Results for “security”

Journal articles (OpenAlex) Sara E. Davies, Phyu Phyu Oo, Queenie Pearl Villalon Tomaro · Global Responsibility to Protect Geopolitics

To Prevent and Protect Sexual and Gender-Based Violence: ASEAN Commitments to the Regional Plan of Action on Women, Peace and Security

Abstract This article examines the Association of Southeast Asian Nations (ASEAN) fulfilment of commitments to prevent and protect populations from sexual and gender-based violence (SGBV) under the ASEAN Regional Plan of Action on Women, Peace and Security (RPA-WPS). Using qualitative content analysis of 30 publicly available documents, including ASEAN Chair’s Statements from the 40th to 46th Summits (2021–2025), as well as relevant ASEAN, UN General Assembly, UN Security…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Thuy Thu Nguyen, Phan Thanh Hoa · Information and Computer Security Geopolitics

Deepfake awareness and privacy protective behaviours: evidence from Vietnamese young faceswap apps users

Purpose Deepfakes are synthetic media (audio recordings, videos or photos) created using artificial intelligence. In recent years, deepfakes have become an increasing concern for internet users; therefore, protecting oneself from cybercrime attacks is vital. The purpose of this study is to use the Technology Acceptance Model and Protection Motivation Theory to build a serial mediation model of the relation between deepfake awareness, perceived security and privacy risks…

Read at Journal articles (OpenAlex)

arXiv (research papers) Vincent Siu SI

Agent Security Needs Redefinition through a Holistic Framework

Agent security is widely treated as a question about action content. Defenses ask whether an instruction looks malicious. Benchmarks ask whether an agent performs a harmful sounding action. \textbf{We argue that agent security is fundamentally a contextual problem, and that the current content based framing systematically misdefines it.} A command to ``delete user data'' might be a routine administrative request or a prompt injection attacking production systems, and the…

Read at arXiv (research papers)

arXiv (research papers) Yedidel Louck SI

Protocol-Level Attacks on Agentic Commerce Platforms: A Cross-Platform Taxonomy, AIP-Bench, and Unified Defense

Agentic commerce platforms let AI agents autonomously discover services, move payments, and wield user credentials on their users' behalf, and they already handle real money. Their security has so far been studied almost entirely at the level of the AI model, through prompt injection and misalignment. We show that the more consequential risks lie one layer down, in the protocol between agents and commerce services. There, vulnerabilities are structural : exploitation is…

Read at arXiv (research papers)

Journal articles (OpenAlex) Belén Gallardo, Rodrigo A. Estévez, Valeria Espinoza et al. · Frontiers in Marine Science Geopolitics

Exploring heterogeneity in marine energy preferences: insights from Chile

Marine energies can reduce carbon emissions, diversify energy supply, and improve energy security worldwide. However, no form of energy generation is without a social and environmental impact, and these impacts can lead to tension and conflict between governments, energy providers, and communities. Understanding heterogeneity in public preferences towards marine energy is critical to formulating appropriate policies and targeted development strategies. This study used a…

Read at Journal articles (OpenAlex)

arXiv (research papers) Zhanhao Hu SI

Twin Agent: Context Residual Compression for Privilege Separated Agents

Large language model (LLM) agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream reasoning and tool use. Existing secure-by-design approaches mitigate this risk by separating untrusted observations from privileged execution and careful control of information flow, but often degrade utility and require extensive task-specific engineering. We thus propose Twin Agent, a general privilege separation design…

Read at arXiv (research papers)

Inter-American Dialogue Yifang Wang Geopolitics

Managing Sovereign Waters: Infrastructure, Maritime Security, and Strategic Agency Comparative—Approaches from the Caribbean and the Pacific

On May 28, 2026, the Inter-American Dialogue’s Asia & Latin America Program held "Managing Sovereign Waters: Infrastructure, Maritime Security, and Strategic Agency," the second event in a private roundtable series titled "Comparative Policymaking in a Shifting Global Architecture: Approaches from the Caribbean and the Pacific."

