Results for “Across”

Journal articles (OpenAlex) Milica Kočović De Santo · Social Sciences & Humanities Open Geopolitics

Beyond performative decolonization: Epistemic justice in degrowth curricula

While universities across the Global North increasingly adopt decolonial rhetoric, most initiatives remain limited to what Ahmed (2012) calls “non-performative” diversity work, which obscures rather than challenges underlying power structures. This article moves beyond performative decolonization by examining how degrowth curricula operationalize authentic epistemic justice in university transformation. Through critical analysis of the Autonomous University of Barcelona MA…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Lillian Artz, Lisa Vetten, Harsha Gihwala et al. · Higher Education Research & Development Geopolitics

Gender-based violence in higher education institutions in Cuba and Mexico: A comparative analysis of awareness, institutional response, and policy gaps

This article explores gender-based violence (GBV) in ten higher education institutions (HEIs) across Cuba and Mexico. Drawing on a literature review and primary data, this paper examines how GBV is experienced, perceived, and addressed within academic environments in both countries. The high level findings show that – despite formal commitments to gender equality by both governments and HEIs – limited awareness of institutional procedures among both students and staff, and a…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Will Brehm, Palwasha Mirbacha, Mir Abdullah Miri · Comparative Education Review Geopolitics

Reverse Transitologies in Comparative Education: Pedagogies of Unbelonging Under the Taliban

This article presents empirical findings from 21 teachers’ experiences across Afghanistan during the first year following the Taliban’s return to power. It examines the transformations within the school system and their impact on the teaching profession, students, and learning environment. These changes are analyzed through three interrelated dimensions: unpredictability, inflexibility, and unknowable futures. Together, these dimensions inform the development of the concept…

Read at Journal articles (OpenAlex)

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)

arXiv (research papers) Indranil Halder SI

Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover

Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth observed without injection to exponential growth with the number of inference-time samples. We first identify a minimal statistical mechanism for these two regimes by giving a small set of assumptions on the distribution of safe generation across…

Read at arXiv (research papers)

Journal articles (OpenAlex) Jahangir Karami, Maziar Mozaffari Falarti · Central Asian Survey Geopolitics

Inter-regionalism and strategic adaptation in Central Asia: economic development and geopolitical resilience in a multipolar order

Central Asia’s fragmented regional landscape has long challenged traditional models of regionalism, constrained by Soviet legacies, sovereignty sensitivities and external rivalries. This article argues that inter-regionalism offers a more suitable framework for understanding cooperation in the region. Rather than seeking deep integration, inter-regionalism enables pragmatic, project-based collaboration across multiple organizations, including the Shanghai Cooperation…

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)

arXiv (research papers) Junchen Li SI

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG

Retrieval-Augmented Generation (RAG) systems are vulnerable to blocking attacks, in which poisoned documents cause large language models (LLMs) to refuse benign queries. Existing attacks rely on adversarial suffixes or explicit instructions, which are increasingly ineffective against modern LLMs, susceptible to prompt injection filtering, or require feedback from the target system. We observe overlapping risk categories and refusal criteria across safety-aligned LLMs, a…

Read at arXiv (research papers)

Journal of Democracy Alvaro Piaggio, Javier El-Hage, Malaak Jamal Geopolitics

Tracking Tyranny in an Age of Democratic Backsliding

The slide from democracy to authoritarianism is often subtle, gradual, and driven from within. The newly launched Tyranny Tracker is a sophisticated tool for classifying political regimes across the spectrum. Source

Read at Journal of Democracy

arXiv (research papers) Tian Zhang SI

AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification

Tool-augmented large language model (LLM) agents aggregate dialogue history, tool outputs, and retrieved content into an accumulated runtime state to complete multi-step tasks. This execution model exposes agents to indirect prompt injection (IPI) attacks, in which attacker-controlled instructions embedded in external artifacts enter the agent state and later influence tool use. Multi-turn IPI is especially challenging because injected content can persist across steps and…

Read at arXiv (research papers)

arXiv (research papers) Marcus Graves SI

Reverse CAPTCHA: Evaluating LLM Susceptibility to Invisible Unicode Instruction Injection

