Results for “App”

arXiv (research papers) Hanna Foerster SI

CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents

AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior. Among proposed defenses, architectural isolation provides the strongest guarantees by strictly separating trusted task planning from untrusted environment observations. However, applying this design to Computer Use Agents (CUAs), which automate tasks by viewing screens and executing actions, presents a fundamental challenge. Current agents require continuous observation of…

Read at arXiv (research papers)

arXiv (research papers) Oleg Brodt SI

The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multistep Malware Delivery Mechanism

Prompt injection was initially framed as the large language model (LLM) analogue of SQL injection. However, over the past three years, attacks labeled as prompt injection have evolved from isolated input-manipulation exploits into multistep attack mechanisms that resemble malware. In this paper, we argue that prompt injections evolved into promptware, a new class of malware execution mechanism triggered through prompts engineered to exploit an application's LLM. We introduce…

Read at arXiv (research papers)

War on the Rocks Orlando J. Pérez Geopolitics

After Maduro: Trump’s Managed Authoritarianism Trap in Venezuela

It’s early days, but the Trump administration’s approach to a post-President Nicolás Maduro Venezuela is quickly coming into focus. This is not externally imposed democracy building but a regime management project that relies on compliant regime insiders, the existing state security apparatus, and offshore coercive leverage. As I argued previously in these pages, removing the apex of an authoritarian pyramid does not dissolve the pyramid. What changes is who gets to set the…

Read at War on the Rocks

Journal articles (OpenAlex) Chijioke Uwah, Priviledge Cheteni, Desira Davids · International Journal of Adolescence and Youth Geopolitics

Applied theatre as a tool for social transformation: examining its impact on learners affected by gang violence

Research indicates a significant correlation between fractured family structures and gang involvement, with children from unstable homes facing heightened risks of untreated mental health issues like depression and anxiety, which can predispose them to gangsterism. This qualitative study explored the impact of forum theatre interventions in Helenvale, Gqeberha, engaging 16 participants aged 12–14 from two local primary schools, with balanced gender representation. Data…

Read at Journal articles (OpenAlex)

Simon Willison SI

First impressions of Claude Cowork, Anthropic's general agent

New from Anthropic today is Claude Cowork, a "research preview" that they describe as "Claude Code for the rest of your work". It's currently available only to Max subscribers ($100 or $200 per month plans) as part of the updated Claude Desktop macOS application. Update 16th January 2026: it's now also available to $20/month Claude Pro subscribers. I've been saying for a while now that Claude Code is a "general agent" disguised as a developer tool. It can help you with any…

Read at Simon Willison

arXiv (research papers) Shawn Li SI

Defenses Against Prompt Attacks Learn Surface Heuristics

Large language models (LLMs) are increasingly deployed in security-sensitive applications, where they must follow system- or developer-specified instructions that define the intended task behavior, while completing benign user requests. When adversarial instructions appear in user queries or externally retrieved content, models may override intended logic. Recent defenses rely on supervised fine-tuning with benign and malicious labels. Although these methods achieve high…

Read at arXiv (research papers)

Journal articles (OpenAlex) Michalinos Zembylas · Educational Review Geopolitics

Conservatism as affective ideology: rethinking the recent attacks on higher education

This conceptual paper examines recent conservative attacks on higher education through the lens of affective ideology. While Michael Apple’s landmark framework of “conservative modernisation” has illuminated how ideological coalitions restructure education, comparatively little attention has been paid to the affective power that motivates and sustains such political projects. The paper argues that conservatism in higher education cannot be understood solely as an ideological…

Read at Journal articles (OpenAlex)

arXiv (research papers) Zhiyuan Chang SI

Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning

Large language model (LLM)-integrated applications have become increasingly prevalent, yet face critical security vulnerabilities from prompt injection (PI) attacks. Defending against PI attacks faces two major issues: malicious instructions can be injected through diverse vectors, and injected instructions often lack clear semantic boundaries from the surrounding context, making them difficult to identify. To address these issues, we propose InstruCoT, a model enhancement…

