Results for “Data”

Journal articles (OpenAlex) Ramazan Ahmadi, Suat Kolukırık · International Journal of Sociology and Social Policy Geopolitics

Poverty and social policies related to poverty in Afghanistan: a study on Hazaras in Bamyan

Purpose This research applies a sociological approach to analyze poverty in Bamyan, Afghanistan and seeks to understand its root causes, contributing factors, impacts and the possible interventions to eradicate poverty. Design/methodology/approach A mixed-methods approach – quantitative and qualitative methods were used to collect data through questionnaires, interviews and focus groups. The quantitative data were processed by descriptive analysis using SPSS for Pearson…

Read at Journal articles (OpenAlex)

arXiv (research papers) Ninghui Li SI

Security Considerations for Artificial Intelligence Agents

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by Perplexity's experience operating general-purpose agentic systems used by millions of users and thousands of enterprises in both controlled and open-world environments. Agent architectures change core assumptions around code-data separation…

Read at arXiv (research papers)

arXiv (research papers) J Alex Corll SI

The Mirror Design Pattern: Strict Data Geometry over Model Scale for Prompt Injection Detection

Prompt injection defenses are often framed as semantic understanding problems and delegated to increasingly large neural detectors. For the first screening layer, however, the requirements are different: the detector runs on every request and therefore must be fast, deterministic, non-promptable, and auditable. We introduce Mirror, a data-curation design pattern that organizes prompt injection corpora into matched positive and negative cells so that a classifier learns…

Read at arXiv (research papers)

arXiv (research papers) Chuan Guo Michael Pokorny SI

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

Instruction hierarchy (IH) defines how LLMs prioritize system, developer, user, and tool instructions under conflict, providing a concrete, trust-ordered policy for resolving instruction conflicts. IH is key to defending against jailbreaks, system prompt extractions, and agentic prompt injections. However, robust IH behavior is difficult to train: IH failures can be confounded with instruction-following failures, conflicts can be nuanced, and models can learn shortcuts such…

Read at arXiv (research papers)

arXiv (research papers) Nanzi Yang SI

Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance Vulnerabilities

The Model Context Protocol (MCP) is a recently proposed interoperability standard that unifies how AI agents connect with external tools and data sources. By defining a set of common client-server message exchange clauses, MCP replaces fragmented integrations with a standardized, plug-and-play framework. However, to be compatible with diverse AI agents, the MCP specification relaxes many behavioral constraints into optional clauses, leading to misuse-prone SDK…

Read at arXiv (research papers)

Journal articles (OpenAlex) Liguo Zhang, Pengcheng Wang, Rucheng Lu · Humanities and Social Sciences Communications Geopolitics

Can bilateral relations promote border construction? Evidence from China-Vietnam borders

Population flow, port trade, industrial agglomeration, network expansion, and security infrastructure, all underpinned by geopolitical cooperation, are reflected in the construction space evolution. Border construction expansion has become a central manifestation of the bilateral relationship development between the two countries. Using the GDELT database to develop a “bilateral augmentation-bilateral segmentation” system, this study measured the bilateral relationship…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Yi-Xuan Wu · International journal of law, crime and justice Geopolitics

Addressing challenges in investigating money laundering cases facilitated by underground banking across the Taiwan strait: The role of supervisory technology (SupTech)

This study investigates Taiwan's capacity to combat money laundering associated with cross-border underground banking, a persistent vulnerability in its AML/CFT framework. Despite a comprehensive legal foundation incorporating underground banking as a predicate offense under the Banking Act and the Money Laundering Control Act, enforcement remains constrained by fragmented data silos, limited manpower, and outdated investigative methods. Drawing on institutional analysis…

Read at Journal articles (OpenAlex)

Dialogue Earth (formerly Diálogo Chino) Leonardo Coelho Geopolitics

‘AI for whom?’ Inside Brazil’s data centre boom

The government’s legislative push for the sector is stalling, while experts warn of its socio-environmental risks and governance gaps

Read at Dialogue Earth (formerly Diálogo Chino)

Journal articles (OpenAlex) Dalina Amonhaemanon, Jarunee Wonglimpiyarat · foresight Geopolitics

Transforming financial inclusion through digital finance: comparative foresight from Thailand and Vietnam

Purpose This study aims to reconceptualize digital financial inclusion as a dynamic, converging and inclusive transition rather than a static measure of access. Using comparative foresight evidence from Thailand and Vietnam, it investigates how digital finance, human capital and policy frameworks coevolve in shaping sustainable financial ecosystems. By analyzing post-pandemic and post-recovery data, the study seeks to identify distinct diffusion pathways and structural…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Thomas Zeitzoff · Terrorism and Political Violence Geopolitics

Where’s the Sabotage? Repression, Recruitment, and Tactical Evolution in the U.S. Radical Environmental Movement

Why did the U.S. radical environmental movement shift away from tactics like arson and sabotage in the mid-2000s? And given the rising threat of climate change, why haven’t these more contentious tactics made a comeback? This puzzle is particularly significant to scholars of terrorism because radical environmental groups like the Earth Liberation Front appear in major terrorism databases, and faced heavy repression from the government, despite causing no fatalities. I argue…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Daniel Sloot, Kristin Limbach, Corinne Faure et al. · Cell Reports Sustainability Geopolitics