We introduce Reverse CAPTCHA, an evaluation framework that tests whether large language models follow invisible Unicode-encoded instructions embedded in otherwise normal-looking text. Unlike traditional CAPTCHAs that distinguish humans from machines, our benchmark exploits a capability gap: models can perceive Unicode control characters that are invisible to human readers. We evaluate five models from two providers across two encoding schemes (zero-width binary and Unicode…

Read at arXiv (research papers)

Asia Times Julian McBride South China Sea

China’s fishing fleets are Beijing’s secret naval weapon

China is rapidly expanding its reach across the Indo-Pacific, deploying a shadow fleet of nominally civilian fishing vessels as a covert extension of the world’s largest naval force. By weaponizing hundreds of thousands of fishing boats alongside the Chinese Navy (PLAN) and Coast Guard (CCG), Beijing has developed a gray zone militia strategy that threatens

Read at Asia Times

arXiv (research papers) Yanna Jiang SI

SoK: Agentic Skills -- Beyond Tool Use in LLM Agents

Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit applicability conditions, execution policies, termination criteria, and reusable interfaces. Unlike one-off plans or atomic tool calls, skills operate (and often do well) across tasks. This paper maps the skill layer across the full lifecycle…

Read at arXiv (research papers)

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)

Journal articles (OpenAlex) Imam Subkhan · Diaspora Studies Geopolitics

Techno-Nationalism and the Indonesian Scientific Diaspora in the United States

Abstract This article reimagines techno-nationalism by moving beyond its conventional state-centred framing to highlight the cultural practices of individuals, particularly the Indonesian scientific diaspora. Rather than treating technology merely as a communication tool, the study argues that technology possesses agency, shaping how diasporic scientists construct and sustain national identity across borders. By examining the everyday practices of the Indonesian scientific…

Read at Journal articles (OpenAlex)

arXiv (research papers) Emmanuel Bamidele SI

AMV-L: Lifecycle-Managed Agent Memory for Tail-Latency Control in Long-Running LLM Systems

Long-running LLM agents require persistent memory to preserve state across interactions, yet most deployed systems manage memory with age-based retention (e.g., TTL). While TTL bounds item lifetime, it does not bound the computational footprint of memory on the request path: as retained items accumulate, retrieval candidate sets and vector similarity scans can grow unpredictably, yielding heavy-tailed latency and unstable throughput. We present AMV-L (Adaptive Memory Value…

Read at arXiv (research papers)

Journal articles (OpenAlex) Karin Mayr‐Dorn, Gaia Narciso, Duc Anh Dang et al. · European Economic Review Geopolitics

Trade diversion and labor market adjustment: Vietnam and the U.S.-China trade war

This paper investigates the effects of the U.S.-China trade war on labor market outcomes in a third country, Vietnam. We exploit variation in the extent of U.S. tariff hikes on Chinese imports across industries as well as pre-existing industry employment patterns in Vietnam. We find that Vietnamese individuals and districts that are more exposed to the trade war experience higher employment and lower informal employment in traded industries. Our findings reveal that…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yu Yin SI

The Vulnerability of LLM Rankers to Prompt Injection Attacks

Large Language Models (LLMs) have emerged as powerful re-rankers. Recent research has however showed that simple prompt injections embedded within a candidate document (i.e., jailbreak prompt attacks) can significantly alter an LLM's ranking decisions. While this poses serious security risks to LLM-based ranking pipelines, the extent to which this vulnerability persists across diverse LLM families, architectures, and settings remains largely under-explored. In this paper, we…

Read at arXiv (research papers)

Asia Times Gabriel Honrada South China Sea

MQ-9 drones sharpen US eye on China’s Pacific moves

As the US spreads a dense web of MQ-9 Reapers across the Indo-Pacific to monitor China, it is making a high-stakes bet: that persistent drone surveillance will deter Chinese aggression—but these assets also risk exposing a critical vulnerability in America’s defense strategy if confronted by sophisticated adversaries. This month, the South China Morning Post (SCMP)

Read at Asia Times

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)

