Results for “App”

Journal articles (OpenAlex) Jacob Oppong Nkansah · Higher Education Evaluation and Development Geopolitics

Choosing Hong Kong: African doctoral students and the multipolar dynamics of 21st century global higher education

Purpose As global higher education shifts toward a multipolar framework, Hong Kong's appeal to international scholars is growing. However, the evolving factors influencing the increasing presence of African doctoral students remain underexplored. This study investigates the drivers behind this trend, contributing theoretically to the literature on academic mobility by offering a nuanced understanding of migration dynamics within emerging education hubs. The findings provide…

Read at Journal articles (OpenAlex)

Rappler Reuters South China Sea

Philippines takes exception to China embassy comment on job losses

'We take strong exception to the embassy's tone, which appears to imply that such cooperation could be withheld as a form of leverage or retaliation,' the Department of Foreign Affairs says

Read at Rappler

The Guardian Socialism Guardian Staff

Social inequality is thriving in the hive | Brief letters

Beehive socialism | Ratcliffe’s apology | Tommy Cooper’s dream | Valentine’s Day | Love boat The beehive may not be quite the utopian dream it first appears to be (Letters, 9 February). Worker bees need to be so active during the summer months that they typically only survive for about four to six weeks. Drone bees’ longevity is not much better. The lucky ones may get to service the queen, but die as a consequence. Unsurprisingly, the queen fares much better. Tom Challenor…

Read at The Guardian Socialism

arXiv (research papers) Aashish Kolluri SI

Optimizing Agent Planning for Security and Autonomy

Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe actions by enforcing confidentiality and integrity policies, but currently appear costly: they reduce task completion rates and increase token usage compared to probabilistic defenses. We argue that existing evaluations miss a key benefit of system-level defenses: reduced reliance on human oversight…

Read at arXiv (research papers)

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)

arXiv (research papers) Zhenhua Zou SI

Blind Gods and Broken Screens: Architecting a Secure, Intent-Centric Mobile Agent Operating System

The evolution of Large Language Models (LLMs) has shifted mobile computing from App-centric interactions to system-level autonomous agents. Current implementations predominantly rely on a "Screen-as-Interface" paradigm, which inherits structural vulnerabilities and conflicts with the mobile ecosystem's economic foundations. In this paper, we conduct a systematic security analysis of state-of-the-art mobile agents using Doubao Mobile Assistant as a representative case. We…

Read at arXiv (research papers)

The Guardian Communism Ajit Niranjan in Ploiești

‘The trend is irreversible’: has Romania shattered the link between economic growth and high emissions?

Emissions have plunged 75% since communist times in the birthplace of big oil – but for some the transition has been brutal Once the frozen fields outside Bucharest have thawed, workers will assemble the largest solar farm in Europe: one million photovoltaic panels backed by batteries to power homes after sunset. But the 760MW project in southern Romania will not hold the title for long. In the north-west, authorities have approved a bigger plant that will boast a capacity…

Read at The Guardian Communism

arXiv (research papers) Qianli Wang SI

When Skills Lie: Hidden-Comment Injection in LLM Agents

LLM agents often rely on Skills to describe available tools and recommended procedures. We study a hidden-comment prompt injection risk in this documentation layer: when a Markdown Skill is rendered to HTML, HTML comment blocks can become invisible to human reviewers, yet the raw text may still be supplied verbatim to the model. In experiments, we find that DeepSeek-V3.2 and GLM-4.5-Air can be influenced by malicious instructions embedded in a hidden comment appended to an…

Read at arXiv (research papers)

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)

arXiv (research papers) Zhuoheng Li SI

Extended to Reality: Prompt Injection in 3D Environments

Multimodal large language models (MLLMs) have advanced the capabilities to interpret and act on visual input in 3D environments, empowering diverse applications such as robotics and situated conversational agents. When MLLMs reason over camera-captured views of the physical world, a new attack surface emerges: an attacker can place text-bearing physical objects in the environment to override MLLMs' intended task. While prior work has studied prompt injection in the text…

Read at arXiv (research papers)

Journal articles (OpenAlex) Ilda Nadia Monica de la Asunción Pari-Bedoya · Frontiers in Political Science Geopolitics

The securitization of the Peruvian-Chilean border and the criminalization of the migrant in the discourse of Sin Fronteras (Tacna, Peru)

This article analyzes the journalistic discourse of the Tacna-based newspaper Sin Fronteras during the migration situation on the Peruvian-Chilean border between February and May 2023. Through a qualitative approach based on Critical Discourse Analysis of 139 press articles, the research examines the linguistic and narrative mechanisms used to construct the figure of the migrant. The results reveal the predominance of a securitization and criminalization frame that presents…

