Results for “App”

arXiv (research papers) Hengkai Ye SI

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation

Large language models (LLMs) increasingly rely on external tools to perform time-sensitive tasks and real-world actions. While tool integration expands LLM capabilities, it also introduces a new prompt-injection attack surface: tool poisoning attacks (TPAs). Attackers manipulate tool descriptions by embedding malicious instructions (explicit TPAs) or misleading claims (implicit TPAs) to influence model behavior and tool selection. Existing defenses mainly detect anomalous…

Read at arXiv (research papers)

Journal of Democracy Breza Race Maksimovic, Stefania Kapronczay Geopolitics

The Day After Hungary’s Pivotal Election

As Hungary approaches a crucial election, Viktor Orbán finds himself vulnerable. These are the three most likely post-election scenarios and how civil society must respond. Source

Read at Journal of Democracy

InSight Crime Alex Papadovassilakis

Did US Military Strikes Impact Caribbean Drug Trafficking?

Did US Military Strikes Impact Caribbean Drug Trafficking? The United States' military-first approach in the Caribbean have disrupted certain drug trafficking routes. But traffickers have already adapted and Venezuela remains important to the cocaine trade.

Read at InSight Crime

Journal articles (OpenAlex) Yichong Mi · Theoretical and Natural Science Geopolitics

Research on Applying a CRITIC-Based ARIMA Model to Predict the Number of Nuclear Weapons

Nuclear weapons are among the most destructive weapons and can swiftly devastate cities and even entire countries. Accordingly, analyzing the scale of nuclear arsenals is closely related to international security. Using nuclear-weapon data from multiple countries, This research formulates an Auto-regressive Integrated Moving Average (ARIMA) model and combines it with the CRITIC method to forecast how many countries may possess nuclear armaments in future times. To estimate…

Read at Journal articles (OpenAlex)

arXiv (research papers) Geert Trooskens XY.AI Labs, Palo Alto, CA SI

Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation

We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which workflows execute deterministically without further model invocation. This paradigm has antecedents in prior work on declarative pipeline optimization (DSPy) and hybrid neural-symbolic planning (LLM+P); our contribution is a systems-oriented study of its application to high-stakes enterprise workflows, with particular emphasis on…

Read at arXiv (research papers)

Journal articles (OpenAlex) Wagner Goncalves · Social Sciences & Humanities Open Geopolitics

Active non-alignment or pendular diplomacy? The Venezuela veto and Brazil's foreign policy contradictions

This article examines Brazil's veto of Venezuela's Brics membership application at the October 2024 Kazan Summit, representing the first veto in Brics history. Through a comprehensive analysis of diplomatic records, government statements, and institutional dynamics, this case study reveals how Brazil's decision exposed fundamental contradictions within its “active non-alignment” foreign-policy doctrine. The analysis demonstrates that Brazil's selective application of…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Eka Dyah Pramusinta, Putra Pamungkas, Siti Aisyah Tri Rahayu · Studies in Economics and Finance Geopolitics

Financial development, green energy security and income inequality: dynamic panel quantile regression approach

Purpose This paper examines the relationship between financial development, green energy security, and income inequality for emerging and developing economies. Design/methodology/approach The authors use dynamic panel quantile regression with nonadditive fixed effects for a sample of 112 emerging and developing economies spanning from 2001 to 2021. Findings The findings demonstrate that financial development has a nonlinear relationship with income inequality. The…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Zhi Geng, Xiuchuan Lu · Language Culture and Curriculum Geopolitics

Carrying identity across borders: a kit bag study of Chinese language teachers in Latin America

This study examines how Chinese language teachers in Latin America construct and negotiate their professional and personal identity in cross-cultural and resource-constrained contexts through everyday material practices. It employs the kit bag method as an embodied, object-based elicitation approach to examine how identity is materially carried, enacted, and negotiated across borders through everyday objects. Data were generated through participant-recorded videos and…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Jhon Valdiglesias · F1000Research Geopolitics

Regulatory Design and Long-Term Growth: Insights from China’s Experience for Latin America

Background: Regulatory efficiency is increasingly recognized as a key determinant of long-term economic growth. China's institutional consolidation offers a comparative reference case for understanding how streamlined procedures, and coordinated governance can reduce transaction costs and foster development. In contrast, many Latin American countries face persistent administrative complexity that may hinder growth. Methods: This study applies Institutional Theory and…

Read at Journal articles (OpenAlex)

Inter-American Dialogue Ana Kourchenko Geopolitics

Regional Competitiveness and Resilience through Integration of Digital and Physical SEZs (Special Economic Zones)

North American competitiveness and resilience to geopolitical and climate disruptions increasingly depend on whether the region can co-design and co-locate its digital and manufacturing supply chains, so they reinforce rather than constrain one another. This approach provides a new paradigm and framework, one based on “ring-fencing” supply chains. Alongside efforts to shift factories closer to home and secure physical inputs, it is equally important to create trusted rules…

