Results for “security”

Journal articles (OpenAlex) Alexander Kmentt · Frontiers in Political Science Geopolitics

Weapons of peace or instruments of catastrophe? Rethinking nuclear deterrence, legitimacy, and security in light of humanitarian evidence

This article advances a policy-oriented argument about the legitimacy and sustainability of nuclear deterrence in light of the expanding scientific and humanitarian evidence base on the consequences and risks of nuclear weapons. Drawing on research developed through the Humanitarian Impacts of Nuclear Weapons Initiative and on arguments elaborated within the Treaty on the Prohibition of Nuclear Weapons (TPNW), particularly the 2025 report on the security concerns of states…

Read at Journal articles (OpenAlex)

arXiv (research papers) Gulshan Saleem SI

A Layered Security Framework Against Prompt Injection in RAG-Based Chatbots

Prompt injection is ranked as the most critical vulnerability in large language model (LLM) deployments by the OWASP Top 10 for LLM Applications, yet existing defenses operate at isolated pipeline stages and remain incomplete. Input filters cannot inspect retrieved documents, while output monitors cannot prevent malicious payloads from reaching the model. Consequently, retrieval-augmented generation (RAG) chatbots remain vulnerable to indirect injection, where a poisoned…

Read at arXiv (research papers)

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)

arXiv (research papers) Yuchuan Tian SI

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents

Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects. Existing evaluations often collapse these stages into a single attack success rate, making it difficult to tell whether a model merely agreed with an attacker or actually produced observable harm. We introduce SafeClawBench, a staged benchmark for…

Read at arXiv (research papers)

Journal articles (OpenAlex) Fabrizio Del Carpio Delgado, Rafael Romero-Carazas, Roque Juan Espinoza Casco et al. · F1000Research Geopolitics

Temporal prediction of arrests for illicit drug trafficking and micro-distribution using ARIMA models in Peru

Introduction Illicit drug trafficking and micro-distribution represent persistent challenges affecting public security, institutional governance, and social dynamics in Peru. In this context, the aim of the study was to temporally predict trends in arrests related to illicit drug trafficking and micro-distribution using ARIMA models in Peru. Methods The research was conducted under a quantitative approach with a non-experimental, descriptive-predictive, and retrospective…

Read at Journal articles (OpenAlex)

arXiv (research papers) Ismail Hossain SI

SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills

Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely unvetted. The gap we fill: existing scanners operate at the code layer and are structurally blind to instruction-layer and multi-agent risk - natural-language directives that hijack an agent, exfiltrate data through encoded side channels, or chain harm across pipelines - so what is needed is a…

Read at arXiv (research papers)

arXiv (research papers) Xinhang Ma SI

AutoDojo: A Generative Benchmark for Evaluating Prompt Injection Defenses in LLM Agents

Indirect prompt injection (IPI) is a major security threat to LLM-powered agents. Thus, a growing body of work has proposed a variety of defensive approaches against IPI which can be grouped into three broad categories: prompt-level, filter-based, and system-level designs. However, commonly used benchmarks for evaluating defense, such as AgentDojo, are \emph{inherently static}, generating a fixed distribution of IPI attacks. Consequently, a defense can score well on them…

Read at arXiv (research papers)

arXiv (research papers) Saeid Jamshidi SI

Security Engineering of OpenClaw: Analyzing Attack Surface Expansion and Trust-Boundary Violations

Agentic large language model (LLM) systems can now execute actions, not only produce text. When model outputs trigger privileged operations such as shell commands, browser automation, or external tool calls, the security problem shifts from alignment alone to system configuration and structural design. We analyze OpenClaw, a self-hosted multi-agent system in which LLM outputs can execute commands and interact with tools and services. We measure compromise probability…

Read at arXiv (research papers)

Journal of Democracy Alexander Noyes Geopolitics

Why Mali Is at a Dangerous Crossroads

Mali’s spiraling security crisis puts its entire region at risk. A return to democracy will be key to preventing the country from becoming a terrorist safe haven in West Africa. Source

Read at Journal of Democracy

The Guardian Myanmar Associated Press in Bangkok

China arrests US academic at conference for ‘espionage activities’

Arrest of Min Zin, who writes about Myanmar and Chinese foreign policy, comes just month after Trump visit to Beijing China has arrested a US scholar who writes about Myanmar and Chinese foreign policy on suspicion of spying. Min Zin was suspected of “engaging in espionage activities that endanger China’s national security,” China’s ministry of foreign affairs spokesperson, Lin Jian, said on Friday.

