Results for “Data”

arXiv (research papers) Dongcheng Zhang SI

Owner-Harm: A Missing Threat Model for AI Agent Safety

Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own deployers. Real-world incidents illustrate the gap: Slack AI credential exfiltration (Aug 2024), Microsoft 365 Copilot calendar-injection leaks (Jan 2024), and a Meta agent unauthorized forum post exposing operational data (Mar 2026). We propose…

Read at arXiv (research papers)

arXiv (research papers) Anes Abdennebi SI

Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference

The applications of Generative Artificial Intelligence (GenAI) and their intersections with data-driven fields, such as healthcare, finance, transportation, and information security, have led to significant improvements in service efficiency and low latency. However, this synergy raises serious concerns regarding the security of large language models (LLMs) and their potential impact on the privacy of companies and users' data. Many technology companies that incorporate LLMs…

Read at arXiv (research papers)

arXiv (research papers) Zedian Shao SI

Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection

Multi-modal large language models (MLLMs) have emerged as powerful tools for analyzing Internet-scale image data, offering significant benefits but also raising critical safety and societal concerns. In particular, open-weight MLLMs may be misused to extract sensitive information from personal images at scale, such as identities, locations, or other private details. In this work, we propose ImageProtector, a user-side method that proactively protects images before sharing by…

Read at arXiv (research papers)

Journal articles (OpenAlex) Pasquale Giacobbe, Andrea Mosca, Patrizia Ordine et al. · European Journal of Political Economy Geopolitics

Help-seeking after gender-based violence: The role of local female political representation

Using data from Italy’s largest network of anti-violence centers (AVCs), this study investigates whether increased female representation in local politics affects women’s access to formal support services after experiencing gender-based violence. We focus on access to AVCs, as it represents a concrete step and a potential turning point toward escaping violence–distinct from more informal or exploratory forms of help-seeking. Exploiting staggered elections and the…

Read at Journal articles (OpenAlex)

Oxfam International Cass Hebron

Death by aid cuts: Oxfam reaction to OECD preliminary data on aid spending in 2025

Death by aid cuts: Oxfam reaction to OECD preliminary data on aid spending in 2025 Cass Hebron Thu, 04/09/2026 - 13:00 Off In response to the publication today of the Organization for Economic Cooperation and Development’s (OECD) preliminary data on Official Development Assistance (ODA) for 2025, Oxfam’s Development Finance Lead Didier Jacobs said: “Wealthy governments are turning their backs on the lives of millions of women, men and children in the Global South with these…

Read at Oxfam International

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) Rahul Balamurugan, Preethi Nanjundan, Avichal Sharma · Northeast Journal of Complex Systems Geopolitics

Complex Systems Mapping of Fiscal Growth Dynamics at Strategic Maritime Chokepoints Using Time-Series Slopes

This study examines how maritime and trading states allocate public resources between defence, health, and economic growth around three strategic chokepoints the Strait of Malacca, the Strait of Hormuz, and the Suez Canal. The analysis extends the classic “guns versus butter” framing by treating defence and health spending as co-evolving components of an interconnected fiscal-growth system. Using World Development Indicators data (1999-2024), trend slopes are estimated for…

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) 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)

Journal articles (OpenAlex) Mustafa Disli, Shakir Jalaly, Laurent Weill · Economics of Transition and Institutional Change Geopolitics

Do Women Make Better Borrowers and Loan Officers? Evidence From Afghanistan

ABSTRACT This study explores how gender is associated with microfinance loan performance in Afghanistan, a conservative and conflict‐affected society. We use data from over 9500 borrowers across Taliban‐ and government‐controlled areas for the period from January 2017 to February 2020, before the 2021 Taliban takeover. We analyse how borrower and loan officer gender are related to loan outcomes. Contrary to prevailing literature, our findings reveal that female borrowers…

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)

Rappler Ralph Romulus Arias Frondoza, Amadeus Quiaoit South China Sea

[OPINION] The West Philippine Sea is also a digital battlefield

The nature of the conflict has already changed. Data, narratives, and perception shape it.

