Results for “Security”

arXiv (research papers) Runpeng Geng SI

PIArena: A Platform for Prompt Injection Evaluation

Prompt injection attacks pose serious security risks across a wide range of real-world applications. While receiving increasing attention, the community faces a critical gap: the lack of a unified platform for prompt injection evaluation. This makes it challenging to reliably compare defenses, understand their true robustness under diverse attacks, or assess how well they generalize across tasks and benchmarks. For instance, many defenses initially reported as effective were…

Read at arXiv (research papers)

arXiv (research papers) Nicolás E. Díaz Ferreyra SI

Security Concerns in Generative AI Coding Assistants: Insights from Online Discussions on GitHub Copilot

Generative Artificial Intelligence (GenAI) has become a central component of many development tools (e.g., GitHub Copilot) that support software practitioners across multiple programming tasks, including code completion, documentation, and bug detection. However, current research has identified significant limitations and open issues in GenAI, including reliability, non-determinism, bias, and copyright infringement. While prior work has primarily focused on assessing the…

Read at arXiv (research papers)

Journal articles (OpenAlex) Madhav Joshi, Grace Sullivan · Australian Journal Of International Affairs Geopolitics

Where are the international allies of Afghan women?

The Women, Peace, and Security (WPS) agenda has provided a gendered governance framework for conflict prevention and international peacebuilding for the last twenty-five years. Under the Taliban’s rule in Afghanistan, women and girls face ‘gender apartheid,’ including bans on education and employment, exclusion from public spaces, and widespread gender-based violence. This discussion presents data on the international community’s interactions with the Taliban collected…

Read at Journal articles (OpenAlex)

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) Zhuowen Yuan SI

ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems

Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. However, as agents increasingly rely on third-party tools and MCP servers, a new class of supply-chain threats has emerged, where malicious behaviors are embedded in seemingly benign tools, silently hijacking agent execution, leaking sensitive data, or triggering unauthorized actions. Despite their growing impact, there is currently no comprehensive benchmark for…

Read at arXiv (research papers)

arXiv (research papers) Fariha Tanjim Shifat SI

LLM-Enabled Open-Source Systems in the Wild: An Empirical Study of Vulnerabilities in GitHub Security Advisories

Large language models (LLMs) are increasingly embedded in open-source software (OSS) ecosystems, creating complex interactions among natural language prompts, probabilistic model outputs, and execution-capable components. However, it remains unclear whether traditional vulnerability disclosure frameworks adequately capture these model-mediated risks. To investigate this, we analyze 295 GitHub Security Advisories published between January 2025 and January 2026 that reference…

Read at arXiv (research papers)

arXiv (research papers) Dalal Alharthi SI

Automating Cloud Security and Forensics Through a Secure-by-Design Generative AI Framework

As cloud environments become increasingly complex, cybersecurity and forensic investigations must evolve to meet emerging threats. Large Language Models (LLMs) have shown promise in automating log analysis and reasoning tasks, yet they remain vulnerable to prompt injection attacks and lack forensic rigor. To address these dual challenges, we propose a unified, secure-by-design GenAI framework that integrates PromptShield and the Cloud Investigation Automation Framework…

Read at arXiv (research papers)

arXiv (research papers) Wenhui Zhu SI

Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose severe security challenges. Specifically, Indirect Prompt Injections (IPI), which conceal malicious instructions within third-party content, can trigger unauthorized actions such as data exfiltration during normal operations. While current…

Read at arXiv (research papers)

arXiv (research papers) Yilin Xiao SI

LogicPoison: Logical Attacks on Graph Retrieval-Augmented Generation

Graph-based Retrieval-Augmented Generation (GraphRAG) enhances the reasoning capabilities of Large Language Models (LLMs) by grounding their responses in structured knowledge graphs. Leveraging community detection and relation filtering techniques, GraphRAG systems demonstrate inherent resistance to traditional RAG attacks, such as text poisoning and prompt injection. However, in this paper, we find that the security of GraphRAG systems fundamentally relies on the…

Read at arXiv (research papers)