Read at The Guardian Myanmar

arXiv (research papers) Zihao Wang SI

Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents

LLM-based web agents are increasingly deployed in real-world settings such as e-commerce, where they interact extensively with untrusted web content while executing actions that carry direct financial consequences. This makes them vulnerable to prompt-injection attacks, in which seemingly benign web content conceals adversarial instructions that manipulate the agent's behavior. Existing security benchmarks adopt an \textit{attack-centric} perspective, focusing on the…

Read at arXiv (research papers)

arXiv (research papers) Pengfei He SI

PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections

Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources. Existing defenses mainly focus on blocking malicious content at inference time, and current red-teaming methods primarily optimize attack success. As a result, developers have limited visibility into how latent prompt injections emerge and…

Read at arXiv (research papers)

arXiv (research papers) Timothy McAllister SI

Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows

As LLM-based multi-agent systems (MAS) are deployed in the wild, the resilience of their collaboration structures against adversarial compromise becomes a critical safety concern. Attackers may leverage prompt-injection or jailbreaking to sabotage individual agents within MAS workflows, but the interaction between model scaling and system-level resilience remains poorly understood. This paper investigates how model scale affects the security of linear multi-agent workflows…

Read at arXiv (research papers)

Stimson Center Kaitlyn Hashem Geopolitics

Is Claudia Sheinbaum Head of State or Head of Her Party?

The U.S. indictment of a sitting governor was unprecedented and will reshape US-Mexico relations and security cooperation.

Read at Stimson Center

Journal articles (OpenAlex) Susan Hutchinson · Australian Journal Of International Affairs Geopolitics

Department of Home Affairs’ implementation of WPS – the case of Afghan women applying to come to Australia

This paper examines the Department of Home Affairs’ implementation of the Women, Peace and Security (WPS) agenda through the experiences of Afghan women seeking refuge in Australia. Drawing on practitioner reflections and case studies from advocacy work supporting hundreds of high-risk Afghan women, it critically analyses the extent to which visa policies and processes address the intersecting vulnerabilities of displaced women. The paper situates this analysis within the…

Read at Journal articles (OpenAlex)

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) Yuchen Ling SI

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation

Large language model (LLM) agents are rapidly moving from conversational interfaces to software components that plan, invoke tools, maintain memory, and act on external environments. This transition changes the nature of security risk. In agentic settings, failures are no longer limited to unsafe text generation. Untrusted content may redirect control flow, misuse tool privileges, corrupt persistent state, leak sensitive information, or trigger harmful external actions. At…

Read at arXiv (research papers)

Journal articles (OpenAlex) Đậu Tuấn Nam, Nguyễn Anh Cường · Cogent Arts and Humanities Geopolitics

Vietnam’s foreign-policy identity and instrument choice, 1995–2025: reassessing bamboo diplomacy as identity-anchored hedging

This article reassesses Vietnam’s ‘bamboo diplomacy’ as a recent discursive codification of a longer foreign-policy repertoire rather than as a label that can be projected uncritically across the entire 1995–2025 period. The article asks how Vietnam’s foreign-policy identity affects instrument choice under pressure from major-power competition, maritime security risk and economic dependence. It treats identity as the independent variable, operationalized through the durable…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yuanbo Xie SI

What If Prompt Injection Never Left? Rethinking Agent Security through Cross-Session Stored Prompt Injection

Modern agentic systems fundamentally reshape the security boundary of LLMs by introducing persistent system state including memories, filesystems, tools, and other long-lived contextual artifacts that survives across sessions. As external information crosses this boundary and becomes part of persistent agent state, malicious instructions are no longer confined to a single interaction, but can silently persist and influence future executions long after the original attacker…

Read at arXiv (research papers)

InSight Crime Gavin Voss Geopolitics

Violence Between Criminal Groups and LatAm Governments Has Risen Since Trump: Report

Violence Between Criminal Groups and LatAm Governments Has Risen Since Trump: Report As US President Donald Trump attempts to sway security policy in Latin America and the Caribbean, a new report found that confrontations between security forces and criminal groups are on the rise, while criminal groups are adapting.

