Results for “Data”

arXiv (research papers) Farzad Nourmohammadzadeh Motlagh SI

When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications

Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models (LLMs) that enable users to query data using conversational input rather than formal query languages such as SQL. While this paradigm significantly improves usability and accessibility, it introduces new security risks, particularly the amplification of SQL injection vulnerabilities through the prompt-to-SQL translation process. Malicious…

Read at arXiv (research papers)

arXiv (research papers) Ben Kereopa-Yorke SI

Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning

We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use protocols, causing incorrect conclusions through correct reasoning. Unlike prompt injection, Oracle Poisoning manipulates the data agents reason over, not their instructions. We demonstrate six attack scenarios against a production 42-million-node code knowledge graph, providing the first empirical demonstration of knowledge…

Read at arXiv (research papers)

arXiv (research papers) Ziwen Cai SI

When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks

Since the official release of ChatGPT in 2022, large language models (LLMs) have rapidly evolved from chatbot-style interfaces into agentic systems that can delegate work through tools and newly spawned subagents. While these capabilities improve automation and scalability, they also pose new security risks in multi-agent networks. Existing research has studied how individual LLM-based agents can be compromised through prompt injection, jailbreaking, poisoned retrieval data…

Read at arXiv (research papers)

Journal articles (OpenAlex) Mohammad Mohsin Saberi, Praveena Mungra · International Journal of Science and Research Archive Geopolitics

Mental Health and Well-being of Afghan Students in India: Stressors, Coping Strategies, and Support Needs

This study examines the mental health and well-being of Afghan students in India, focusing on the challenges they face as international students from a conflict-affected background. The study adopts a qualitative-dominant mixed-method approach, utilizing an interview-based questionnaire administered online to thirty Afghan students enrolled in various higher education institutions across India. The data were analyzed using thematic analysis, supported by descriptive…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Jason Gainous, Tricia J. Gray, Kevin M. Wagner · Frontiers in Political Science Geopolitics

Digital vs. state media in Cuba: counter-flows and support for normalizing US relations

Introduction This study examines how digital vs. state-controlled media consumption shapes support for normalizing US-Cuban relations in Cuba during the 2014 to 2016 thaw period. Methods Using individual-level data from a 2016 nationally representative NORC survey of Cuban citizens, we test three hypotheses concerning the effects of digital media consumption, state media consumption, and their interaction. Results Digital media consumption is positively associated with…

Read at Journal articles (OpenAlex)

arXiv (research papers) Krti Tallam SI

Authorization Propagation in Multi-Agent AI Systems: Identity Governance as Infrastructure

The security discussion around agentic AI focuses heavily on prompt injection. This paper argues that multi-agent systems also create a distinct authorization problem: maintaining authorization invariants as non-human principals retrieve data, delegate tasks, and synthesize results across changing boundaries. We call this problem authorization propagation. It is not reducible to prompt injection and is not fully addressed by classical access-control models such as RBAC…

Read at arXiv (research papers)

Atlantic Council Ignacio Albe, Enrique Millán-Mejía Geopolitics

How the Iran war is affecting Latin America and the Caribbean’s economic outlook

The data show how energy and commodity shortages are pushing inflation higher, tightening financial conditions, and slowing growth.

Read at Atlantic Council

arXiv (research papers) Wonbae Kim SI

SecureMCP: A Policy-Enforced LLM Data Access Framework for AIoT Systems via Model Context Protocol

The deployment of Large Language Model (LLM)-generated SQL queries in Artificial Intelligence of Things (AIoT) systems introduces critical security risks, as prompt injection attacks can manipulate LLMs into producing unauthorized queries that expose sensitive data or execute destructive operations. Existing NL2SQL research focuses on query accuracy, while MCP server implementations provide only SQL-level protections without fine-grained role-based access control. This paper…

Read at arXiv (research papers)

Journal articles (OpenAlex) Joonhyung Lee, Kang Keun Rhee · World Economy Geopolitics

The Impact of the US ‐China Trade War on Vietnam's US Exports

ABSTRACT This paper examines the unintended consequences of the 2018–2019 US‐China trade war for Vietnam, a key bystander economy, using quarterly HS 8‐digit US import data from 2017Q1 to 2020Q4. While the average treatment effect on Vietnam's exports to the US is small and statistically insignificant, substantial heterogeneity arises from pre‐war revealed comparative advantages (RCAs). Vietnam experienced markedly stronger export growth in sectors where China held high…

Read at Journal articles (OpenAlex)

CSIS Asia Maritime Transparency Initiative Bich Tran South China Sea

Strategic Imperatives for the Philippines’ Indigenous Space Capabilities

The Philippine Space Agency (PhilSA) is expected to launch the Multispectral Unit for Land Assessment (MULA) satellite in the final quarter of 2026. This will mark a significant milestone in the development of the country’s space program. The advancement of indigenous space capabilities will enable the Philippines to reduce its dependence on foreign satellite data

