industries (financial services, healthcare, defense, government). The framework ships in two flavors: an open flavor preserving OpenClaw compatibility while emitting audit, classification, and…

Read at arXiv (research papers)

OWASP GenAI Security Project Helen Oakley and Venkata (Sai) Kishore Modalavalasa Security

FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project

FinBot is a hands-on companion to the OWASP GenAI Security Project, offering an interactive Capture-The-Flag environment built around a simulated financial services application. Designed as the 'Juice Shop for the Agentic AI', it lets builders and defenders explore agentic risks in a live, multi-agent system with real tool access.

Read at OWASP GenAI Security Project

Journal articles (OpenAlex) Pasquale Giacobbe, Andrea Mosca, Patrizia Ordine et al. · European Journal of Political Economy Geopolitics

Help-seeking after gender-based violence: The role of local female political representation

Using data from Italy’s largest network of anti-violence centers (AVCs), this study investigates whether increased female representation in local politics affects women’s access to formal support services after experiencing gender-based violence. We focus on access to AVCs, as it represents a concrete step and a potential turning point toward escaping violence–distinct from more informal or exploratory forms of help-seeking. Exploiting staggered elections and the…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Max Haiven · Distinktion Journal of Social Theory Geopolitics

The speculative imagination within, against and beyond Amazon: the Worker as Futurist project in an increasingly fascist context

Amazon, which might be said to emblematize the Silicon Valley ethos of mobilizing massive capital to ‘disrupt’ capitalist industries and everyday life, is today among the world’s largest employers, retailers and providers of cloud computing services. But the firm was in no small part built through science and speculative fiction, not only as a genre of entertainment it sells, but as a set of ideas, narratives, tropes and ideologies that have facilitated its internal and…

Read at Journal articles (OpenAlex)

arXiv (research papers) Duanyi Yao SI

Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models

Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this recommendation-seeking behavior to inject unauthorized advertisements. Unlike traditional pattern-triggered backdoors that rely on artificial triggers such as pixel patches or special tokens, Hidden Ads activates on natural user behaviors: when users…

Read at arXiv (research papers)

arXiv (research papers) Haoyu Wang SI

SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants

LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the potential of locally deployed agents integrated with personal data and services, but this autonomy introduces significant safety and security risks. Unintended actions from LLM reasoning failures can cause irreversible harm, while prompt injection attacks may exfiltrate credentials or compromise the…

Read at arXiv (research papers)

arXiv (research papers) Charoes Huang SI

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning

The Model Context Protocol (MCP) has rapidly emerged as a universal standard for connecting AI assistants to external tools and data sources. While MCP simplifies integration between AI applications and various services, it introduces significant security vulnerabilities, particularly on the client side. In this work we conduct threat modelings of MCP implementations using STRIDE (Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, Elevation of…

Read at arXiv (research papers)

arXiv (research papers) Reshabh K Sharma SI

Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slices

AI agents increasingly execute users' natural-language (NL) tasks by calling Web services, yet today's Web authorizes these calls through OAuth, which grants permissions over operators (e.g., TRANSFER), not operations (operator plus operands, e.g., transfer $100 to Bob). This gap cannot be closed by refining scope granularity, because operands are combinatorial, quantitative, and often derived from runtime computations across servers. Operator-scoped authorization therefore…

Read at arXiv (research papers)

arXiv (research papers) Frank Li SI

OpenClaw PRISM: A Zero-Fork, Defense-in-Depth Runtime Security Layer for Tool-Augmented LLM Agents

Tool-augmented LLM agents introduce security risks that extend beyond user-input filtering, including indirect prompt injection through fetched content, unsafe tool execution, credential leakage, and tampering with local control files. We present OpenClaw PRISM, a zero-fork runtime security layer for OpenClaw-based agent gateways. PRISM combines an in-process plugin with optional sidecar services and distributes enforcement across ten lifecycle hooks spanning message…

Read at arXiv (research papers)

Older stories