Read at Inter-American Dialogue

The Guardian Cuba Ruaridh Nicoll in Havana Geopolitics

US claims of Cuba’s ‘unique threat’ jar with reality of hunger and blackouts

State department’s 100-page report is latest push in Trump administration campaign to bring down government The US government’s latest allegations that Cuba is behind “many of the most significant upheavals in recent American political history” and that its leaders pose “a unique threat to American homeland security” have come as startling revelations to those living under the six-month-long US oil blockade in Havana, where desperate people search through piles of…

Read at The Guardian Cuba

Journal articles (OpenAlex) Chukwuma Godwin Onyia · African Security Review Geopolitics

Twenty years of terror: How Boko Haram exploited the Bystander effect to build its resilience

Since transitioning to civilian rule in 1999, Nigeria has faced a persistent security crisis. Central to this instability is the longevity of terrorist organisations, particularly Boko Haram and its splinter factions. This study examines the group’s two-decade resilience by exploring how Muslim bystanders’ passivity in northern Nigeria facilitates its operations. Utilising a mixed-methods approach – integrating quantitative data with qualitative case studies – this research…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Fabian Stigar · Open Access Government Geopolitics

Sea denial in the Black Sea: Lessons for Europe

Sea denial in the Black Sea: Lessons for Europe Ukraine turned maritime vulnerability into a strategic advantage in the Black Sea. Europe must now turn those wartime lessons into lasting maritime security. At the start of Russia’s full-scale invasion, the naval balance looked overwhelmingly one-sided. Russia seized Snake Island, blockaded Ukrainian ports, and threatened both amphibious operations and Ukraine’s access to global maritime trade. Yet the most consequential…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Morena Skalamera · Global Policy Geopolitics

Beyond Dualism: EU Policy Toward Central Asia Through Decarbonization, Problem Linkage, and Civil Society Engagement

ABSTRACT Despite the large reappraisal of the EU's security and economic interests in Central Asia, its foreign policy impact has remained weak. This article develops a constructivist, multi‐level framework to examine how European and Chinese approaches to decarbonization are translated into policy in Kazakhstan and Uzbekistan. I argue that the EU and China advance fundamentally different conceptions of decarbonization, yet neither approach determines outcomes directly…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jie Li SI

Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing

Large language model (LLM) agents are starting to take on routine work in high-performance computing (HPC), including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows. To do this work, an agent commonly acts under its user's credentials and inherits the user's access to files and the scheduler. This arrangement creates a failure mode that ordinary account-level controls do not capture. Adversarial…

Read at arXiv (research papers)

arXiv (research papers) Devina Jain SI

Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security

LLM-based agents process external content, exposing them to prompt injection and multi-turn manipulation. We present a 21-scenario benchmark for adaptive cross-session attacks against fresh-session LLM defenders: an autonomous LLM attacker observes prior defender responses and pivots across rounds, while each defender response is evaluated as a fresh interaction. A controlled 3 x 3 attacker-defender matrix contains 945 battles. Restricting scoring to the first round yields…

Read at arXiv (research papers)

arXiv (research papers) Rabimba Karanjai SI

Context Contamination in LLM Analysis of Network Security Logs: Poison with Passive Prompt Injection and Mitigation Evaluation

Large Language Models are increasingly deployed in Security Operations Centers for log analysis tasks including summarization, alert triage, and threat investigation. These systems ingest logs from external-facing services and process network logs as natural language contexts to generate security insights. We demonstrate that this architectural pattern introduces a critical vulnerability: adversaries can embed prompt injection payloads in log-generating fields that persist…

Read at arXiv (research papers)

Journal articles (OpenAlex) Renato Matheus Mendes Fakhoury, Gabriella Gricius · European Journal of International Security Geopolitics

Eco-anxiety and the self in a warming world: Conceptualising ontologically insecure communities

