Results for “Security”

arXiv (research papers) Ali Dehghantanha SI

SoK: The Attack Surface of Agentic AI - Tools and Autonomy

Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation (RAG), and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly enlarges the attack surface. In this systematization, we map out the trust boundaries and security risks of agentic LLM-based systems. We develop a comprehensive taxonomy of attacks spanning prompt-level injections, knowledge-base…

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)

Journal articles (OpenAlex) Kerstin Tomiak, Katharina P. Coleman · Security Dialogue Geopolitics

Performing as local staff: work strategies of Afghan employees in NATO's ISAF operation

Abstract This article explores the work strategies through which Afghan local staff employed by NATO's International Security Assistance Force (ISAF) sought to navigate a hierarchical and mistrustful work environment in which they held structurally subordinate positions. Drawing on sociological and feminist theories of performance and performativity and based on in-depth interviews with 17 former ISAF employees, the article identifies three performance strategies through…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Jack Holland, Harrison Swinhoe · International Studies Quarterly Geopolitics

Ontological Security beyond Binaries: Islamic State’s brOthering of Jihadist Competitors through Genocide

Abstract Ontological Security Theory has established that states pursue stable identities through autobiographical stories. Likewise, Genocide Studies has shown the importance of narrative for identity construction prior to instances of existential violence. However, these literatures have tended to focus on the narration of binary relations between Self and Other. Instead, we develop a novel account of non-state, and non-Western, ontological security-seeking behavior with a…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Øystein H. Rolandsen, Ursula C. Schroeder, Simone Tholens et al. · International Studies Review Geopolitics

Security Assistance and the Crisis of the Liberal International Order

Abstract The crisis of the Liberal International Order (LIO) has intensified amid growing great-power competition, the war in Ukraine, and the erosion of multilateral institutions. This Forum examines security assistance (SA)—the training, equipping and support of external security actors—as a critical lens for understanding how this crisis is unfolding and how international order is increasingly contested in practice. The Forum consists of an introductory essay and nine…

Read at Journal articles (OpenAlex)

arXiv (research papers) Vincent Siu SI

A Framework for Formalizing LLM Agent Security

Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective is being pursued, and whether the action serves that objective. However, existing definitions of security attacks against LLM agents often fail to capture this contextual nature. As a result, defenses face a fundamental utility-security tradeoff: applying…

Read at arXiv (research papers)

Journal articles (OpenAlex) Oliver P. Richmond, Roger Mac Ginty · Global Change Peace & Security Geopolitics

Peace and the debacles of Afghanistan and Iraq: Lessons for future peacemaking and peacebuilding scholarship

Critical knowledge production and the accumulated knowledge and practices around peace and intervention was largely ignored in relation to the Western interventions in Iraq and Afghanistan. Subsequent stabilisation exercises indicated a continuing tendency to adopt a Western epistemic lens and ignore local and regional contexts and perspectives. This was either ignored or co-opted by ‘global’ security concerns (seen through an American prism), and has laid the way for the…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yuntong Zhang SI

VeriGrey: Greybox Agent Validation

Agentic AI has been a topic of great interest recently. A Large Language Model (LLM) agent involves one or more LLMs in the back-end. In the front end, it conducts autonomous decision-making by combining the LLM outputs with results obtained by invoking several external tools. The autonomous interactions with the external environment introduce critical security risks. In this paper, we present a grey-box approach to explore diverse behaviors and uncover security risks in LLM…

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)

OWASP GenAI Security Project Scott Clinton, Project Co-lead Security

OWASP GenAI Security Project Expands AI Security Frameworks Ahead of RSA 2026, Celebrates Continued Sponsor Support

New resources, a full week of RSA programming and growing industry adoption mark a milestone moment for the open-source AI security community WILMINGTON, Del. — March 19, 2026 — The OWASP GenAI Security Project (genai.owasp.org), a leading global open-source and expert community, growing to more than 25K members, dedicated to delivering practical guidance and tools

Read at OWASP GenAI Security Project

arXiv (research papers) Zijian Ling SI

Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs

Speech-driven large language models (LLMs) are increasingly accessed through speech interfaces, introducing new security risks via open acoustic channels. We present Sirens' Whisper (SWhisper), the first practical framework for covert prompt-based attacks against speech-driven LLMs under realistic black-box conditions using commodity hardware. SWhisper enables robust, inaudible delivery of arbitrary target baseband audio-including long and structured prompts-on commodity…

Read at arXiv (research papers)

arXiv (research papers) Chenlong Yin SI

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks remains insufficiently evaluated, potentially creating a false sense of security. In this work, we propose PISmith, a reinforcement learning (RL)-based red-teaming framework that systematically assesses existing prompt-injection defenses by training an attack LLM to optimize injected…

Read at arXiv (research papers)

Dialogue Earth (formerly Diálogo Chino) Rosilena Lindo Geopolitics

For Latin America, the Gulf conflict is making the case for clean energy

Escalating conflicts show that renewables are not just a climate option, they are a security strategy, writes Panama’s former energy secretary

Read at Dialogue Earth (formerly Diálogo Chino)

arXiv (research papers) Zonghao Ying SI

Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw

The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to execute complex workflows. This level of access creates unprecedented security challenges. Consequently, traditional content-filtering defenses have become obsolete. This report presents a comprehensive security analysis of the OpenClaw…

Read at arXiv (research papers)

Journal articles (OpenAlex) David Shim, Delf Rothe · Media War & Conflict Geopolitics

Climate no future? Picturing imaginaries of climate activists between hope and violence

This visual essay adds to current research on climate futures, violence and conflict by presenting findings from ‘Security Imaginaries of Climate Movements’ (SECIMA), a citizen science project with climate activists conducted between 2022 to 2024. Combining elements of photovoice and photo elicitation, the project engaged activists from Fridays for Future, Extinction Rebellion and The Last Generation to explore how activists imagine (violent) futures in the global climate…