Read at InSight Crime

Stimson Center Joaquin Matamis Geopolitics

Renewing the UN’s Toolbox for Peace and Security

Amidst growing funding constraints, hardening geopolitical rivalries, and surging conflicts, how should the UN “get back to basics”?

Read at Stimson Center

arXiv (research papers) Hang Li SI

"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems

The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting from the strong instruction-following capabilities and broad prior knowledge of LLMs, educators can deploy AG systems across diverse tasks using only natural language rubrics while achieving satisfactory grading performance. Despite these advantages, new security concerns may also arise. In particular, prompt injection (PI)…

Read at arXiv (research papers)

arXiv (research papers) Ryle Goehausen SI

Gate AI: LLM Security Benchmark Evaluation Methodology and Results

Published evaluations of prompt-injection and jailbreak detectors for Large Language Models often suffer from two systematic weaknesses: per-dataset threshold tuning and undisclosed operating points. We describe an evaluation harness that addresses both. The detector under evaluation is scored across 16 public benchmarks (12,111 samples) using 5-fold cross-validation. StratifiedKFold (by row) is the headline pass; a parallel StratifiedGroupKFold pass over a composite key…

Read at arXiv (research papers)

InSight Crime Deborah Bonello Geopolitics

The InSight Take: PCC and Red Command— Who Loses From US Terrorist Designations in Brazil?

The InSight Take: PCC and Red Command— Who Loses From US Terrorist Designations in Brazil? In this week's InSight Take, Managing Editor Deborah Bonello and Co-Director Steven Dudley discuss the recent US terrorist designations of the PCC and Red Command gangs, and how they affect Brazil's security landscape, elections, and economy.

Read at InSight Crime

Atlantic Council Maite Latorre Yerou, Patricia R. Francis Geopolitics

US-Caribbean maritime cooperation: Why stronger ports, supply chains, and security matter now

The Caribbean is not a peripheral region but a core component of the United States' economic and security environment. Its ports support US trade, its routes shape regional stability, and its infrastructure is now central to geopolitical competition.

Read at Atlantic Council

arXiv (research papers) Chao Wang SI

Confused ChatGPT: Cross-App Context Poisoning via First-Party APIs

ChatGPT Apps, launched by OpenAI on Oct. 6, 2025, introduce an app-in-app paradigm in which third-party applications share a single chat context with the user and with every other connected app. The ecosystem grew from 122 apps in Dec. 2025 to 888 by May 2026, yet its security has remained uninvestigated. We identify cross-app context poisoning, a variant of indirect prompt injection distinguished by three properties: 1) the injection persists in the shared chat context…

Read at arXiv (research papers)

arXiv (research papers) Alexander Sternfeld SI

Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs

LLM-based coding assistants are seeing rapid adoption, offering substantial gains in developer productivity. As organizations increasingly ship code these agents produce, the security of that code becomes critical. Prior work has shown that minor prompt perturbations degrade the functional correctness of LLM-generated code, but whether they also compromise code security has remained unstudied. We apply token-level mutations to prompts across three models and five programming…

Read at arXiv (research papers)

arXiv (research papers) Yu Yin SI

Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings

Recent generative engine optimisation (GEO) research has shown that prompt-injection attacks can push a target product to the top of an LLM's recommendation list, with the strongest attacks reporting around $80\%$ success and raising serious security concerns about RAG-based recommendation. However, these results assume the attacked document is always fed directly to the generator, bypassing the retriever and reranker. This is unrealistic: in deployed RAG systems, the attack…

Read at arXiv (research papers)

Rappler Bea Cupin South China Sea

Marcos in Japan: Security, energy, trade, and peace in a chaotic world

The Philippine President is accorded a state visit, signaling Manila’s growing importance to Japan and vice versa

Read at Rappler

arXiv (research papers) Xiang Fang SI

Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security

Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt injection, pose significant risks to the integrity and availability of LLMs in security-critical applications. This paper proposes the Adversarial Prompt Disentanglement (APD) framework, a novel defense mechanism that proactively identifies…

Read at arXiv (research papers)

Older stories