Read at CSIS Asia Maritime Transparency Initiative

arXiv (research papers) Yuyang Gong SI

LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training

Large language models are increasingly embedded into systems that interact with user data, retrieved web content, and external tools, creating a new attack surface: prompt injection, where malicious commands embedded in untrusted data override the trusted command and induce unintended behavior. Existing defenses mainly rely on fine-tuning the model to preserve an explicit boundary between trusted commands and the untrusted data portion, so that the model learns to prioritize…

Read at arXiv (research papers)

Journal articles (OpenAlex) Yang Chen, Jinglong Niu · Drones Geopolitics

Intelligent Unmanned Aerial Vehicle Swarm Control Under Electronic Warfare: A Cognitive–Intent Dual-Stream Reinforcement Learning Framework

Multi-unmanned aerial vehicle (UAV) platforms integrate radio-frequency (RF) sensing, datalinks, and onboard embedded compute; adversarial electronic warfare (EW) degrades these subsystems through jamming and forces decentralized control policies to act on fragmented observations—a setting aligned with intelligent electronic systems and autonomous robotics in contested spectrum. Cooperative swarms then face two compounding failure modes: loss of coherent situational…

Read at Journal articles (OpenAlex)

arXiv (research papers) Weifei Jin SI

CleanBase: Detecting Malicious Documents in RAG Knowledge Databases

Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks, in which an adversary inserts malicious documents containing carefully crafted injected prompts into the knowledge database. When a user issues a question targeted by the attack, the RAG system may retrieve these malicious documents, whose injected prompts mislead it into generating attacker-specified answers, thereby compromising the integrity of the RAG system. In this work, we propose…

Read at arXiv (research papers)

Journal articles (OpenAlex) Ya Tan, Peng Ma, Qingxin Lan et al. · World Economy Geopolitics

Does South–South Cooperation Deliver? The Economic Impacts of BRICS Plus Platform

ABSTRACT This study investigates whether South–South cooperation delivers tangible economic benefits by examining the impact of the BRICS Plus platform on the economic development of participating countries. Using national‐level panel data for 125 countries from 2009 to 2022 and applying a staggered Difference‐in‐Differences approach, we find that BRICS Plus participation is associated with an average annual GDP per capita growth rate increase of approximately 3.42% compared…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Vladimir Miroljub Cvetković, Dalibor Milenković, Jasmina Bašić et al. · Safety Geopolitics

Predictive Model of Community Disaster Resilience Across Serbia: A BRIC–DROP Composite Index and Spatial Patterns

Community disaster resilience is increasingly guiding risk-reduction investments, but in many Southeast European settings, comparable subnational data remain scarce. This study assesses perceived community disaster resilience across Serbia by combining BRIC–DROP dimensions into a single index and analyzing differences across hazard types and sociodemographic factors. A cross-sectional household survey was conducted using multistage random sampling and the “next birthday”…

Read at Journal articles (OpenAlex)

Global Voices Daria Dergacheva

The human cost of the data center push in Latin America

In this cross-border article, Global Voices is sharing stories from several countries in Latin America where communities are pushing back against AI-driven data center development.

Read at Global Voices

Journal articles (OpenAlex) Saheed Babajide Owonikoko · Small Wars and Insurgencies Geopolitics

From Boko Haram to Islamic State West Africa Province: the spread and consolidation of Salafi Jihadist influence in the Lake Chad region

The insurgent campaign in the Lake Chad Region is transforming, yet this transformation is not reflected in scholarship. Using contested space/competitive governance theories and a combination of primary and secondary data, this study examines how the shift from Boko Haram to the Islamic State West Africa Province (ISWAP) show the spread and consolidation of terrorism in the Lake Chad Region. It also shows the implication of the spread and consolidation for States in the…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Juan Ortiz Freuler · International journal of communication Geopolitics

Informational Sovereignty: The Commercial and Geopolitical Risk of Newsroom Dependency on Third-Party Infrastructure in Latin America

This article reveals significant market consolidation within the digital infrastructure of Latin American media. Extending the political economy of media literature from ownership to control over underlying infrastructure, it uses a newly constructed database of over 400 data points to analyze the online infrastructure of 18 media outlets across 6 Latin American countries, focusing on 11 key elements of the media stack. Findings indicate that dominant players, such as…

Read at Journal articles (OpenAlex)

arXiv (research papers) Tosin Adewumi SI

BatteryPass-12K: The First Dataset for the Novel Digital Battery Passport Conformance Task

We introduce a novel task of digital battery passport (DBP) conformance classification and introduce the first public benchmark for the task: BatteryPass-12K, created synthetically from real pilot samples. This is as the EU's battery regulation on DBPs comes into effect soon and there exists no public dataset. We evaluated 22 language models (LMs) in zero-shot inference, spanning small LMs (SLMs), mixture of experts (MoEs), and dense LLMs. We also conducted analysis…