Read at Journal articles (OpenAlex)

arXiv (research papers) Ninghui Li SI

Security Considerations for Artificial Intelligence Agents

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by Perplexity's experience operating general-purpose agentic systems used by millions of users and thousands of enterprises in both controlled and open-world environments. Agent architectures change core assumptions around code-data separation…

Read at arXiv (research papers)

arXiv (research papers) Frank Li SI

OpenClaw PRISM: A Zero-Fork, Defense-in-Depth Runtime Security Layer for Tool-Augmented LLM Agents

Tool-augmented LLM agents introduce security risks that extend beyond user-input filtering, including indirect prompt injection through fetched content, unsafe tool execution, credential leakage, and tampering with local control files. We present OpenClaw PRISM, a zero-fork runtime security layer for OpenClaw-based agent gateways. PRISM combines an in-process plugin with optional sidecar services and distributes enforcement across ten lifecycle hooks spanning message…

Read at arXiv (research papers)

arXiv (research papers) Xinhao Deng SI

Taming OpenClaw: Security Analysis and Mitigation of Autonomous LLM Agent Threats

Autonomous Large Language Model (LLM) agents, exemplified by OpenClaw, demonstrate remarkable capabilities in executing complex, long-horizon tasks. However, their tightly coupled instant-messaging interaction paradigm and high-privilege execution capabilities substantially expand the system attack surface. In this paper, we present a comprehensive security threat analysis of OpenClaw. To structure our analysis, we introduce a five-layer lifecycle-oriented security framework…

Read at arXiv (research papers)

Journal articles (OpenAlex) Deborah Manzi, Francesco Calderoni · Journal of Criminal Justice Geopolitics

A simulation approach to assess law enforcement intervention impact: How the efficiency/security trade-off affects drug trafficking networks' resilience to arrests

Despite extensive research on criminal group disruption, little is known about how alternative efficiency/security configurations within drug trafficking organizations (DTOs) shape resilience under sustained law enforcement pressure. DTOs face a core trade-off: efficiency—achieved through coordination and information sharing—increases exposure, while security—based on compartmentalization and trust—constrains flexibility and scale. Although widely theorized, this trade-off…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Jana Baldus, Anna-Katharina Ferl · Contemporary Security Policy Geopolitics

Apocalyptic imaginaries: Risk and regulation in discourses of military AI and nuclear weapons

Discourses on nuclear weapons and military applications of artificial intelligence (AI) portray them either as apocalyptic super weapons, posing catastrophic risks, or as indispensable to states’ national survival and the international security architecture. At the same time, debates about and governance efforts to regulate these weapons have become contested, stalled, or even abandoned. We examine the intersection of both regulatory discourses by asking: How do contemporary…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Liguo Zhang, Pengcheng Wang, Rucheng Lu · Humanities and Social Sciences Communications Geopolitics

Can bilateral relations promote border construction? Evidence from China-Vietnam borders

Population flow, port trade, industrial agglomeration, network expansion, and security infrastructure, all underpinned by geopolitical cooperation, are reflected in the construction space evolution. Border construction expansion has become a central manifestation of the bilateral relationship development between the two countries. Using the GDELT database to develop a “bilateral augmentation-bilateral segmentation” system, this study measured the bilateral relationship…

Read at Journal articles (OpenAlex)

arXiv (research papers) Sumit Ranjan SI

VoiceSHIELD-Small: Real-Time Malicious Speech Detection and Transcription

Voice interfaces are quickly becoming a common way for people to interact with AI systems. This also brings new security risks, such as prompt injection, social engineering, and harmful voice commands. Traditional security methods rely on converting speech to text and then filtering that text, which introduces delays and can ignore important audio cues. This paper introduces VoiceSHIELD-Small, a lightweight model that works in real time. It can transcribe speech and detect…

Read at arXiv (research papers)

Rappler Bea Cupin South China Sea

The price of stealing Philippines’ top security secrets

A Chinese national got his hands on details of rotation and resupply missions to the West Philippine Sea in 2023 — through a Filipino with access to the Philippine Coast Guard in Palawan

Read at Rappler

arXiv (research papers) Neha Nagaraja SI

Goal-Driven Risk Assessment for LLM-Powered Systems: A Healthcare Case Study

While incorporating LLMs into systems offers significant benefits in critical application areas such as healthcare, new security challenges emerge due to the potential cyber kill chain cycles that combine adversarial model, prompt injection and conventional cyber attacks. Threat modeling methods enable the system designers to identify potential cyber threats and the relevant mitigations during the early stages of development. Although the cyber security community has…

Read at arXiv (research papers)

Asia Times Gabriel Honrada South China Sea

China’s undersea Great Wall targets US sub supremacy

Beneath the waves of the Pacific, China is quietly building a layered undersea warfare system designed not just to contest US submarines, but to secure its nuclear deterrent and reshape the region’s strategic balance. In testimony before the US-China Economic and Security Review Commission, Rear Admiral Mike Brookes warned that China views undersea warfare as

Read at Asia Times

Journal articles (OpenAlex) Daniel Sloot, Kristin Limbach, Corinne Faure et al. · Cell Reports Sustainability Geopolitics

Public perceptions of energy security risks and energy transition support in France and Germany

The recent European energy crisis following the Russia-Ukraine war of 2022 has highlighted energy security risks and influenced public debates over the course of the sustainable energy transition. We investigate how public concerns over four dimensions of energy security risks (reliability of supply, import dependency, affordability, and environmental impact) are related to support for the energy transition in Germany and France. Our survey data ( n = 2,010 participants)…

Read at Journal articles (OpenAlex)

Older stories