Read at Rappler

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)

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) Lorenzo Rotunno, Sanchari Roy, Anri Sakakibara et al. · The World Bank Economic Review Geopolitics

Trade Policy and Jobs in Vietnam: The Unintended Consequences of US–China Tariffs

Abstract This paper uses the US–China tariffs of 2018–2019 as an exogenous shock to export opportunities in Vietnam to identify how trade policy affects job creation. Using a difference-in-differences framework, it first shows that the US tariffs on China increased the range of products exported by Vietnam to the United States in the two years after the tariffs hit. Using firm-level data, it then shows that this expansion in export opportunities led to job creation. Around 5…

Read at Journal articles (OpenAlex)

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) 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)

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)

arXiv (research papers) Michael Hind SI

LLMON: An LLM-native Markup Language to Leverage Structure and Semantics at the LLM Interface

Textual Large Language Models (LLMs) provide a simple and familiar interface: a string of text is used for both input and output. However, the information conveyed to an LLM often has a richer structure and semantics, which is not conveyed in a string. For example, most prompts contain both instructions ("Summarize this paper into a paragraph") and data (the paper to summarize), but these are usually not distinguished when passed to the model. This can lead to model…

Read at arXiv (research papers)

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) Abed K. Musaffar SI

Detection of adversarial intent in Human-AI teams using LLMs

Large language models (LLMs) are increasingly deployed in human-AI teams as support agents for complex tasks such as information retrieval, programming, and decision-making assistance. While these agents' autonomy and contextual knowledge enables them to be useful, it also exposes them to a broad range of attacks, including data poisoning, prompt injection, and even prompt engineering. Through these attack vectors, malicious actors can manipulate an LLM agent to provide…

Read at arXiv (research papers)

arXiv (research papers) Shawn Li SI

The Autonomy Tax: Defense Training Breaks LLM Agents

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against prompt injection attacks that manipulate agent behavior through malicious observations or retrieved content. We reveal a fundamental \textbf{capability-alignment paradox}: defense training designed to improve safety systematically destroys…

Read at arXiv (research papers)

arXiv (research papers) Haocheng Li SI

Parameter-Efficient Modality-Balanced Symmetric Fusion for Multimodal Remote Sensing Semantic Segmentation

Multimodal remote sensing semantic segmentation enhances scene interpretation by exploiting complementary physical cues from heterogeneous data. Although pretrained Vision Foundation Models (VFMs) provide strong general-purpose representations, adapting them to multimodal tasks often incurs substantial computational overhead and is prone to modality imbalance, where the contribution of auxiliary modalities is suppressed during optimization. To address these challenges, we…

Read at arXiv (research papers)

arXiv (research papers) Saikat Maiti SI

Caging the Agents: A Zero Trust Security Architecture for Autonomous AI in Healthcare

Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research demonstrates that these agents exhibit critical vulnerabilities in realistic settings: unauthorized compliance with non-owner instructions, sensitive information disclosure, identity spoofing, cross-agent propagation of unsafe practices, and indirect…

Read at arXiv (research papers)

arXiv (research papers) Vanshaj Khattar SI

Amplification Effects in Test-Time Reinforcement Learning: Safety and Reasoning Vulnerabilities

Test-time training (TTT) has recently emerged as a promising method to improve the reasoning abilities of large language models (LLMs), in which the model directly learns from test data without access to labels. However, this reliance on test data also makes TTT methods vulnerable to harmful prompt injections. In this paper, we investigate safety vulnerabilities of TTT methods, where we study a representative self-consistency-based test-time learning method: test-time…

Read at arXiv (research papers)

arXiv (research papers) Mateusz Dziemian SI

How Vulnerable Are AI Agents to Indirect Prompt Injections? Insights from a Large-Scale Public Competition

LLM based agents are increasingly deployed in high stakes settings where they process external data sources such as emails, documents, and code repositories. This creates exposure to indirect prompt injection attacks, where adversarial instructions embedded in external content manipulate agent behavior without user awareness. A critical but underexplored dimension of this threat is concealment: since users tend to observe only an agent's final response, an attack can conceal…

Read at arXiv (research papers)

Journal articles (OpenAlex) Lillian Artz, Lisa Vetten, Harsha Gihwala et al. · Higher Education Research & Development Geopolitics

Gender-based violence in higher education institutions in Cuba and Mexico: A comparative analysis of awareness, institutional response, and policy gaps

This article explores gender-based violence (GBV) in ten higher education institutions (HEIs) across Cuba and Mexico. Drawing on a literature review and primary data, this paper examines how GBV is experienced, perceived, and addressed within academic environments in both countries. The high level findings show that – despite formal commitments to gender equality by both governments and HEIs – limited awareness of institutional procedures among both students and staff, and a…

Read at Journal articles (OpenAlex)

Older stories