Results for “Security”

Journal articles (OpenAlex) Carolina Ojeda · Land Geopolitics

The Chilean Invisible Reconstruction in Post-Fire Recovery: Interdisciplinary Perspectives and Soil Security Challenges Amidst an Extractive Economic Model

Current post-fire recovery strategies in Mediterranean Chile primarily emphasize discernible outcomes, such as residential reconstruction and expedited reforestation. In this context, neglecting soil degradation remains a critical geographical oversight. This perspective proposes the integration of a soil security framework as an “invisible reconstruction” to mitigate the unacknowledged deterioration of the five soil dimensions (capacity, condition, capital, connectivity…

Read at Journal articles (OpenAlex)

arXiv (research papers) Van Tran SI

Rethinking Agent Security as a Networking Problem

AI agents are rapidly becoming more capable and widely deployed, promising substantial gains in productivity and enabling new classes of applications. However, their growing autonomy also introduces significant privacy and security risks. Existing defenses are predominantly agent-centric, relying on the agent itself to detect threats and enforce privacy and security policies. This approach is fundamentally limited because it entrusts policy enforcement to AI agents whose…

Read at arXiv (research papers)

arXiv (research papers) Yutao Mou SI

ToolHazard: Scaling Adversarial Environments for Security Evaluation and Alignment of LLM-based Agents

Large language model (LLM) agents integrated with external tools are vulnerable to indirect prompt injections embedded in environmental states. However, existing studies largely rely on manually implemented or reused environments, stochastic LLM-based tool simulation, and predefined injection locations, limiting scalable security research across broader domains. To bridge this gap, we propose **ToolHazard**, a scalable adversarial environment synthesis framework that reduces…

Read at arXiv (research papers)

InSight Crime Jeremy McDermott

The InSight Take: Abelardo de la Espriella Inherits Colombia’s Fractured Criminal Landscape

The InSight Take: Abelardo de la Espriella Inherits Colombia’s Fractured Criminal Landscape In this week's InSight Take, Co-Director Jeremy McDermott and Senior Colombia Analyst Sara Garcia unpack what Abelardo de la Espriella inherits, Washington's likely support, whether de la Espriella can match the Uribe-era security gains, and the human rights risks of a harder military push.

Read at InSight Crime

arXiv (research papers) Md Jafrin Hossain SI

On Understanding, Identifying, and Mitigating Vulnerabilities in Agentic Large Language Models

Large Language Models (LLMs) have undergone a shift from stateless conversational interfaces to autonomous agents capable of multi-step planning, tool invocation, code execution, and maintaining persistent memory. When these agents operate with real-world privileges---calling APIs, modifying files, and querying databases---a compromised reasoning step can trigger unauthorized data access, irreversible state changes, or cascading failures, yet the security research community…

Read at arXiv (research papers)

Journal articles (OpenAlex) Xing Li · Lecture Notes in Education Psychology and Public Media Geopolitics

A Study on the Legitimisation of Energy Security Policies under GATT Article XX

Energy security is now linked to environmental protection and climate governance. Because of this, energy-related trade measures have become an important issue in both geopolitics and environmental politics. This paper asks how these measures can be justified under WTO law, especially under GATT Article XX.This paper uses discursive institutionalism as its theoretical framework. It studies legal rules, WTO case law, and the way states justify their policies under Article XX…

Read at Journal articles (OpenAlex)

arXiv (research papers) Xinze Chen SI

SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills

Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security properties remain under-explored. We present \textsc{SkillsMetric}, a five-stage static analysis framework that scores skill packages along pattern density, statistical anomaly, dataflow taint, import anomaly, and capability mismatch dimensions. We construct an adversarial evaluation dataset of 2{,}266 skills spanning 16~attack types…

Read at arXiv (research papers)

arXiv (research papers) Laiqiao Qin SI

BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes

Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or external data. Existing detection methods only detect the presence of injection and refuse to respond upon detection, overlooking the fact that for many modern aligned models, well-crafted instructions can resist most injection attacks. This means that the injection robustness varies significantly…

