Results for “without”

arXiv (research papers) Xabier Muruaga SI

Bounded Agents: Delegation Security for Multi-Agent AI Systems

LLM-based agents can act on behalf of a user to access cloud services, call tools, or invoke agents. At session start, the agent's permissions are set but remain static, and each request is evaluated independently, without considering prior actions. Within its permissions, an agent may act contrary to the delegated task, combine individually permitted actions into a prohibited outcome, or delegate authority to a sub-agent without limiting it. A prompt injection poses a risk…

Read at arXiv (research papers)

arXiv (research papers) Madhusudhanan G SI

Visible Reasoning and Indirect Prompt-Injection Monitorability Across English, Tamil, and Tanglish

Chain-of-thought monitoring is a potentially useful safety signal, but its reliability across languages and behavioral settings remains uncertain. In a small case study of eight manually verified synthetic scenarios, one model, one annotator, and one deterministic generation seed, I study API-visible reasoning during indirect prompt injection in Sarvam-105B across English, Tamil, and Tanglish. A four scenario pilot found 5/12 injected attack successes without reasoning and…

Read at arXiv (research papers)

Journal articles (OpenAlex) Titus Chih-Chieh Chen, Nien‐chung Chang‐Liao · International Interactions Geopolitics

Sunk costs without tying hands: Multiple signaling in China’s coercive diplomacy during the 2022 Taiwan Strait Crisis

This paper investigates China’s coercive diplomacy during the 2022 Taiwan Strait Crisis. Using quantitative natural language processing techniques, we unveil the key emotional, operational, and semantic characteristics of China’s propaganda campaigns during Pelosi’s Taiwan visit. While the literature focuses on how China signals its resolve in diplomatic disputes by generating audience costs, we find that Beijing’s coercive diplomacy relies on sunk-cost rather than…

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)

Journal articles (OpenAlex) Imrana Alhaji Buba · Journal of Peace Research Geopolitics

Civilian compliance and victimization in the Boko Haram insurgency

Abstract How does variation in civilian compliance strategies shape wartime victimization? Across civil wars, some contested communities are displaced while others remain in place despite exposure to armed actors. Existing research explains civilian victimization primarily through armed actors' strategies, with limited attention to how civilians shape its form. I argue that civilian compliance, defined as accommodating the demands of armed actors without formally joining…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Collins Uchenna Chimeleze, Norziana Jamil, Zuhaira Muhammad Zain et al. · Scientific Reports Gadgets

Intelligent malware detection on Android smartphones via a hybrid approach using gradient boosting and convolutional neural network

Malware is malicious software that infiltrates systems without user consent. Effective detection involves identifying such software and distinguishing it from benign programs. While machine learning has shown promise in malware detection, many existing techniques demand extensive feature engineering and representation, leading to higher computation times and error rates. To address these limitations, we propose CNN-GBM, a hybrid model combining Convolutional neural networks…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Lena Molnar, Sarah McCook · Social Sciences Geopolitics

“Everyone’s Moving, and Learning Together”: Young People and Practitioners Working with Collective Care to Create Futures Without Gender-Based Violence

Gender-based violence may be considered a failure or absence of care across the interpersonal, symbolic, and structural levels. Feminist scholars have called for closer attention to an ethic of care as one vital pathway to shared solidarity for social justice and relations of non-violence. Works from Black, Indigenous, queer and disability writers and activists have similarly illustrated the transformative potential of collective care for building community and ending…

Read at Journal articles (OpenAlex)

arXiv (research papers) Shihao Weng SI

AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection

Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters. In practice, user requests are often underspecified: they describe the desired outcome without fully specifying acceptable behavior. An injection can exploit this ambiguity, causing the agent to complete the task in a way the user would reject. As the user's expectations become clearer through concrete cases, a…

Read at arXiv (research papers)

Global Voices Liam Anderson

In Brazil, court ruling sheds light on the story of an undocumented and stateless woman

After 40 years without documents or an official identity, a woman born in Bolivia was able to regularize her immigration status and begin the process of recognition as a stateless person.

Read at Global Voices

Latinoamérica21 Florencia Davidzon Geopolitics

The last ownerless territory: Antarctica and the 2048 window

As 2048 approaches, Antarctica's greatest challenge is no longer sovereignty, but the construction of a global framework to protect the last territory without an owner. O post The last ownerless territory: Antarctica and the 2048 window apareceu primeiro em Latinoamérica 21.