Read at Journal articles (OpenAlex)

Inquirer Global Nation dlejano South China Sea

China-PH ‘word war’ may delay South China Sea code – Tulfo

MANILA, Philippines – Senate Committee on Foreign Relations chairman Sen. Erwin Tulfo on Wednesday said the escalation of exchanges between the Chinese Embassy and Philippine officials may delay the approval of the South China Sea Code of Conduct. Following a meeting with Department of Foreign Affairs (DFA) Secretary Theresa Lazaro, Tulfo said the agency had

Read at Inquirer Global Nation

arXiv (research papers) Xilong Wang SI

WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents

Prompt injection attacks manipulate webpage content to cause web agents to execute attacker-specified tasks instead of the user's intended ones. Existing methods for detecting and localizing such attacks achieve limited effectiveness, as their underlying assumptions often do not hold in the web-agent setting. In this work, we propose WebSentinel, a two-step approach for detecting and localizing prompt injection attacks in webpages. Given a webpage, Step I extracts…

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)

arXiv (research papers) Alsharif Abuadbba SI

Human Society-Inspired Approaches to Agentic AI Security: The 4C Framework

AI is moving from domain-specific autonomy in closed, predictable settings to large-language-model-driven agents that plan and act in open, cross-organizational environments. As a result, the cybersecurity risk landscape is changing in fundamental ways. Agentic AI systems can plan, act, collaborate, and persist over time, functioning as participants in complex socio-technical ecosystems rather than as isolated software components. Although recent work has strengthened…

Read at arXiv (research papers)

arXiv (research papers) Poushali Sengupta SI

Context Dependence and Reliability in Autoregressive Language Models

Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which context elements actually influence the output, as standard explanation methods struggle with redundancy and overlapping context. Minor changes in input can lead to unpredictable shifts in attribution scores, undermining interpretability and…

Read at arXiv (research papers)

Journal articles (OpenAlex) Dominic Hewson · Journal of Political Power Geopolitics

Power and the pandemic: how contrasting COVID-19 responses in the United Kingdom, China and Vietnam reveal alternatives to neoliberal biopolitics

This paper documents and examines the efforts of the UK government to manage COVID-19. Arguing that these efforts were influenced by commitments to neoliberal biopolitics and governmental strategies of control, it draws from a range of sources to contrast the UK response with alternative aspirations and applications of power in Vietnam and China. Findings highlight the social and political nature of the pandemic, illustrating how different values and strategies generated…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Jinwon Lee, Jaeseok Cho, Moonyoung Kim · Journal of East Asian Studies South China Sea

Buying Silence: Maritime Disputes in the South China Sea and Chinese Aid Allocation Patterns for Target Countries

Abstract How does China strategically allocate foreign aid to increase its influence on South China Sea disputes? We posit that China uses foreign aid as a tool of strategic appeasement to manage militarized interstate disputes, particularly targeting claimant states with smaller winning coalitions that are more susceptible to aid influence. The results of our empirical analysis show that China is more likely to allocate aid to the ASEAN SCS claimants with a smaller winning…

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)

arXiv (research papers) Jarrod Barnes SI

OpenSec: Measuring Incident Response Agent Calibration Under Adversarial Evidence

As large language models (LLMs) improve, so do their offensive applications: frontier agents now generate working exploits for under $50 in compute (Heelan, 2026). Defensive incident response (IR) agents must keep pace, but existing benchmarks conflate action execution with correct execution, hiding calibration failures when agents process adversarial evidence. We introduce OpenSec, a dual-control reinforcement learning (RL) environment that evaluates IR agents under…

Read at arXiv (research papers)

Journal articles (OpenAlex) Jon Truby, Andrew Mazen Dahdal, Rafael Dean Brown et al. · Research in Globalization Geopolitics

Diplomacy in the age of AI: Legal and strategic approaches to techno-nationalism, regulatory soft power and the AI chips race

This article explores how the Artificial Intelligence (AI) race has intensified global com- petition but also created avenues for international cooperation and developments in inter- national law. The study refines the concept of ‘Tech Diplomacy’ and introduces a novel definition of ‘AI Diplomacy’ as distinguished from ‘AI Statehood’ and ‘AI Sovereignty’. The examination concludes by identifying how ‘AI Diplomacy’ through governance and capacity-building can become a tool…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Kieran E. James, Henry D. Tuidraki, Sheikh Ali Tanzil · Frontiers in Sports and Active Living Geopolitics

