Results for “own”

Journal articles (OpenAlex) Khanullah Mohammady · Journal of Financial Economic Policy Geopolitics

Determinants of financial inclusion in Afghanistan: a micro-level probit analysis

Purpose The purpose of this study is to analyse the socio-demographic and economic determinants of financial inclusion (FI) in Afghanistan. Design/methodology/approach The study uses the Global Findex data 2021 and probit regression models to analyse determinants of various FI indicators and barriers. Findings The results reveal low levels of formal FI in Afghanistan. Account ownership is limited, and formal saving and borrowing are almost absent. In case of emergency…

Read at Journal articles (OpenAlex)

Simon Willison SI

Prompt Injection as Role Confusion

Prompt Injection as Role Confusion First, I absolutely love this: This is a blog-style writeup of the paper. I wish every paper would come with one of these. Academic writing is pretty dry - the impact of a paper can be so much higher if you publish a readable version to accompany the formal one. Charles Ye, Jasmine Cui, and Dylan Hadfield-Menell present some fascinating research into the challenge of having models distinguish their own privileged text (here wrapped in role…

Read at Simon Willison

arXiv (research papers) Yanhang Li SI

When AUC 0.998 Is Not Enough: A Candidate Evaluation Protocol for Hidden-State Probes of Indirect Prompt Injection in Multimodal Computer-Use Agents

Hidden-state probing -- a linear classifier on a frozen vision-language model's internal activations -- has emerged as an attractive evaluation tool for flagging indirect prompt injection (IPI) in multimodal computer-use agents before the agent emits a corrupted action. We argue, on a single-backbone cautionary case study (Qwen2.5-VL-7B on Mind2Web, teacher-forced replay), that a high probing AUC on a clean-vs-attack split is not, on its own, evidence of malicious-content…

Read at arXiv (research papers)

The Guardian Vietnam Associated Press

Vietnam police rescue hundreds of cats stolen for meat by crime ring

Major operation launched after spate of pet thefts in Ho Chi Minh City, according to local media Police in Vietnam have rescued more than 400 cats in a bust of a cat meat crime ring in Ho Chi Minh City, according to animal welfare groups and local media reports. More than 40 cats were reunited with their owners after the multiday operation last week, but several dozen of those rescued have died due to the harsh conditions in which they were found, the groups said.

Read at The Guardian Vietnam

Journal articles (OpenAlex) Shan Huang · Humanities and Social Sciences Communications Geopolitics

The formation and transformation of modern China’s industrial and social structures and the logic of sinified Marxism

This study examines the formation and transformation of contemporary China’s industrial and social structures, particularly the changes induced by economic reforms since 1978. It explores the government’s use of Sinified Marxism to legitimise these structural changes. The paper critically reviews state-led development strategies during the socialist industrialisation phase in the 1950s, with a specific focus on the establishment of state-owned enterprises (SOEs) during the…

Read at Journal articles (OpenAlex)

Journal of Democracy Geopolitics

The Future of Multiracial Democracy

Immigration to the West has long been soaring, as growing numbers of people flee hunger, poverty, and war. This surge of migrants has taken a toll on the democracies they wish to call home, many of which are struggling to serve even their own citizens. Source

Read at Journal of Democracy

Journal articles (OpenAlex) Martin J. Conyon, Lerong He · Review of Corporate Finance Geopolitics

Communist party organizations in Chinese firms

The defining feature of corporate governance in China is political control. Control is exercised by Chinese Communist Party (CCP) organizations inside firms. It is political authority, not equity ownership per se, that constrains decisions. We review post-2015 legal changes, including the 2023 Company Law, on CCP presence in firms, and analyze a corpus of ∼3,000 corporate charters for the 100 largest listed firms (2010–2025). Using a reproducible machine-based…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Tadeáš Vala, Jakub Zbytovsky · Studies in Conflict and Terrorism Geopolitics

Jihadism and Counter-Terrorism Strategy in African Countries

After the military defeat of the Islamic State (IS) in the Middle East, the primary activity of this terrorist organization has shifted to African countries. Similar to al-Qaeda, from which it originally emerged, IS has in recent years aimed at establishing cooperation or incorporating African Islamist extremist movements under its own brand. Currently, the majority of originally insurgent Islamist movements in Africa (at least formally) fall under the franchise of either of…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Marko Lehti, Henna-Riikka Pennanen · Global Change Peace & Security Geopolitics