Read at Latinoamérica21

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)

Oxfam International Nesrine Aly

Gaza’s $71bn reconstruction will cost seven times all previous rebuilds combined, and will fail without Palestinian leadership – Oxfam warns

Gaza’s $71bn reconstruction will cost seven times all previous rebuilds combined, and will fail without Palestinian leadership – Oxfam warns Nesrine Aly Wed, 07/22/2026 - 21:00 Off Oxfam and Palestinian organisations hand world leaders a blueprint for Gaza's recovery — one that puts Palestinian ownership and accountability for Israel's genocide at its core. The $71.4 billion needed to rebuild Gaza is seven times, in real terms, the combined cost of reconstruction after every…

Read at Oxfam International

Latinoamérica21 Ernesto Hernández Norzagaray Geopolitics

Perestroika without glasnost in Venezuela and Cuba

Venezuela and Cuba are experimenting with a limited economic opening to preserve political control, following the model of China and Vietnam without opening the door to democratic freedoms. O post Perestroika without glasnost in Venezuela and Cuba apareceu primeiro em Latinoamérica 21.

Read at Latinoamérica21

Illiberalism Studies Program (GWU) Paul Vacca Geopolitics

Elon Musk and SpaceX’s Futurist Coup

From January to May 2025, for nearly 130 days, the world’s richest man set out to position himself at the summit of global power. Without any elected mandate, he was...

Read at Illiberalism Studies Program (GWU)

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) Hugo García Cuesta SI

Multi-Agent Firewall Architecture for Privacy Protection of Sensitive Data in Interactions with Language Models

While Large Language Models (LLMs) have become essential productivity tools, their integration into workflows without adequate safeguards creates significant risks. This paper proposes an open-source, privacy-focused, user-facing firewall designed to secure both web-based and programmatic LLM interactions. The architecture combines a browser extension and a proxy for total traffic interception across both HTTP(S) and WebSocket communications. At its core, a flexible…

Read at arXiv (research papers)

arXiv (research papers) Aya Spira SI

Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks via Universal and Transferable Adversarial HalluSquatting

The growing adoption of agentic LLM applications has introduced a new threat previously named as promptware. While prior work has established that adversaries can exploit direct channels to LLM applications to apply promptware under weak threat models, many applications do not provide any direct channels that could be exploited for prompt injection beyond the Internet. This raises a question: can attackers exploit LLM applications at scale without any direct channels in…

Read at arXiv (research papers)

arXiv (research papers) Kristina Nikolić SI

Untrusted Content Masking for Web Agents with Security Guarantees

Defenses that provide security guarantees against prompt injection attacks rely on strict isolation between trusted instructions and untrusted data. In text-based environments such as tool-use APIs, this separation arises naturally: agents can reason from interface definitions without ever processing untrusted content. Extending these guarantees to web agents faces a fundamental challenge: to perceive and interact with their environment, web agents must first observe the…

Read at arXiv (research papers)

Journal articles (OpenAlex) Ana Inés Langer, Lluis de Nadal, Eugenia Mitchelstein · Social Media + Society Geopolitics

From Fringe to Power in the TikTok Age: Libertarian Ideology and Transgressive Performances in Milei’s ‘Populism Without the People’

Democracies around the world are under strain from radical right populist leaders and parties, raising urgent questions about their appeal. One way to approach this is by examining what and how they communicate on social media. TikTok warrants close attention, not only as the fastest-growing platform for news and information, but also because of the wider ‘Tiktokification’ of social media and the growing importance of visual communication. Yet populist communication on…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Violet Cheung‐Blunden, Serena Rajkumar, Yuka Hirata et al. · The Journal of Social Psychology Geopolitics

Threat-Induced Conservatism in a Liberal Electorate: Issue-Based Shifts without Ideological Transformation

Psychology theories of threat management posit that perceived threats can drive individuals toward security-focused, often conservative, policies. Yet, evidence for a threat-induced conservative shift has been inconsistent across studies, raising the possibility that such effects are contingent on the political context. The present studies were conducted in a novel context by recruiting voters in a liberal-leaning city prior to voting on a local ballot measure to revise the…

Read at Journal articles (OpenAlex)

Havana Times Circles Robinson

Can Economic Reform Work in Cuba Without Political Reform?

Cuba's fundamental challenge: Can meaningful economic reform endure within a political system structurally designed to constrain it?