Read at arXiv (research papers)

Journal articles (OpenAlex) Peter Kačmáry, Kristína Kleinová, Norbert Lörinc · Sustainability Geopolitics

Price Shocks and Their Implications for Sustainable Logistics, Energy Security and Supply Chain Resilience in Europe

European energy markets have experienced significant instability as a result of consecutive global systemic shocks, particularly the COVID-19 pandemic and the geopolitical conflict in Ukraine. This paper analyses the development of crude oil and natural gas prices between 2019 and 2024 and discusses their implications for sustainable logistics, energy security and supply chain resilience in Europe. The study is based on secondary data from internationally recognized sources…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Abhay Kumar Ray, Rupak Sharma, Sunil Kr Pandey · International Journal of Wireless and Microwave Technologies Gadgets

Multiclass Cyber Attack Classification in Smart Home IoT Networks Using Ensemble Machine Learning with the ML-EdgeIIoT Dataset

With the rapid adoption of smart home solutions and related technologies, edge computing has emerged as a key enabler by offering low-latency data processing, increased efficiency and improved scalability. However, this integration in IoT systems introduces complex security challenges in smart home edge environments, increasingly susceptible to cyber threats such as denial-of-service (DoS), malware injection, passive surveillance, and unauthorized access. This paper…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jeremy McHugh SI

The Anatomy of a Prompt Injection: A Component Model for Structured Analysis

Four years after prompt injection was first identified in 2022, attacks are still predominantly documented as verbatim strings rather than structured exploits, despite advancing agent capabilities and threat actors embedding injections to subvert AI-assisted security analysis. This paper formalizes the structure of prompt-injection artifacts, enabling defenders, red teamers, and cyber threat intelligence (CTI) teams to label, compare, and mutate attacks without relying on…

Read at arXiv (research papers)

arXiv (research papers) Aditya Katkar SI

NiyamAI - An Intent-Bound AI Agent with Cryptographically Verifiable Guardrails using Zero-Knowledge Proofs

Autonomous LLM agents with tool execution capabilities introduce severe security risks through prompt injection, goal hijacking, and unauthorized action invocation. Existing guardrails rely on unverified, host local software filters system prompts, semantic classifiers, policy engines that share the execution environment of the untrusted agent, offering no guarantee to an external observer that a safety policy was correctly evaluated. A compromised host produces no evidence…

Read at arXiv (research papers)

Simon Willison SI

Incident Report: unsanctioned agent behaviour during cyber testing

Incident Report: unsanctioned agent behaviour during cyber testing It happened again. This time it was the UK government's AI Security Institute who accidentally attacked other companies while running an evaluation with models with the safety filters turned off. From their technical paper (PDF): During a cyber evaluation, from 25 to 28 July 2026, AI agents engaged in sustained, unsanctioned activity directed at what were, in practice, real people and organisations. These…

Read at Simon Willison

arXiv (research papers) Yanting Wang SI

Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming

Prompt injection poses significant security risks to LLM agents. Efficient and effective red-teaming is therefore critical, both for evaluating these risks and for collecting training data to improve defenses. Existing state-of-the-art prompt injection red-teaming methods primarily rely on reinforcement learning (RL), producing attacker models that often generalize poorly to new target LLMs. In this work, we develop PIMiner, an agentic system for prompt injection…

Read at arXiv (research papers)

LSE European Politics and Policy blog Blog Team Geopolitics

What role should the Council of the Baltic Sea States play in today’s fractured world?

The Council of the Baltic Sea States was established in the early 1990s to help bridge the former East-West divide. But it has increasingly taken on a security role in the aftermath of Russia’s full-scale invasion of Ukraine in 2022. Tobias Etzold and Stefan Gänzle argue that the real test for the Council as a … Continued The post What role should the Council of the Baltic Sea States play in today’s fractured world? first appeared on LSE European Politics.