Abstract While much work has been done on ontological security relating to the state’s sense of self, whether addressing the role of migration, globalisation, and even membership to supranational entities like the European Union, scholars have explored less how creating ontological security could be an unexpected outcome in responding to anxiety around shared environmental spaces. In this paper, we conceptualise an ‘ontological insecurity community’ – where groups of states…

Read at Journal articles (OpenAlex)

arXiv (research papers) Mohammad Allahbakhsh SI

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation

Penetration testing traditionally evaluates whether adversaries can exploit weaknesses in software, infrastructure, configurations, or operational controls to achieve security-relevant compromise. This paradigm remains necessary for AI-enabled systems, but it is no longer sufficient. In such systems, adversaries may influence prompts, retrieved content, sensor inputs, training data, memory, tools, or human-AI interaction loops to alter system behavior without directly…

Read at arXiv (research papers)

arXiv (research papers) Sanket Badhe SI

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation

Reusable skills are becoming a fundamental building block of Large Language Model (LLM) agents, enabling capabilities to be packaged, shared, and reused across diverse applications. However, existing security research primarily focuses on prompt injection and runtime execution, leaving security risks throughout the broader skill lifecycle largely unexplored. In this paper, we present SkillSec-Eval, a lifecycle-aware framework for systematically evaluating the security of…

Read at arXiv (research papers)

Journal articles (OpenAlex) Thi Ha Do, Niloufer Selvadurai · Asian Journal of Law and Society Geopolitics

Data Sovereignty and the Digital Economy: Analysing the Effectiveness of Viet Nam’s Cyber Security and Cybercrime Laws

Abstract Viet Nam’s pursuit of data sovereignty is reshaping its digital governance, while its implications for individual rights and digital markets require more careful consideration. The transition from the 2018 Cyber Security Law to the 2025 consolidated Cyber Security Law raises an important questions: how can data sovereignty be advanced while preserving legal certainty, rights protection, and digital economic growth? This article applies doctrinal analysis and a…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Ming-Min Yang, Kwei‐Bo Huang · Asian Studies Review Geopolitics

What Minilateralism Can and Can’t Do in Cross-Taiwan Strait Conflict Management

What can – and can’t – minilateralism contribute to the management of cross-Taiwan Strait conflict? Although US-linked minilateral mechanisms have multiplied across the Indo–Pacific, their concrete relevance to Taiwan’s security has not been systematically assessed. To address this gap, the study develops a comparative framework focused on policy signalling, deterrence by punishment and by denial, and escalation dynamics, and applies it to three prominent cases: the…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yaxin Li SI

Devil in the Lens: Analyzing and Defending Physical Prompt Injection Against Vision-Language Models on Wearable Devices

Vision-Language Models (VLMs) are rapidly deployed on human-facing wearable devices such as smart glasses to enable multimodal perception and AI-assisted decision-making. While prior research has demonstrated the risks of visual prompt injection into digital image inputs of VLMs, the unique security challenges posed by the increasing integration between physical environments and wearable intelligence, such as those embodied in VLM-enabled AI glasses, remain underexplored…

Read at arXiv (research papers)

Inquirer Global Nation clopez South China Sea

A decade on, arbitral award remains central to PH sea strategy

MANILA, Philippines — A decade after the landmark arbitral award that invalidated China’s nine-dash line, now 10-dash line, the decision remains a critical strategic asset for the Philippines, even as its long-term value depends on Manila’s ability to strengthen its domestic capabilities and deepen security partnerships overseas. Elaine Tolentino, former chair of De La Salle

Read at Inquirer Global Nation

Article 19 katia

Moldova: Putting civil society’s digital security skills into practice

In July ARTICLE 19 Europe brought together civil society organisations and emerging digital security practitioners from across Moldova to explore how local technical expertise can respond to the digital security needs these organisations actually face. The participants work in a wide spectrum of fields: human rights, civic participation, rural development, child protection, humanitarian assistance, social and