Read at arXiv (research papers)

Journal articles (OpenAlex) Lorne L. Dawson, Garth James Davies, Emma Belton · Terrorism and Political Violence Geopolitics

The Crime-Terrorism Nexus and Jihadist Radicalization in the West: New Data and Interpretative Challenges

In 2016 Basra and Neumann proposed that the prevalence of criminal backgrounds amongst European jihadists is consequential for understanding who radicalizes, how and why. This idea was rapidly integrated into radicalization studies, but empirical research over the last decade reveals a more complex situation than commonly understood. This study provides a critical review and synthesis of the findings of newer empirical studies of this posited nexus and new data from the…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Scott L. Malcomson · International Affairs Geopolitics

On digital non-alignment

Abstract In a digital era, how are states aligning themselves in order to maximize digital prosperity while minimizing digital vulnerability? This article argues for ‘digital non-alignment’ as the best concept for understanding how states are addressing this question, using India as a case-study. Neo-realist International Relations (IR) theory and concepts that derive from it, such as digital sovereignty and even data imperialism, fall short in enabling a rich understanding…

Read at Journal articles (OpenAlex)

arXiv (research papers) Nay Myat Min SI

Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models

Large language models deployed at runtime can misbehave in ways that clean-data validation cannot anticipate: training-time backdoors lie dormant until triggered, jailbreaks subvert safety alignment, and prompt injections override the deployer's instructions. Existing runtime defenses address these threats one at a time and often assume a clean reference model, trigger knowledge, or editable weights, assumptions that rarely hold for opaque third-party artifacts. We introduce…

Read at arXiv (research papers)

arXiv (research papers) Zonghao Ying SI

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization

Large Language Model (LLM) agents are increasingly used to automate complex workflows, but integrating untrusted external data with privileged execution exposes them to severe security risks, particularly direct and indirect prompt injection. Existing defenses face significant challenges in balancing security with utility, often encountering a trade-off where rigorous protection leads to over-defense, or where subtle indirect injections bypass detection. Drawing inspiration…

Read at arXiv (research papers)

Journal articles (OpenAlex) Paul C. Hong, Cristiane Biazzin, Fernando Coelho Martins Ferreira · Latin American Policy Geopolitics

Evaluating the Brazil–China Trade Relationship: Navigating Economic Disparities, Divergent Objectives, and Strategic Influence in Latin American Logistics

ABSTRACT This study is guided by two research questions, what factors sustain the Brazil–China trade relationship and explain its strategic relevance within evolving geopolitical dynamics, and how can this relationship be systematically analyzed to inform understanding of emerging market partnerships. The study adopts a theory‐building approach and develops a conceptual framework grounded in interdependence theory, supported by trade data and institutional evidence. The…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yuandao Cai SI

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents

Autonomous Large Language Model (LLM) agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorized tool execution. Securing these systems requires effective information flow tracking. Yet, traditional taint analysis that is designed for program memory states fundamentally…

Read at arXiv (research papers)

Journal articles (OpenAlex) Thảo Hương Phan, Thao Viet Tran, Trang Mai Tran · Economies Geopolitics

Export Resilience in Vietnam: A Causal Machine Learning Approach Using Industry-Level Panel Data (2000–2024)

Vietnam’s exports expanded dramatically from $14.5 billion in 2000 to $405 billion in 2024, elevating the country to the world’s 22nd largest exporter despite persistent global shocks. This paper introduces the application of the Causal Machine Learning Approach to Resilience Estimation (CLARE) to industry-level trade analysis, utilizing a comprehensive panel of 97 HS2 sectors from 2000 to 2024 (2425 observations) drawn from UN COMTRADE and WITS databases. We implement…

Read at Journal articles (OpenAlex)

arXiv (research papers) Sahil Rajesh Dhayalkar SI

Overcoming the Impedance Mismatch: A Theoretical Roadmap for Fusing Foundation Models and Knowledge Graphs

Modern artificial intelligence remains fundamentally divided between the continuous, probabilistic spaces of Foundation Models and the discrete, deterministic structures of Knowledge Graphs. While Retrieval-Augmented Generation (RAG) attempts to connect them by serializing graph data into text, we argue this lexical bridging is merely a superficial patch. In this paper, we formalize the underlying structural and geometric friction as the \textit{Impedance Mismatch}. By…

Read at arXiv (research papers)

arXiv (research papers) Robert Sorab Stanley SI

An AI Agent Execution Environment to Safeguard User Data

AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data (e.g., personal and financial information). This poses a serious risk to security and privacy: an AI model may hallucinate or make mistakes, and adversaries may attack it (e.g., via prompt injection) to exfiltrate user data. This paper presents GAAP (Guaranteed Accounting for Agent Privacy), an execution environment for AI agents that…

Read at arXiv (research papers)

Older stories