Read at LSE European Politics and Policy blog

arXiv (research papers) Xuebin Li SI

Breadcrumbing Search Agents: Per-Turn Scheming Over Long-Horizon Trajectories

LLM-based search agents are widely used for information-seeking tasks, but their reliance on external tool returns introduces a critical security risk: web content retrieved during execution is untrusted, exposing agents to prompt injection and goal hijacking. Prior work on search-agent safety primarily focuses on static web-content injection, but modern agents issue follow-up queries and cross-check competing sources, so a single injected page is often diluted or rejected…

Read at arXiv (research papers)

Journal articles (OpenAlex) Saira Bano · Asian Security Geopolitics

Shared insecurity, divergent responses: Pakistan, India, and China after the Return of the Taliban

The return of the Taliban to power in Afghanistan in August 2021 transformed the regional security environment, intensifying concerns regarding terrorism, cross-border militancy, refugee flows, and geopolitical competition. Yet Pakistan, India, and China responded in markedly different ways to this common source of regional insecurity. Why do states facing the same regional security shock adopt divergent policies? Drawing on Regional Security Complex Theory (RSCT), this…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Shameer Modongal, Ashly K. Ramachandran · Global Change Peace & Security Geopolitics

Beyond widening and deepening?: BRICS security narrative revisionism and its limits

Security studies, as a subdiscipline of International Relations (IR), has inherited Eurocentric paradigms that often universalise Western historical experiences while marginalising perspectives from the Global South. Although post-Cold War debates widened and deepened the concept of security to encompass human development, health, climate change, and other non-military concerns, these frameworks can still reproduce Western priorities and interventionist assumptions. This…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Abdul Wasi Popalzay · Journal of Asian and African Studies Geopolitics

Kazakhstan’s multidimensional engagement with Taliban-led Afghanistan (2021–2026)

The Taliban’s 2021 takeover posed a strategic dilemma for Central Asian states engaging an internationally isolated regime. This study analyzes Kazakhstan’s shift from defensive isolationism to functional integration with Taliban-led Afghanistan (2021–2026). Using process tracing, trade analysis, and legal-institutional examination, it develops a “Compartmentalized Pragmatism” framework. Findings show a four-domain engagement architecture, diplomatic, economic, security, and…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Seunghyun Kim · The Pacific Review Space

Institutional density and the statutory articulation of security: Japan’s Basic Acts on ocean and space policy

This article explains why security-related claims acquired different statutory forms in Japan’s maritime and space framework legislation. Comparing the policy processes behind the Basic Act on Ocean Policy (2007) and the Basic Space Act (2008), it treats the two laws not as direct measures of total sectoral securitization but as framework-legislation sites in which security-related claims were translated into statutory form. The article argues that this divergence is best…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Nurgul Karaeva, Жылдыз Ахматовна Дехканова, Gulnara S. Baitikova et al. · Aquaculture Aquarium Conservation & Legislation Geopolitics

Water and environmental cooperation in Central Asian countries: a historical and comparative analysis (1990s to present)

Transboundary water cooperation in Central Asia links irrigation needs, energy security and environmental risk management. The study aimed to trace the evolution of water and environmental cooperation in Central Asia between 1991-2025, using Kyrgyzstan, Kazakhstan and Uzbekistan as examples. The study was conducted as a historical and comparative analysis based on intergovernmental agreements, coordination protocols, materials from regional institutions and project…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Edoardo Lavezzo · Journal of Contemporary European Studies Geopolitics

The complexity of multilateral shelter: evidences from the EU’s approach in the Eastern Partnership

Affecting the systemic environment, the Russian invasion of Ukraine has sparked a new era for small states’ security, evidencing the necessity to find stability and protection in wider states or organisations. Among the geopolitical players that have been directly affected by this crisis, the European Union (EU) has been trying to react in a cohesive and coherent way according to its multilateral principles to protect the states under former Soviet influence. Drawing on the…

Read at Journal articles (OpenAlex)

Stimson Center Joaquin Matamis Geopolitics

Nuclear Security News and Member Updates Roundup, July 2026

As conflict in Iran flares again, U.S. and Saudi Arabia strike a controversial civil nuclear deal; drone strike reportedly kills Zaporizhzhya NPP chief engineer; and a contractor at India’s largest nuclear plant reports a data security breach.