Multilateral global governance and peace from the perspectives of agonistic and Confucian relationality: China, BRICS, and the ASEAN Regional Forum

To address the pluralising dynamics of global governance, this study engages with a plurality of perspectives. A plurality of perspectives can be engaged in knowledge production on two levels. First, multiple perspectives in international relations studies are applied to transcend the narrow ontological, epistemological, and normative underpinnings of one’s own go-to-perspectives. And second, different perspectives of political actors are chosen as one’s objects of study in…

Read at Journal articles (OpenAlex)

The Conversation Michelle Grattan, Professorial Fellow, University of Canberra Geopolitics

View from The Hill: Ed Husic stirs pot on AUKUS as Peter Garrett to lead public inquiry

The controversial AUKUS pact continues to cause headaches for the government - even within its own ranks.

Read at The Conversation

Journal articles (OpenAlex) Luka Babic, Lorena Popović · Europe Asia Studies Geopolitics

Migration and Non-National Identity Building in Socialist Yugoslavia: The Case of Croatian Istria (1945–1991)

This essay examines two forms of non-national identity, ‘Istrianity’ and ‘Yugoslavism’, in socialist Yugoslavia. It argues that internal Yugoslav migration to Istria played a crucial role in shaping and establishing these two, intertwined, alternatives to national identity. The presence of Yugoslav migrants, their ‘otherness’, heightened the local population’s awareness of their own ‘Istrianity’. The essay highlights the historical, cultural and demographic changes in Istria…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yaoyu Zhao SI

LACUNA: Safe Agents as Recursive Program Holes

LLM agents increasingly act by writing code, yet a split persists between the runtime that drives the agent and the code the model writes. The runtime owns the loop, context, and control flow, and the model has little say over any of them. Letting model-written code shape the runtime itself would make agents more expressive, but it would also sharpen safety problems. A model can be diverted by a prompt injection, call the wrong tool, or fail partway and leave an inconsistent…

Read at arXiv (research papers)

Simon Willison SI

Microsoft Copilot Cowork Exfiltrates Files

Microsoft Copilot Cowork Exfiltrates Files The biggest challenge in designing agentic systems continues to be preventing them from enabling attackers to exfiltrate data. In this case Microsoft Copilot Cowork (yes, that's a real product name) was allowing agents to send emails to the user's own inbox without approval... but those messages were then displayed in a way that could leak data to an attacker via rendered images: Because these messages can contain external images…

Read at Simon Willison

arXiv (research papers) Narek Maloyan SI

Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents

Always-on AI agents (OpenClaw, Hermes Agent) run as a single persistent process under the owner's identity, folding messaging, memory, self-authored skills, scheduling, and shell into one authority boundary. This configuration opens what we call \emph{sleeper channels}: an untrusted input to one surface persists as a memory, skill, scheduled job, or filesystem patch, then fires later through a different surface with no attacker present. Two independent axes define the class…

Read at arXiv (research papers)

arXiv (research papers) Ying Li SI

No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills

LLM-powered agents can silently delete documents, leak credentials, or transfer funds on a routine user request, not because the agent was attacked, but because the skill it invoked broke its own declared safety rules. We call these specification violations: benign inputs cause a skill to breach the natural-language guardrails in its own specification, typically because the guardrail's semantics are undefined for autonomous execution, or because the implementation silently…

Read at arXiv (research papers)

Journal articles (OpenAlex) Gesa Witt, Amelie Bernzen · Geoforum Geopolitics

Solving space-related conflicts through degrowth approaches? Navigating tourism-driven housing challenges on the East Frisian islands

The East Frisian islands in Northern Germany are a major coastal tourism destination, with visitor numbers peaking during European spring and summer holidays. They are also popular among second home-owners, many of whom rent out their properties as holiday apartments. The islands’ economies are thus heavily reliant on income generated through the tourism industry. Related challenges such as a shortage of skilled labour and affordable, employer-independent accommodation…

Read at Journal articles (OpenAlex)

Journal of Democracy Jacob Mchangama, Jeff Kosseff Geopolitics

How Hate-Speech Laws Crush Dissent Everywhere

When democracies pass laws against hate speech and extremism, they are giving autocrats the cover they need for their own crackdowns. We shouldn’t let democratic norms become a blueprint for repression. Source