Read at arXiv (research papers)

Journal articles (OpenAlex) Anja-Liisa Gonsior, Helene Pleil, Christian Reuter · Journal of Cyber Policy Geopolitics

‘Difficult but possible’: an exploratory approach to the regulation of cyber weapons using lessons learned from chemical weapons arms control

Given the rising global prevalence of cyberattacks, cyber operations are being deployed with greater frequency in military settings. Despite rapid technological developments and associated threats, there is currently no binding international regulatory framework or agreement in place. It is frequently questioned whether the mechanisms of classic arms control (AC) can be adapted to the realities of cyberspace. In the field of AC, the regulation of chemical weapons represents…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Gilad Karo, Tom Divon, Blake Hallinan · Social Media + Society Geopolitics

The TikTok Caliphate: How Jihadist Supporters Exploit Algorithmic Recommendations and Evade Content Moderation

Jihadist organizations and their supporters have long used social media to spread propaganda, creating enduring content moderation challenges. Despite TikTok’s purported zero-tolerance approach to violent extremism, terrorist propaganda persists on the platform. This study investigates how supporters of ISIS and Al-Qaeda employ TikTok’s features to exploit algorithmic recommendations and evade content moderation, increasing their visibility within a hostile platform…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) D.K. SUO, A.E. IGHARO, M.A.S. AL‑FARYAN et al. · Applied Ecology and Environmental Research Geopolitics

SYNERGIZING ENERGY SECURITY, URBANIZATION, AND DECARBONIZATION IN CHINA (1990–2023): A POLICY– INNOVATION–INFRASTRUCTURE APPROACH TO SUSTAINABLE DEVELOPMENT

This study examines the dynamic relationship between energy security, urbanization, technological innovation, and decarbonization in China over the period 1990–2023. Using a dynamic panel framework and the System Generalized Method of Moments (SYS-GMM), the analysis evaluates how these factors jointly shape sustainable development outcomes. The findings indicate that energy security and technological innovation exert significant positive effects on decarbonization…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Juha A. Vuori · Global Studies Quarterly Geopolitics

Review as Ritual: Maintaining and Disrupting Nuclear Deterrence through the Treaty on the Non-Proliferation of Nuclear Weapons Review Process

Abstract The article uses ritual action as an approach to analyze the Treaty on the Non-Proliferation of Nuclear Weapons (NPT) and its review process as (1) claims of providing solutions to problems that involve liminal boundaries and uncontrollable forces (nuclear war), (2) rooted in expert diplomatic practice (regime formation), (3) identifying evil and providing boundaries to it (securitization), and (4) reifying social processes and political structures (international…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Bama Andika Putra · Educational Process International Journal South China Sea

Case Studies in Indonesian Foreign Policy Teaching: Retrospective and Decision-Making Approaches

Background/purpose. Teaching Indonesian Foreign Policy (IFP) for international relations (IR) students comes with its challenges. The wide coverage of substantive topics and the use of pedagogical strategies that facilitate active learning have been largely overlooked by instructors in Indonesian and Southeast Asian higher education institutions offering IFP courses. The purpose of this study is to explore alternative means of learning IFP, which enable a more nuanced…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Mun-Young Ryu, Byung-Hee Won, Hyun-jo Kim · Nuclear Technology Geopolitics

Intelligent Decision Support System for Nuclear Export Control: A BERT-Based Approach

The nuclear industry is distinguished by its highly secured and restricted nature, requiring rigorous safety validation, which necessitates additional considerations for Artificial Intelligence (AI) adoption compared to other industries. Nuclear export control requires comprehensive assessment of strategic items through expert classification but faces growing challenges in knowledge transfer and consistent decision making across increasing international trade volumes. This…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Nguyen Cong Tung · Foreign Policy Analysis South China Sea

Unveiling Relational Power in Foreign Policy: Insights from China–Vietnam Relations