Public perceptions of energy security risks and energy transition support in France and Germany

The recent European energy crisis following the Russia-Ukraine war of 2022 has highlighted energy security risks and influenced public debates over the course of the sustainable energy transition. We investigate how public concerns over four dimensions of energy security risks (reliability of supply, import dependency, affordability, and environmental impact) are related to support for the energy transition in Germany and France. Our survey data ( n = 2,010 participants)…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Sebastián Edwards · Journal of Business Cycle Research Geopolitics

Networked Information and Industrial Output: Evidence from Chile’s 1972 Truckers’ Strike

Abstract This paper examines Cybersyn—Chile’s cybernetic coordination system under Salvador Allende—during the October 1972 national truckers’ strike, which cut aggregate industrial output by roughly 9%. Using monthly data for twenty sectors and a calibrated CES–Leontief model, I construct sector-specific counterfactuals for the trucking shock. The four government-designated priority sectors outperform their structural predictions by an average of 17 index points; the…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Joseph Ching Velasco · Journal of Current Southeast Asian Affairs South China Sea

Coercion and Restraint in the South China Sea: China's Differentiated Assertiveness towards the Philippines and Vietnam

China's behaviour in the South China Sea varies systematically among claimant states rather than unfolding uniformly. It often confronts the Philippines with coercive tactics but adopts greater restraint towards Vietnam. This article explains this patterned variation through a comparative framework that integrates realist and constructivist insights. Drawing on maritime incident data and elite-level interactions, it argues that China calibrates its use of coercion and…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Pedrona Serra Payeras, Susanna Soler Prat, Carlos Alexis Matus-Castillo et al. · Frontiers in Sports and Active Living Geopolitics

Student-athletes at risk: faculty voices on gender-based violence and the need for structural change in physical activity and sport sciences programs

Creating Gender-Based Violence (GBV) free environments remains a significant challenge in the fields of physical activity, sport, and higher education. This study examines the perceptions, experiences, and proposals of university teaching staff regarding GBV within a Physical Activity and Sport Sciences (PASS) programs. Three focus groups were conducted with 17 faculty members (eight women and nine men). Data was analyzed through a reflexive thematic analysis complemented by…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Nicolás Villarroel · Memory Studies Geopolitics

Remembering the Chilean solidarity campaign in Australia: Convivial and conflicting memories of activism

In this article, I analyse the memories of the Solidarity Campaign among Chilean exiles in Australia from a dialogical perspective. I argue that dialogic remembering involves taking a position and answering to other voices that populate a mnemonic field, and that the positions in this dialogue are shaped by sociohistorical contexts. I explore this by drawing on data from my research about the memory of the Chilean dictatorship among Chilean exiles in Australia, where I…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Maria Amjad, Mark Berlin, Sara Daub et al. · Journal of Peace Research Geopolitics

Commanders of the Mujahideen: introducing the Jihadist Leaders Dataset (JLD)

Abstract Recent research has explored how militant leaders' backgrounds shape their decision-making while in power. However, existing studies primarily focus on leaders of rebel groups participating in civil wars, overlooking smaller, yet lethal and influential, armed groups that operate outside civil war contexts. To address this gap, we introduce the Jihadist Leaders Dataset (JLD), which provides original, systematic data on the backgrounds and prewar experiences of 237…

Read at Journal articles (OpenAlex)

arXiv (research papers) Piyush Jaiswal SI

Analysis of LLMs Against Prompt Injection and Jailbreak Attacks

Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same time, LLMs are vulnerable to prompt-based attacks. Thus, analyzing this risk has become a critical security requirement. This work evaluates prompt-injection and jailbreak vulnerability using a large, manually curated dataset across…

Read at arXiv (research papers)

arXiv (research papers) Che Wang SI

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs

The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security vulnerabilities, particularly indirect prompt injection (IPI) attacks. Existing attack methods are limited by their reliance on static patterns and evaluation on simple language models, failing to address the fast-evolving nature of modern AI agents. We…

Read at arXiv (research papers)

arXiv (research papers) Zac Garby SI

The LLMbda Calculus: AI Agents, Conversations, and Information Flow

Large language models are increasingly deployed as agents: they plan, call tools, read untrusted data, and act on the results. This exposes them to prompt injection: data meant only to be read is obeyed as an instruction. The most principled defences replace content inspection with provenance: classifying data by source and keeping trusted and untrusted apart through a separation of duty (the dual-LLM pattern) and information-flow control. Yet the leading systems are hard to…

Read at arXiv (research papers)

arXiv (research papers) Lei Ba SI

CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets or simulated environments, failing to capture the security risks arising from dynamic code execution, tool interactions, and multi-turn context. To bridge this gap, we introduce CIBER, an automated benchmark that combines dynamic attack…

Read at arXiv (research papers)

Journal articles (OpenAlex) Tapiwa Patson Sisimayi, James Tauya Muperi, Sandra Vuyiswa · Feminist Encounters A Journal of Critical Studies in Culture and Politics Geopolitics