Read at Journal of Democracy

arXiv (research papers) Mingshuo Liu SI

PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization

Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style personally identifiable information (PII) from public pages. Many prior defenses are deployed at the model, service, or agent layer rather than at the webpage itself, leaving ordinary page owners with limited deployable options. We present PIIGuard, a webpage-level defense that repurposes indirect prompt injection as a protective…

Read at arXiv (research papers)

Journal articles (OpenAlex) Claudia Beatriz Murray, Luis Vergara, José María Zingoni et al. · Housing Policy Debate Geopolitics

Translating Community Land Trusts: Institutional Barriers and Stakeholder Sense-Making in Argentina and Chile

This paper investigates the potential for community land trust (CLT) adoption in two Latin American contexts: Bahía Blanca, Argentina, and Temuco, Chile, where housing systems are shaped by neoliberal legacies, legal centralism, and cultural attachments to individual ownership. Drawing on two multi-stakeholder focus groups where participants were largely unfamiliar with the CLT model, the findings capture a crucial early stage of sense-making in which stakeholders interpret…

Read at Journal articles (OpenAlex)

arXiv (research papers) Soheil Khodayari SI

Indirect Prompt Injection in the Wild: An Empirical Study of Prevalence, Techniques, and Objectives

As LLMs are increasingly integrated into systems that browse, retrieve, summarize, and act on web content, webpages have become an untrusted input vector for downstream model behavior. This enables site owners, contributors, and adversaries to embed instructions directly in web resources, i.e., indirect prompt injections. While prior work demonstrates such attacks in controlled settings, their prevalence, deployment, and real-world impact remain unclear. We present one of…

Read at arXiv (research papers)

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)

Journal of Democracy Mohammad Ali Kadivar Geopolitics

Why the Iranian Regime Owns the Streets

The progovernment rallies that crowd Iran’s streets are no accident. They are a critical and underappreciated pillar of the regime’s strength, and they are shaping Iran’s response to the war. Source

Read at Journal of Democracy

arXiv (research papers) Jiaqi Li SI

Poster: ClawdGo: Endogenous Security Awareness Training for Autonomous AI Agents

Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat judgement entirely untrained. We present ClawdGo, a framework for endogenous security awareness training: we teach the agent to recognise and reason about threats from the inside, at inference time, with no model modification. Four…

Read at arXiv (research papers)

arXiv (research papers) Dongcheng Zhang SI

Owner-Harm: A Missing Threat Model for AI Agent Safety

Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own deployers. Real-world incidents illustrate the gap: Slack AI credential exfiltration (Aug 2024), Microsoft 365 Copilot calendar-injection leaks (Jan 2024), and a Meta agent unauthorized forum post exposing operational data (Mar 2026). We propose…

Read at arXiv (research papers)

arXiv (research papers) İpek Abasıkeleş Turgut SI

Evaluating a Layered Prompt-Injection Defence for the Model Context Protocol: A Record-Level Audit of Decision Conventions, Corpus Provenance and Reproducibility

The Model Context Protocol (MCP) extends the prompt-injection attack surface of large language model applications to tool descriptions, parameter schemas and tool outputs. Defences for it report detection figures that are not comparable, because each is measured on its authors' own corpus under a decision convention that is rarely stated. This paper audits one such evaluation at the level of individual decision records. Its object is CASCADE, a fully local layered defence…

Read at arXiv (research papers)

Rappler Bea Cupin South China Sea

PH defense dept: China to blame for damage to its own reputation

'Transparency is abhorred by those who twist the truth and manipulate narratives to legitimize their unlawful acts and baseless claims,' says DND spokesperson Assistant Secretary Arsenio Andolong

Read at Rappler

arXiv (research papers) Saikat Maiti SI

Caging the Agents: A Zero Trust Security Architecture for Autonomous AI in Healthcare

Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research demonstrates that these agents exhibit critical vulnerabilities in realistic settings: unauthorized compliance with non-owner instructions, sensitive information disclosure, identity spoofing, cross-agent propagation of unsafe practices, and indirect…

Read at arXiv (research papers)

Latinoamérica21 Inés Amézaga Feijoo Geopolitics

Democracy and Disorder

In a world that is reorganizing itself beyond the bounds of rules and oversight, democracies face the urgent challenge of resisting the advance of authoritarian leadership without renouncing their own limits. O post Democracy and Disorder apareceu primeiro em Latinoamérica 21.

Read at Latinoamérica21

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)

Older stories