Abstract This article employs the relational power approach to explain the essence and dynamics of China–Vietnam relations. The bilateral relationship between these two neighboring communist states has remained relatively stable since their diplomatic normalization in 1991. Vietnam has regarded China as a top priority in its foreign policy, despite historical legacies and lingering territorial conflicts in the South China Sea. Meanwhile, China has, at times, tolerated…

Read at Journal articles (OpenAlex)

arXiv (research papers) Panagiotis Theocharopoulos SI

Multilingual Hidden Prompt Injection Attacks on LLM-Based Academic Reviewing

Large language models (LLMs) are increasingly considered for use in high-impact workflows, including academic peer review. However, LLMs are vulnerable to document-level hidden prompt injection attacks. In this work, we construct a dataset of approximately 500 real academic papers accepted to ICML and evaluate the effect of embedding hidden adversarial prompts within these documents. Each paper is injected with semantically equivalent instructions in four different languages…

Read at arXiv (research papers)

arXiv (research papers) Jiayu Hu SI

Look Closer! An Adversarial Parametric Editing Framework for Hallucination Mitigation in VLMs

While Vision-Language Models (VLMs) have garnered increasing attention in the AI community due to their promising practical applications, they exhibit persistent hallucination issues, generating outputs misaligned with visual inputs. Recent studies attribute these hallucinations to VLMs' over-reliance on linguistic priors and insufficient visual feature integration, proposing heuristic decoding calibration strategies to mitigate them. However, the non-trainable nature of…

Read at arXiv (research papers)

Rappler Bea Cupin South China Sea

PCG to China: Aid for fisherman ‘appreciated,’ but why were you in PH EEZ?

The Philippine Coast Guard acknowledges China's 'humanitarian gesture' toward a Filipino fisherman, but questions why the Chinese were sailing just 71 nautical miles off Zambales in the first place

Read at Rappler

Journal articles (OpenAlex) Afees Adebare Salisu · Journal of Economic Studies Geopolitics

Climate risks and green stocks in Vietnam

Purpose Vietnam is among the countries most vulnerable to tropical cyclone risks, and its carbon-intensive production model influences its climate change trajectory. Nevertheless, various initiatives have been undertaken to tap into the country’s green economy potential, and I advance the related literature by exploring the connection between climate risks and green assets in Vietnam. Design/methodology/approach Firstly, by employing the predictive models, I examine the…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Jesse Smith · Journal for the Scientific Study of Religion Geopolitics

Partisan and Racial Sorting of Christian Nationalism, 1996–2022: Backlash and Counter Backlash on the (White) Secular Left and Religious Right

ABSTRACT Christian nationalism scholarship and discourse has surged in the years since Trump's 2016 election victory, even as, by most measures, adherence to Christian nationalist beliefs has declined. Applying scholarship on political backlash, I propose that this apparent discrepancy may be explained both by ideological trends antithetical to public religion among Democrats and politicization of religious identity among Republicans, leading to partisan divergence. Given…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yihan Wang SI

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs

The integration of Large Language Models (LLMs) into wearable sensing is creating a new class of mobile applications capable of nuanced human activity understanding. However, the reliability of these systems is critically undermined by their vulnerability to prompt injection attacks, where attackers deliberately input deceptive instructions into LLMs. Traditional defenses, based on static filters and rigid rules, are insufficient to address the semantic complexity of these…

Read at arXiv (research papers)

Journal articles (OpenAlex) Linh Hoang Vu, Tran Duc Hiep, Nguyen Thuy Anh · Discover Sustainability Geopolitics

New structural economics and its implications for Vietnam's high economic growth paths

Vietnam has achieved rapid growth since the Đổi Mới reforms, but sustaining momentum on the path to high-income status remains uncertain. This study analyzes Vietnam’s structural transformation through the lens of New Structural Economics (NSE), highlighting both achievements and persistent vulnerabilities. It contributes in three ways. First, it applies the Growth Identification and Facilitation (GIF) framework at the sectoral level, using recent evidence on productivity…

Read at Journal articles (OpenAlex)