Read at Inter-American Dialogue

arXiv (research papers) Yanting Wang SI

AgentWatcher: A Rule-based Prompt Injection Monitor

Large language models (LLMs) and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: (1) their effectiveness degrades significantly as context length increases, and (2) they lack explicit rules that define what constitutes prompt injection, causing detection decisions to be implicit, opaque, and difficult to reason about. In this work, we propose…

Read at arXiv (research papers)

Journal articles (OpenAlex) Elisenda Aguilera-Cora, Roger Cuartielles · Catalan Journal of Communication & Cultural Studies Geopolitics

Framing the tourism degrowth protests in Barcelona and its implications for place branding strategies

Grounded in framing and place branding theories, this study proposes a novel approach to analyse how digital newspapers reported on the protest for tourism degrowth held in Barcelona in July 2024. Using qualitative framing analysis, it examines textual and visual frames of 45 news stories and their accompanying images across 28 digital newspapers. Results show newspapers framed the protest as a conflict. While local, regional and national newspapers focused on the…

Read at Journal articles (OpenAlex)

arXiv (research papers) Meiwen Ding SI

Covert Visual Prompt Injection against Commercial Multimodal Large Language Models

Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks. Existing prompt injection methods predominantly rely on textual prompts or perceptible visual prompts that are observable by human users. In this work, we study imperceptible visual prompt injection against powerful closed-source MLLMs, where adversarial instructions are embedded in…

Read at arXiv (research papers)

Journal articles (OpenAlex) Miriam Siemon, Wolfgang Reißmann, Margreth Lünenborg · Feminist Media Studies Geopolitics

Navigating the crisis – media activism on gender-based violence during the pandemic. Results from a longitudinal multi-method study

Gender-based violence (GBV) is a fundamental safety risk and major public health issue for women and genderqueer individuals. This paper examines online activist media practices in the German discourse on GBV during the COVID-19 pandemic, which exacerbated GBV. Using a practice theory approach to social media activism, we analyzed how different actors, such as feminist activists and journalists, engage in public discourse on GBV relationally. We employed a mixed-methods…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Hidetaka Yoshimatsu · Japanese Journal of Political Science Geopolitics

Policy emulation and vested interests: Japan’s strategic response to economic security amid US–China technology competition

Abstract China’s growing technological power and the resulting US–China rivalry prompted various countries, including Japan, to adopt necessary countermeasures. This study examines Japan’s strategic approach to economic security and technology policy under the framework of policy emulation and vested interests. The US–China technology competition urged Japan to reformulate its technological strategies with the aim of reducing economic dependence on China. Japan’s policy…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Fabricio A. Fonseca · Asian Education and Development Studies Geopolitics

Latin America in Singapore’s foreign policy: hedging and inter-regionalism

Purpose In recent years, Singapore successfully concluded FTA negotiations with the largest trading blocs in Latin America, potentially becoming the first extra-regional actor to have access to almost 90% of the region’s markets. This paper aims to explore the motivations that led Singapore to approach Latin America, and how it is connected to its foreign policy at large. Design/methodology/approach Through the adaptation of the concepts of geopolitical codes and hedging…

Read at Journal articles (OpenAlex)

arXiv (research papers) Duanyi Yao SI

Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models

Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this recommendation-seeking behavior to inject unauthorized advertisements. Unlike traditional pattern-triggered backdoors that rely on artificial triggers such as pixel patches or special tokens, Hidden Ads activates on natural user behaviors: when users…

Read at arXiv (research papers)

arXiv (research papers) Haozhen Wang SI

PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications. However, their practical deployment is often hindered by issues such as outdated knowledge and the tendency to generate hallucinations. To address these limitations, Retrieval-Augmented Generation (RAG) systems have been introduced, enhancing LLMs with external, up-to-date knowledge sources. Despite their advantages, RAG systems remain vulnerable to adversarial attacks…

Read at arXiv (research papers)

Journal articles (OpenAlex) Moeti Damane, Sin‐Yu Ho · Energy Policy Geopolitics

Green finance and energy security in Africa: A panel VAR approach to sustainable development

Africa's energy security remains fragile amid unreliable supply, high import exposure, and climate shocks, even as the continent pursues a low carbon transition. This study examines how climate-oriented finance and renewable energy deployment relate to energy security in 16 African countries from 2000 to 2021 using a Panel Vector Autoregression framework. To ensure conceptual clarity, external financial inflows, foreign direct investment and mitigation related development…

Read at Journal articles (OpenAlex)

The Guardian Moldova Staff and agencies Geopolitics

Ukraine war briefing: Moldova declares emergency after Russian attack cuts key power line

President urges people to reduce consumption after power line passing through Ukraine damaged by drones; Moscow spring offensive steps up. What we know on day 1,491 Moldova declared a state of emergency in the energy sector after a key power line with Europe was disconnected following Russian strikes in Ukraine. The declaration comes into effect on Wednesday and lasts for 60 days. The prime minister, Alexandru Munteanu, appealed to people to “avoid unnecessary consumption…