Barriers to women's political participation in Zimbabwe: Analysing structural challenges and pathways to gender equality between 2013 and 2023

The article examines barriers and challenges women face in active political participation within major political parties in Zimbabwe, focusing on the policies and mechanisms that inhibit their involvement while offering recommendations for improvement. Data was collected through interviews and focus groups with 20 purposively and conveniently sampled participants from Harare and Bulawayo, along with critical documentary analysis. The data was analysed methodically using…

Read at Journal articles (OpenAlex)

arXiv (research papers) Max Fomin SI

When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift

Detecting prompt injection, jailbreak attacks, and harmful requests is critical for deploying LLM-based agents safely, yet current evaluation practices in this literature overestimate generalization. We train activation-based classifiers (linear probes on LLM hidden states) on a benchmark of 18 datasets (prompt attacks plus benign sources) and propose Leave-One-Dataset-Out (LODO) evaluation, where the held-out dataset is never seen during training. Across four LLMs from…

Read at arXiv (research papers)

arXiv (research papers) Akshat Naik SI

OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage

As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a practical paradigm. Prior work has examined the safety and misuse risks associated with agents. However, much of this has focused on the single-agent case and/or setups missing basic engineering safeguards such as access control, revealing a scarcity of threat modeling in multi-agent systems. We investigate the security…

Read at arXiv (research papers)

Journal articles (OpenAlex) Shengjie Shi, Belen Chen, Ziyi Guang et al. · PLoS ONE Geopolitics

Mapping the evolution of cross-Strait relations via global news big data (2014–2023): An analysis integrating GDELT and machine learning

This study investigates global news media representations of cross-Strait relations from 2014 to 2023 using the GDELT database, framed within the mediatization of politics. Combining large-scale event data and computational text analysis, it offers a multi-level analysis of representational patterns, structural inequalities, and framing dynamics. Six indicators track longitudinal trends including four continuous indices and two event type distributions, show attention spikes…

Read at Journal articles (OpenAlex)

Embrace The Red Security

Scary Agent Skills: Hidden Unicode Instructions in Skills ...And How To Catch Them

There is a lot of talk about Skills recently, both in terms of capabilities and security concerns. However, so far I haven’t seen anyone bring up hidden prompt injection. So, I figured to demo a Skills supply chain backdoor that survives human review. Additionally, I also built a basic scanner, and had my agent propose updates to OpenClaw to catch such attacks. Attack Surface Skills introduce common threats, like prompt injection, supply chain attacks, RCE, data…

Read at Embrace The Red

arXiv (research papers) Ruoyao Wen SI

AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management

Indirect prompt injection threatens LLM agents by embedding malicious instructions in external content, enabling unauthorized actions and data theft. LLM agents maintain working memory through their context window, which stores interaction history for decision-making. Conventional agents indiscriminately accumulate all tool outputs and reasoning traces in this memory, creating two critical vulnerabilities: (1) injected instructions persist throughout the workflow, granting…

Read at arXiv (research papers)

Journal articles (OpenAlex) Kyle Atwell, David C. Logan · Journal of Conflict Resolution Geopolitics

Shadow Wars in the Shadow of the Bomb: The Link Between Nuclear Weapons and Indirect Conflict

How do nuclear weapons affect interstate conflict? Empirical studies on this question have returned mixed results. We argue that these results are due to overlooking indirect conflicts, a distinct and prominent form of limited conflict. Expanding current datasets to account for both conflict intensity and directness provides new insights about interstate conflict. We investigate the relationship between nuclear weapons and conflict through a large-n analysis that includes a…

Read at Journal articles (OpenAlex)

arXiv (research papers) Junhyeok Lee SI

MPIB: A Benchmark for Medical Prompt Injection Attacks and Clinical Safety in LLMs

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly integrated into clinical workflows. However, prompt injection attacks can steer these systems toward clinically unsafe or misleading outputs. We introduce the Medical Prompt Injection Benchmark (MPIB), a dataset-and-benchmark suite for evaluating clinical safety under both direct prompt injection and indirect, RAG-mediated injection across clinically grounded tasks. MPIB emphasizes…

Read at arXiv (research papers)

Journal articles (OpenAlex) Manuel R. Torres Soriano · Journal of Policing Intelligence and Counter Terrorism Geopolitics

Jihadist terrorists as early adopters: A critical examination of terrorist adoption of emerging internet technologies

The idea that jihadist groups are ‘early adopters’ of emerging internet technologies has shaped counterterrorism policies and public discourse. However, this assumption often relies on anecdotal evidence rather than systematic analysis. This study critically examines whether jihadist actors genuinely adopt digital platforms earlier than the general population or whether their behaviour aligns with broader technological trends. Using a dataset of all individuals arrested in…

Read at Journal articles (OpenAlex)

arXiv (research papers) Hao Li SI

AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?

AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes them to serious indirect prompt injection attacks, where malicious instructions embedded in third-party content hijack agent behaviors. To mitigate this threat, a growing number of defenses have been proposed and evaluated under existing agent security benchmarks. These benchmarks provide…

Read at arXiv (research papers)

Older stories