Read at Havana Times

The Guardian Belarus Guardian staff and agencies Geopolitics

Ukraine war briefing: Zelenskyy to Belarus – remove Russian relay stations or ‘we’ll do it’

Zelenskyy says a week should be enough time for Belarus to remove stations, calls for a stop to refined oil supplies to Russian army. What we know on day 1,578 Volodymyr Zelenskyy said a week should be enough for the Belarusian leader, Alexander Lukashenko, to remove equipment from Belarus used by ⁠Russia in its attacks on ⁠Ukraine. “If he doesn’t do it, we’ll do it,” said the Ukrainian president, without elaborating. Zelenskyy said signal relay stations were located in two…

Read at The Guardian Belarus

arXiv (research papers) Zunchen Huang SI

Analyzing the Narration Gap in LLM-Solver Loops

Formal tools such as SAT and SMT solvers are increasingly embedded in language model reasoning pipelines when a safety or security critical question can be formulated in logic. Unlike chain of thought whose steps are sampled from the model distribution without formal guarantee, a solver produces a sound and independently verifiable answer. However, the soundness guarantee can be lost in the interaction between the solver and the model. The hybrid pipeline has three…

Read at arXiv (research papers)

The Guardian Somalia Mohamed Gabobe in Mogadishu and Mark Townsend

Seven-year-old Abdiqadir was hit in a US airstrike. Without a $750 operation, he may lose his ability to walk

Abdiqadir Salah was pierced by shrapnel in a bombing that killed 12 in Somalia. But as the US denies civilians were hurt they face no hope of compensation

Read at The Guardian Somalia

Inter-American Dialogue Giulia Branco Spiess Geopolitics

Brazil’s Quiet Arms Ambition: How Brasília Builds Military Power Without Becoming a Military Power

Brazil has made impressive strides as an arms producer and exporter. In an increasingly turbulent world, it can be expected to try to build on them.

Read at Inter-American Dialogue

Journal articles (OpenAlex) Jalal Bazwan, Ihsanullah Omarkhail · Pacific Focus Geopolitics

China's Security‐First Strategy in Afghanistan: Rethinking the Wakhan Corridor

ABSTRACT This study examines China's approach to the Wakhan Corridor and argues that Beijing's policy toward Afghanistan is shaped primarily by a Hierarchical Security‐Development Nexus reinforced through China's National Security Concept. While recent Afghanistan‐Pakistan trade disruptions have increased Kabul's interest in Wakhan as an alternative route, China remains unwilling to advance connectivity without credible security guarantees. Drawing on policy analysis, field…

Read at Journal articles (OpenAlex)

arXiv (research papers) Lena S. Bolliger SI

Training LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference Optimization

Production LLMs receive instructions from sources with very different levels of trust, yet attend to every token with uniform architectural privilege. This is the structural vulnerability that enables malicious prompt injections and, more broadly, leaves models without a principled way to resolve conflicts between legitimate but competing instructions. A common training-based response is to teach models an explicit instruction hierarchy; existing approaches, however…

Read at arXiv (research papers)

Asia Times Marcus Loh South China Sea

With or without China, Shangri-La Dialogue is still relevant

Former Straits Times editor-in-chief Warren Fernandez writes with characteristic elegance in his latest RSIS piece, “With or Without You: The U2 Doctrine Comes to Shangri-La”, carried in The Straits Times on June 3, 2026. The piece gives cause for three reflections from this year’s Shangri-La Dialogue: whether middle power coalitions can substitute for hard power;

Read at Asia Times

arXiv (research papers) Jafar Isbarov SI

GitInject: Real-World Prompt Injection Attacks in AI-Powered CI/CD Pipelines

AI agents are increasingly embedded in continuous integration and continuous delivery (CI/CD) workflows to autonomously review pull requests, triage issues, and maintain codebases. We study fully automated configurations in which external contributions invoke agents without prior human approval. Because these agents ingest untrusted content while operating with repository credentials and tools, prompt injection can have software supply chain consequences. We present…

Read at arXiv (research papers)

Journal articles (OpenAlex) Phuong T Nguyen · Journal of Comparative & International Higher Education Geopolitics

Regionalization Without a Roadmap: Stakeholder Conceptions of ASEAN Integration at Vietnam National University Hanoi

This study examines stakeholder conceptions of regionalization of higher education at Vietnam National University Hanoi (VNU). Regionalization remains unevenly understood in Southeast Asia and often overshadowed by internationalization discourses. Drawing on document analysis and semi-structured interviews with administrators, faculty, and students, the study explores how regionalization is enacted through student mobility programs. Findings reveal divergent rationales…

Read at Journal articles (OpenAlex)

Older stories