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) Thomas J. Trebat · Journal of Economic Issues Geopolitics

From Extraction to Development: Critical Minerals and Inclusive Industrialization in Latin America

This paper revisits Latin America’s structuralist and neo-structuralist traditions to examine if the region’s lithium endowment can support a new pathway of inclusive industrialization, in which lithium production is rooted in national sovereignty and contributes to global energy security and decarbonization. The global push for decarbonization, especially through transport electrification, has sharply increased demand for critical minerals, including lithium. While China…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Jeffrey A. Larsen, James J. Wirtz · Defence Studies Geopolitics

Providing nuclear deterrence and assurance in Europe and East Asia: the submarine-launched cruise missile

The deployment of a new submarine-launched cruise missile (SLCM) by the U.S. Navy would have multiple benefits for deterrence and assurance in Europe and East Asia, the major theatres of concern for American defence planners. While there are distinctions in the role and impact a nuclear version of SLCM might play in both regions, some elements of the U.S. national security establishment believe that its deployment with maritime forces would enhance deterrence and assurance…

Read at Journal articles (OpenAlex)

arXiv (research papers) Chong Xiang SI

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our vision for system-level defenses against indirect prompt injection attacks. We articulate three positions: (1) dynamic replanning and security policy updates are often necessary for dynamic tasks and realistic environments; (2) certain…

Read at arXiv (research papers)

InSight Crime Gavin Voss

From Airstrikes to Cooperation: Will the ‘New Phase’ of Ecuador’s Drug War Deliver?

From Airstrikes to Cooperation: Will the ‘New Phase’ of Ecuador’s Drug War Deliver? Ecuador's revamping of old security measures like curfews and mass arrests of suspected gang collaborators are now being complemented with airstrikes backed by the United States and operations against transatlantic drug trafficking organizations in tandem with European agencies. But will this new phase be any better than the old one?

Read at InSight Crime

arXiv (research papers) Quan Zhang SI

Evaluating Privilege Usage of Agents with Real-World Tools

Equipping LLM agents with real-world tools can substantially improve productivity. However, granting agents autonomy over tool use also transfers the associated privileges to both the agent and the underlying LLM. Improper privilege usage may lead to serious consequences, including information leakage and infrastructure damage. While several benchmarks have been built to study agents' security, they often rely on pre-coded tools and restricted interaction patterns. Such…

Read at arXiv (research papers)

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)

arXiv (research papers) Alexandre Cristovão Maiorano SI

Evaluating Prompt Injection Defenses for Educational LLM Tutors: Security-Usability-Latency Trade-offs

Educational LLM tutors face a core AI alignment challenge: they must follow user intent while preserving pedagogical constraints and safety policies. We present an evaluation methodology for prompt-injection defenses in this setting, showing that guardrail design entails explicit trade-offs among adversarial robustness, benign-task usability, and response latency. We evaluate a domain-specific multi-layer safeguard pipeline combining deterministic pattern filters, structural…

Read at arXiv (research papers)

arXiv (research papers) Surada Suwansathit SI

A Security Analysis of the OpenClaw AI Agent Framework

AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a systematic taxonomy of 470 advisories filed against OpenClaw, an open-source AI agent runtime, organized by architectural layer and trust-violation type. Vulnerabilities cluster along two orthogonal axes: (1) the system axis, reflecting the…

Read at arXiv (research papers)

arXiv (research papers) Haoyu Wang SI

SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants

LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the potential of locally deployed agents integrated with personal data and services, but this autonomy introduces significant safety and security risks. Unintended actions from LLM reasoning failures can cause irreversible harm, while prompt injection attacks may exfiltrate credentials or compromise the…

Read at arXiv (research papers)

Journal articles (OpenAlex) Titus Chih-Chieh Chen, Wei‐Feng Tzeng · Journal of Chinese Political Science Geopolitics

China’s Security Signaling in the Taiwan Strait: Narratives and Patterns (2016–2024)