Journal articles (OpenAlex) Adnan Aslam · International Economics Geopolitics

Oil shock spillovers in emerging markets: Sectoral dynamics of demand, supply, and risk channels

s: This study investigates how disaggregated oil price shocks (demand, supply, and risk) propagate across emerging market equity sectors. Using quantile granger causality and time-varying parameter vector autoregression extended-joint connectedness frameworks, the analysis captures both dynamic interactions and responses during major turmoil including US-China trade tensions, COVID-19 pandemic, and Russia-Ukraine conflict. Results reveal strong nonlinear and…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Bertrand Marilier · Time & Society Geopolitics

Fashion as spatial disorder: German conservatism and the reordering of dress

From the Renaissance onward, German conservatism has defended space, a locus of stability, against the temporalization associated with Western European modernity. Attempts to map nations and occupations onto an atlas of changeless types were ultimately thwarted by social and technical change, and because it so easily spreads across classes and territories, fashion most readily registered this temporal erosion. But fashion simultaneously undermines and affirms timeless…

Read at Journal articles (OpenAlex)

arXiv (research papers) J Alex Corll SI

Peak + Accumulation: A Proxy-Level Scoring Formula for Multi-Turn LLM Attack Detection

Multi-turn prompt injection attacks distribute malicious intent across multiple conversation turns, exploiting the assumption that each turn is evaluated independently. While single-turn detection has been extensively studied, no published formula exists for aggregating per-turn pattern scores into a conversation-level risk score at the proxy layer -- without invoking an LLM. We identify a fundamental flaw in the intuitive weighted-average approach: it converges to the…

Read at arXiv (research papers)

Inter-American Dialogue Yifang Wang Geopolitics

From Production to Consumption: Japan–Latin America Cooperation in Food and Agriculture

This event on Tuesday March 3, 2026 from 9:00 AM to 12:00 PM ET co-organized by the Inter-American Dialogue’s Asia & Latin America Program and the Japan Association of Latin America and the Caribbean will examine opportunities for deeper Japan–LAC cooperation across food production, agricultural technology, supply chains, and food markets in light of evolving global conditions. It will also explore how these areas of cooperation can contribute to food security, supply chain…

Read at Inter-American Dialogue

arXiv (research papers) Mohan Rajagopalan SI

Protecting Context and Prompts: Deterministic Security for Non-Deterministic AI

Large Language Model (LLM) applications are vulnerable to prompt injection and context manipulation attacks that traditional security models cannot prevent. We introduce two novel primitives--authenticated prompts and authenticated context--that provide cryptographically verifiable provenance across LLM workflows. Authenticated prompts enable self-contained lineage verification, while authenticated context uses tamper-evident hash chains to ensure integrity of dynamic…

Read at arXiv (research papers)

Journal articles (OpenAlex) Bianca Fileborn, Charlotte Mertens, Stephen Robert Burrell · Gender and Education Geopolitics

Teaching on gender-based violence in higher education: critical reflections from criminologists on stolen land

Gender-based violence (GBV) remains a pervasive harm disproportionately affecting Indigenous women and marginalised communities in Australia and across the globe. Despite the centrality of GBV in criminological research, limited attention has been paid to how it is taught in higher education. This article reflects on our experiences teaching GBV within criminology in Australia and the UK, drawing on feminist, queer, intersectional and decolonial frameworks. We argue that…

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)

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)

Journal articles (OpenAlex) Jhon Valdiglesias, Derry Quintana · Frontiers in Political Science Geopolitics

Regulatory efficiency and economic growth: evidence from East Asia and Latin America

Introduction This study reassesses the relationship between regulatory efficiency and economic performance across Latin America and East Asia, aiming to determine whether differences in business entry regulations—measured by the number of days required to start a business—help explain the persistent growth divergence between the two regions. Methods We employ panel data regressions on a harmonized panel dataset, controlling for trade openness, inflation, investment, and…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Bama Andika Putra · Frontiers in Political Science South China Sea

Interpreting changes in the Philippines’ South China Sea policy: insights from the foreign and public policy literatures

The alterations in the Philippines’ South China Sea policies across different Philippine leaders are puzzling. The display of decisiveness against China identified in Aquino and Marcos’ terms was undermined under Duterte’s leadership by the downplaying of the arbitral tribunal’s significance, harsh rhetoric against the US, and a series of appeasement policies to maintain warm relations with China. Bridging the foreign and public policy literatures, this study argues for the…

Read at Journal articles (OpenAlex)

Older stories