Read at Stimson Center

Journal articles (OpenAlex) Ada Celsa Cabrera García, Giuseppe Lo Brutto · Frontiers in Political Science Geopolitics

Latin America in the face of the expansion of BRICS plus: geopolitical tensions in a transforming world order

The expansion of the BRICS forum scheme to BRICS Plus in 2024 represents a turning point in the reconfiguration of the contemporary world system, strengthening South–South cooperation and challenging the historical hegemony of the United States, with significant effects for Latin America and the Caribbean. In this context, the new National Security Policy implemented by the Trump administration in December 2025 represents another critical juncture that highlights the way in…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Xueping Xu, Zhao Yinjuan · International Journal of Science and Research Archive South China Sea

A study on new changes in Vietnam’s fishery harvest policies in the South China Sea and their impacts

After To Lam assumed the office of General Secretary of the Central Committee of the Communist Party of Vietnam in August 2024, Vietnam has further established an interlocked policy system covering economic interests, domestic governance, maritime territorial claims, deployment of maritime security forces, and external maritime cooperation in the fisheries sector of the South China Sea. On the one hand, to lift the “yellow card” warning imposed by the European Union in 2017…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Адриана Ковачева · Sexuality & Culture Geopolitics

Queer Shores. Non-Heteronormative Spaces on the Bulgarian Black Sea Riviera

The primary aim of this article is to offer a preliminary mapping of public spaces along the Bulgarian Black Sea coast which, although originally designed as sites for staging heterosexual holiday romances, were appropriated in the 1960s by queer men in ways that enabled same-sex sexual practices. Previously unpublished archival materials concerning the situation of LGB tourists, including investigative files produced by Polish and Bulgarian security services as well as the…

Read at Journal articles (OpenAlex)

arXiv (research papers) Fazhong Liu SI

Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation

World models give embodied AI a predictive core: they compress observations into states, simulate action-conditioned futures, and enable planning beyond reactive control. This predictive layer, however, opens a new security boundary-compromise can propagate from data, sensors, prompts, or feedback into physical action. Rather than treating world models as an isolated component, this survey traces threats across their entire lifecycle-from data construction and representation…

Read at arXiv (research papers)

Journal articles (OpenAlex) Yelena IZTELEUOVA · Frontiers in Political Science Geopolitics

Coordination of bilateral and multilateral cooperation in Central Asia under conditions of polycrisis

Regional cooperation in Central Asia is characterized by divergent national preferences and overlapping institutional mandates that generate coordination challenges rather than systemic failure. This decentralized cooperation architecture unfolds in a broader context of polycrisis, understood as the interaction of overlapping geopolitical, economic and security pressures shaping regional governance dynamics. The post-2016 period, marked by Uzbekistan’s political transition…

Read at Journal articles (OpenAlex)

Asia Times Benjamin Stuart Reed South China Sea

Watching American power tentatively arrive in the Philippines

OYSTER BAY, PALAWAN – When American forces withdrew from Iraq in 2011, I watched it happen from Kuwait, where I worked as a contracted security guard. The last convoy crossed the berm that December — roughly 100 vehicles — and with it went the war in which I had served. Two years later, at a

Read at Asia Times

Journal articles (OpenAlex) Byron Villacís · Frontiers in Political Science Geopolitics

Manufactured invisibility: statistical infrastructure erosion and the reconfiguration of anticorruption and anti–organized crime capacity in Ecuador

Introduction Ecuador’s recent security crisis has unfolded alongside a quieter institutional shift: the weakening of the statistical infrastructures through which the state documents crime, violence, justice performance, and corruption-relevant dynamics. This study examines how that erosion reshapes the evidentiary conditions under which states confront corruption and organized crime. It develops the concept of manufactured invisibility to describe the cumulative degradation…

Read at Journal articles (OpenAlex)

Older stories