Simon Willison SI

Using Claude in Chrome to navigate out the Cloudflare dashboard

I just had my first success using a browser agent - in this case the Claude in Chrome extension - to solve an actual problem. A while ago I set things up so anything served from the https://static.simonwillison.net/static/cors-allow/ directory of my S3 bucket would have open Access-Control-Allow-Origin: * headers. This is useful for hosting files online that can be loaded into web applications hosted on other domains. Problem is I couldn't remember how I did it! I initially…

Read at Simon Willison

Journal articles (OpenAlex) Phuong Thi Nguyen · Journal of International Logistics and Trade Geopolitics

The impact of technical barriers to trade on Vietnam's fruit and vegetable exports to key markets

Purpose This paper examines Vietnam's fruit and vegetable exports to major destination markets including The United States, South Korea, China and Japan with a particular focus on the impact of technical barriers to trade (TBTs) during the period 2008–2023. Design/methodology/approach Using a gravity model and panel data estimation by Poisson pseudo maximum likelihood (PPML) estimator and generalized least squares (GLS) estimator, the study identifies the effects of economic…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Kristy Campion, Helen Blair Simpson, Amber Hart et al. · Policing An International Journal Geopolitics

“Always out-gun your enemy”: conventional firearms, right-wing extremism and the challenge to contemporary policing

Purpose This article aims to better understand right-wing extremist guidance on conventional firearms, to inform and enhance police preparedness and officer safety. Design/methodology/approach This study uses a novel methodology, which synthesises targeted literature reviews with a weapons intelligence assessment on instructional content in eleven right-wing extremist manifestos, with a case study on conventional firearms possession. These three datapoints were analysed to…

Read at Journal articles (OpenAlex)

arXiv (research papers) Safwan Shaheer SI

Beyond the Benchmark: Innovative Defenses Against Prompt Injection Attacks

In this fast-evolving area of LLMs, our paper discusses the significant security risk presented by prompt injection attacks. It focuses on small open-sourced models, specifically the LLaMA family of models. We introduce novel defense mechanisms capable of generating automatic defenses and systematically evaluate said generated defenses against a comprehensive set of benchmarked attacks. Thus, we empirically demonstrated the improvement proposed by our approach in mitigating…

Read at arXiv (research papers)

Journal articles (OpenAlex) Thomas Just · European Politics and Society Geopolitics

Far-right extremism and mixed martial arts in Germany: radicalization, transnational networks, and democratic resilience

This article examines how far-right extremist groups in Germany appropriate mixed martial arts (MMA) for radicalization, militant training, and transnational networking, and what this reveals about challenges to democratic resilience. It offers one of the first systematic analyses of this underexplored nexus of sport and political violence in political science, demonstrating how combat sports have become embedded in far-right subcultures. Drawing on intelligence reports…

Read at Journal articles (OpenAlex)

arXiv (research papers) Safwan Shaheer SI

Detecting Prompt Injection Attacks Against Application Using Classifiers

Prompt injection attacks can compromise the security and stability of critical systems, from infrastructure to large web applications. This work curates and augments a prompt injection dataset based on the HackAPrompt Playground Submissions corpus and trains several classifiers, including LSTM, feed forward neural networks, Random Forest, and Naive Bayes, to detect malicious prompts in LLM integrated web applications. The proposed approach improves prompt injection detection…

Read at arXiv (research papers)

Inter-American Dialogue Ana Kourchenko Geopolitics

A Tale of Two Sheinbaum’s: Mexico’s Security Strategy Home and Abroad

In this article, the author evaluates the first year of Sheinbaum’s security strategy, focusing on the duality of her security approach.

Read at Inter-American Dialogue

arXiv (research papers) Najmul Hasan SI

Phishing Email Detection Using Large Language Models

Email phishing is one of the most prevalent and globally consequential vectors of cyber intrusion. As systems increasingly deploy Large Language Models (LLMs) applications, these systems face evolving phishing email threats that exploit their fundamental architectures. Current LLMs require substantial hardening before deployment in email security systems, particularly against coordinated multi-vector attacks that exploit architectural vulnerabilities. This paper proposes…

Read at arXiv (research papers)

Older stories