Read at Article 19

arXiv (research papers) Corban Villa SI

Prismata: Confining Cross-Site Prompt Injection in Web Agents

Autonomous web agents promise to automate everyday browsing tasks, but inherit one of the web's oldest attack surfaces. Cross-Site Scripting proved that mixing trusted and untrusted content is dangerous, even on benign pages. Agents resurface this risk by interpreting natural language as instructions, allowing third-party and user-generated content to hijack the agent via prompt injection. The core challenge is that deriving a task-specific security policy requires reasoning…

Read at arXiv (research papers)

OWASP GenAI Security Project OWASPGenAIProject Editor Security

GenAI and Agentic AI Exploit Roundup Q2 2026

April 1 through June 30 2026 Overview Six selected cases show how AI integrations, coding tools, and browser agents can turn ordinary inputs or delegated access into security exposure. Defenders should constrain tool execution and credentials, preserve input provenance, and monitor the actions agents take. Coverage includes incidents and technical disclosures published during the quarter.

Read at OWASP GenAI Security Project

Journal articles (OpenAlex) Ji-Jen Hwang, Alice Yang · Defense and Security Analysis South China Sea

Submarine cables and security competition in the South China Sea: pre-emptive infrastructure power and digital sea lines of communication

China's growing influence in the South China Sea (SCS) extends beyond traditional maritime security to undersea communication cables, creating new risks for digital infrastructure, crisis stability, and defence planning. Using a qualitative case study of the SEA-ME-WE 6 cable project (2020-2025), this article argues that U.S.-China competition exemplifies pre-emptive infrastructure power, whereby states shape cable networks at the construction stage to secure future…

Read at Journal articles (OpenAlex)

Illiberalism Studies Program (GWU) Erin Lockwood Geopolitics

Trump-First Foreign Policy and the Liberal International Order That Never Was

During U.S. President Donald Trump’s first term, he billed his foreign policy as one of “America first,” an agenda that prioritized U.S. security and economic interests over international cooperation. If...

Read at Illiberalism Studies Program (GWU)

Journal articles (OpenAlex) Ruiyu Geng, H Yu, Jinyu Li · Sustainability Geopolitics

Wind-Resource Complementarity and Cross-Border Energy Security in the North Sea: A Data-Driven International Legal Framework for Offshore Wind Cooperation

The North Sea is becoming a shared renewable energy space in which offshore wind deployment, grid planning, market operation and environmental governance increasingly cross borders. This article asks how wind-resource complementarity can inform legal and institutional design for cross-border offshore wind cooperation. It combines a five-year representative-point wind-resource screening analysis using NASA POWER hourly data from 2021 to 2025 with functional…

Read at Journal articles (OpenAlex)

Stimson Center Joaquin Matamis Geopolitics

Nuclear Security News and Member Updates Roundup, May and June 2026

The US and Iran engage in volatile diplomatic talks on Iran's nuclear program; drones strike nuclear facilities in Ukraine, UAE; and efforts continue to strengthen nuclear cybersecurity around the globe.

Read at Stimson Center

Article 19 natashas

Iran: Environmental activists must be immediately released

ARTICLE 19 is deeply concerned about the reported arrests of Houman Jowkar and Sepideh Kashani, environmentalists from the Persian Wildlife Heritage Foundation, by Iranian security forces on 1 July. Their detention is part of a broader pattern of repression targeting civil society, human rights advocates, and other individuals engaged in public interest activities. We call

Read at Article 19

Article 19 katia

Building digital resilience against transnational repression

From 30 June to 1 July 2026, ARTICLE 19 Europe hosted the Transnational Digital Resilience Forum in Prague, bringing together journalists, human rights defenders, lawyers, researchers, and digital security experts from across Europe and beyond. The Forum created a space for participants to exchange experiences, identify emerging trends in transnational digital repression (digital TNR), and discuss practical

Read at Article 19

Older stories