Benevolent paternalism and player transition in Fiji soccer: insights from the Global South

Introduction: Because Fiji is a relatively poor and remote Global South developing country, it is plagued by poor infrastructure, financial problems, and a lack of trained experts who also can relate to athletes in a culturally appropriate manner. In this article, we compare Global North coaching practices with traditional practices in Fiji, which are based mostly on benevolent paternalism and cultural hegemony. A specific focus is the transition of athletes into retirement…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) YEPRYNTSEV Pylyp, Nikitin Anatoly, Maksym Maksimentsev et al. · Journal of Drug and Alcohol Research Geopolitics

Administrative and criminal law analysis of countering cybercrimes in the field of illicit drug trafficking at the regional and local levels

Aim: The purpose of this article is to reveal the administrative, legal, and criminal law analysis of countering cybercrime in the field of illegal drug trafficking at the regional and local levels. Methods: The methodological basis of the study is a set of general scientific, special legal and interdisciplinary approaches that provide a comprehensive analysis of counteraction to cybercrime in the field of illicit drug trafficking at the regional and local levels. The…

Read at Journal articles (OpenAlex)

arXiv (research papers) Andres Karjus SI

Machine-Assisted Grading of Nationwide School-Leaving Essay Exams with LLMs and Statistical NLP

Large language models (LLMs) enable rapid and consistent automated evaluation of open-ended exam responses, including dimensions of content and argumentation that have traditionally required human judgment. This is particularly important in cases where a large amount of exams need to be graded in a limited time frame, such as nation-wide graduation exams in various countries. Here, we examine the applicability of automated scoring on two large datasets of trial exam essays…

Read at arXiv (research papers)

arXiv (research papers) Jiani Liu SI

PINA: Prompt Injection Attack against Navigation Agents

Navigation agents powered by large language models (LLMs) convert natural language instructions into executable plans and actions. Compared to text-based applications, their security is far more critical: a successful prompt injection attack does not just alter outputs but can directly misguide physical navigation, leading to unsafe routes, mission failure, or real-world harm. Despite this high-stakes setting, the vulnerability of navigation agents to prompt injection…

Read at arXiv (research papers)

Journal articles (OpenAlex) Axel Bastián Poque González, Yunesky Masip Macía · Sustainability Geopolitics

Energy Justice, Critical Minerals, and the Geopolitical Metabolism of the Global Energy Transition: Insights from Copper Extraction in Chile and Peru

The global energy transition (ET) is widely portrayed as a technological shift toward low-carbon systems; however, it also entails profound geopolitical and socio-environmental transformations. While energy justice (EJ) has become a key framework for assessing fairness in energy systems, it seldom incorporates the geopolitical restructuring of material, energy, and economic flows that underpin contemporary transitions. This article develops a geopolitically informed approach…

Read at Journal articles (OpenAlex)

arXiv (research papers) Anirudh Sekar SI

Zero-Shot Embedding Drift Detection: A Lightweight Defense Against Prompt Injections in LLMs

Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversarial prompts exploit indirect input channels such as emails or user-generated content to circumvent alignment safeguards and induce harmful or unintended outputs. Despite advances in alignment, even state-of-the-art LLMs remain broadly vulnerable to adversarial prompts, underscoring the urgent need for robust, productive, and generalizable detection mechanisms beyond…

Read at arXiv (research papers)

Journal articles (OpenAlex) Shoji Azuma · International Journal of Arts Humanities & Social Science Geopolitics

Liberalism And Conservatism: Japanese Prime Minister Sanae Takaichi And Her Political Approach

In the contemporary political landscape, two major ideological approaches are commonly identified: liberalism and conservatism. Liberalism tends to be idealistic and equality-oriented, placing emphasis on freedom, human rights, and international cooperation and dialogue. Conservatism, by contrast, is more realistic and order-oriented, prioritizing national interest and security. Although it can sometimes become self-righteous, it generally maintains a pragmatic outlook and…

Read at Journal articles (OpenAlex)

arXiv (research papers) Aiman Al Masoud SI

SD-RAG: A Prompt-Injection-Resilient Framework for Selective Disclosure in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) has attracted significant attention due to its ability to combine the generative capabilities of Large Language Models (LLMs) with knowledge obtained through efficient retrieval mechanisms over large-scale data collections. Currently, the majority of existing approaches overlook the risks associated with exposing sensitive or access-controlled information directly to the generation model. Only a few approaches propose techniques to…

Read at arXiv (research papers)

Older stories