Read at The Guardian Moldova

Journal articles (OpenAlex) Tommaso Gravante, Alice Poma · Social movement studies Geopolitics

Feeling the climate crisis can be overwhelming. Emotion management in climate activism

This article proposes an analysis of the emotion management strategies that Mexican climate activists employ to overcome the emotions they feel by living in the climate crisis, particularly in their social context, all of which may be detrimental to activism. The theoretical framework combines Arlie Hochschild’s emotion management theory, commonly applied in social movement studies, and the contributions of social psychology that examine emotion regulation strategies, which…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Rafiuddin Najam, Harry Anthony Patrinos, Raja Bentaouet Kattan · Journal of Population Economics Geopolitics

The mis-education of women in Afghanistan: from wage premiums to economic losses

Abstract This study examines the private monetary rate of return to schooling in Afghanistan. We use two novel datasets—a series of nationally representative household surveys (2007, 2014, 2020) and administrative data on public employees in 2018—and apply OLS, Heckman selection correction, and instrumental-variables estimation to measure returns to education. We find that one additional year of schooling, on average, is associated with a 3 to 7 percent increase in monthly…

Read at Journal articles (OpenAlex)

Simon Willison SI

Auto mode for Claude Code

Auto mode for Claude Code Really interesting new development in Claude Code today as an alternative to --dangerously-skip-permissions: Today, we're introducing auto mode, a new permissions mode in Claude Code where Claude makes permission decisions on your behalf, with safeguards monitoring actions before they run. Those safeguards appear to be implemented using Claude Sonnet 4.6, as described in the documentation: Before each action runs, a separate classifier model reviews…

Read at Simon Willison

Inquirer Global Nation jbarrion South China Sea

Selective application: China asserts, defies international law at once

China’s continued rejection of the 2016 arbitral decision on the South China Sea reflects not only a legal disagreement but also questions of credibility and intent, an analyst said. Don McLain Gill, an instructor of international relations at De La Salle University, said Beijing has positioned its “narrowly driven interests above international law.” China recognizes

Read at Inquirer Global Nation

Journal articles (OpenAlex) Vladimir Miroljub Cvetković, Dalibor Milenković, Tin Lukić · Geosciences Geopolitics

Measuring Community Disaster Resilience in Serbia Using an Adapted BRIC Framework Grounded in DROP: Index Construction and Regional Disparities

Disaster resilience has become a key focus of risk reduction efforts, but measuring it remains complex due to differences in hazards, development paths, and data systems. This study modifies the Baseline Resilience Indicators for Communities (BRIC) approach, based on the Disaster Resilience of Place (DROP) framework, to evaluate community resilience in Serbia and highlight regional differences. An initial list of 186 indicators was created from international BRIC studies and…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Михаил Минаков · Philosophy & Social Criticism Geopolitics

The Absent Sovereign and the Invisible Foundation: Political Liberalism’s Aporias in Theorizing Constituent Power

How can constituent power be simultaneously constrained by law and genuinely democratic? This question has haunted constitutional theory since Sieyès distinguished constituent from constituted power. This article argues that political liberalism’s attempts to resolve this paradox generate two structural aporias. First, anti-foundationalist approaches to constituent power inevitably produce an invisible foundation: normative standards like “the most reasonable” operate as…

Read at Journal articles (OpenAlex)

arXiv (research papers) Charoes Huang SI

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning

The Model Context Protocol (MCP) has rapidly emerged as a universal standard for connecting AI assistants to external tools and data sources. While MCP simplifies integration between AI applications and various services, it introduces significant security vulnerabilities, particularly on the client side. In this work we conduct threat modelings of MCP implementations using STRIDE (Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, Elevation of…

Read at arXiv (research papers)

arXiv (research papers) Marco Arazzi SI

SecureBreak -- A dataset towards safe and secure models

Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Although previous related works focused primarily on model architectures and alignment methodologies, these approaches alone cannot ensure the complete elimination of harmful generations. This concern is reinforced by the growing body of scientific literature showing that attacks, such…

Read at arXiv (research papers)

arXiv (research papers) Charoes Huang SI

Are AI-assisted Development Tools Immune to Prompt Injection?

Prompt injection is listed as the number-one vulnerability class in the OWASP Top 10 for LLM Applications that can subvert LLM guardrails, disclose sensitive data, and trigger unauthorized tool use. Developers are rapidly adopting AI-assisted development tools built on the Model Context Protocol (MCP). However, their convenience comes with security risks, especially prompt-injection attacks delivered via tool-poisoning vectors. While prior research has studied prompt…

Read at arXiv (research papers)

arXiv (research papers) Vincent Siu SI

A Framework for Formalizing LLM Agent Security

Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective is being pursued, and whether the action serves that objective. However, existing definitions of security attacks against LLM agents often fail to capture this contextual nature. As a result, defenses face a fundamental utility-security tradeoff: applying…

Read at arXiv (research papers)

Older stories