Abstract This paper examines patterns in geo-strategic narratives associated with China's security signaling in the Taiwan Strait since 2020, showing that variations in China’s pressure-oriented diplomatic messaging are associated not only with reactions to U.S. or Taiwanese actions, but also with Beijing’s reassessment of global power dynamics—framed as the “great changes unseen in a century”—and growing confidence in its national capabilities. To test this argument, the…

Read at Journal articles (OpenAlex)

arXiv (research papers) Hieu Xuan Le SI

Prompt Attack Detection with LLM-as-a-Judge and Mixture-of-Models

Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems. In production, guardrails must mitigate these attacks under strict low-latency constraints, resulting in a deployment gap in which lightweight classifiers and rule-based systems struggle to generalize under distribution shift, while high-capacity LLM-based judges remain too slow or costly for live enforcement. In this work, we examine whether…

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)

Journal articles (OpenAlex) Adolfo Donoso, Jorge González, José Ignacio Lagos · Chilean journal of agricultural research Geopolitics

Economic assessment of Chilean agricultural land use, labor demand and input requirements using the Delphi method. Part B: Vegetables for fresh consumption

Among the main food items purchased by households, the market for fresh vegetables plays a strategic role in food security in Chile by ensuring access to healthy and affordable diets.This study aimed to analyze the dynamics of fresh vegetable markets and prices in Chile between 2017 and 2021, with a focus on productivity, farm structure, agrochemical use, and the implications for food system resilience.Using a modified Delphi method, we generated technical-economic estimates…

Read at Journal articles (OpenAlex)

Stimson Center Communications Geopolitics

North Africa Regional Outlook: March 25, 2026

From Sahel security recalibration to Iran war aftershocks, North Africa faces energy shocks, fiscal strain, and intensifying competition over influence.

Read at Stimson Center

Inter-American Dialogue Yifang Wang Geopolitics

Testimony to the U.S.-China Economic and Security Review Commission: China’s Expanding Interests in Latin America

Testimony by Senior Advisor Margaret Myers to the U.S.-China Economic and Security Review Commission on China’s evolving economic and strategic engagement in Latin America and the Caribbean.

Read at Inter-American Dialogue

Journal articles (OpenAlex) Mauricio Salgado · International Migration Review Geopolitics

Beyond Cultural Threat: Causal Evidence on Chileans’ Attitudes Toward Intraregional Immigrants From a Factorial-Survey Experiment

Research on immigration attitudes rarely examines contexts in which immigrants and natives share substantial cultural proximity. Leveraging Chile's recent intraregional inflow — a context that allows us to hold cultural distance constant — this study analyzes whether labor-market, family status, fiscal, and security concerns shape public opinion in the absence of cultural threat. We embedded a factorial - survey experiment in a nationally representative poll, randomizing…

Read at Journal articles (OpenAlex)

arXiv (research papers) Qianlong Lan SI

The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense

Deploying large language models (LLMs) as autonomous browser agents exposes a significant attack surface in the form of Indirect Prompt Injection (IPI). Cloud-based defenses can provide strong semantic analysis, but they introduce latency and raise privacy concerns. We present the Cognitive Firewall, a three-stage split-compute architecture that distributes security checks across the client and the cloud. The system consists of a local visual Sentinel, a cloud-based Deep…

Read at arXiv (research papers)

Inter-American Dialogue Yifang Wang Geopolitics

From Production to Consumption: Japan–Latin America Cooperation in Food and Agriculture

The event considered the enduring engagement between Japan and Latin America and the Caribbean (LAC) to advance shared interests in agricultural development, economic security, and resilient supply chains amid a shifting global landscape.

Read at Inter-American Dialogue

arXiv (research papers) Yechao Zhang SI

Mind Your HEARTBEAT! Claw Background Execution Inherently Enables Silent Memory Pollution

We identify a critical security vulnerability in mainstream Claw personal AI agents: untrusted content encountered during heartbeat-driven background execution can silently pollute agent memory and subsequently influence user-facing behavior without the user's awareness. This vulnerability arises from an architectural design shared across the Claw ecosystem: heartbeat background execution runs in the same session as user-facing conversation, so content ingested from any…

Read at arXiv (research papers)

Older stories