Results for “Across”

Atlantic Council Henry Shuldiner Geopolitics

The recent US-Venezuelan strike on Tren de Aragua’s leader will reverberate across Latin America

The June 12 operation that killed the leader of the Venezuelan criminal organization Tren de Aragua sets a new precedent for cooperation with the United States.

Read at Atlantic Council

Journal articles (OpenAlex) Wan Junjie, Lina Gong, Wang Wenhao · Rock Art Research Geopolitics

THE ROLE OF WOMEN IN THE COMMUNIST PARTY OF CHINA: HISTORICAL EVOLUTION AND POLITICAL IMPLICATIONS

This study examines the evolving role of women within the Communist Party of China (CPC) from its founding to the present, exploring the political and social implications of this historical trajectory for gender equality in contemporary China. Adopting a historical-institutionalist framework, the research traces the continuities and shifts in the CPC's gender policies across each major period of the CPC's development to assess how early commitments to women's emancipation…

Read at Journal articles (OpenAlex)

arXiv (research papers) Aaditya Pai SI

PARSE: Provenance-Aware Retrieval Sanitization for Professional Domain LLM Agents

Prompt injection defenses evaluated on synthetic benchmarks do not generalize to real enterprise documents, which are longer, denser, and interleave legitimate authority language with factual content. We demonstrate this gap with a benchmark of 122 tasks across five professional domains (financial, legal, medical, scientific, DevOps) built on real retrieved documents -- actual SEC filings, Federal Register rules, PubMed abstracts, arXiv papers, and GitHub postmortems…

Read at arXiv (research papers)

Journal articles (OpenAlex) Verónica Amarante, Maira Colacce · Longitudinal and Life Course Studies Geopolitics

Transitions to old age: a multidimensional poverty approach for Chile

Evaluating deprivation among individuals transitioning to older ages requires a multidimensional approach to evaluate their diverse needs. Despite its importance, research on this topic remains limited in the developing world, particularly in Latin America. This study tracks the multidimensional poverty of a cohort of Chileans as they transition into older age, following them longitudinally across three waves (2006, 2009, and 2015). We construct a multidimensional poverty…

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) Zixin Rao SI

FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query Fragmentation and Fusion

Large language model (LLM) agents increasingly rely on long-term memory to support complex task execution, user personalization, and domain adaptation. Meanwhile, emerging access-control mechanisms for LLM agents are being explored to block policy-violating requests and prevent misuse. We reveal a novel attack surface arising from agent memory operations: prohibited content that would trigger access control can be fragmented across interactions, stored in long-term memory in…

Read at arXiv (research papers)

Asia Times Denny Roy South China Sea

China’s latest South China Sea shocks reopen old wounds

The epicenter of the latest South China Sea tensions is near the Philippines, but the shock waves have reverberated across several countries. The new bump in tensions results from two developments in late May and early June. First, the Philippine government announced the appearance of several large objects in Scarborough Shoal (known in the Philippines

Read at Asia Times

The Guardian Myanmar Alex Howlett Geopolitics

Tortured, humiliated and killed: the women who disappear into Myanmar’s prisons

The military junta has detained thousands of political prisoners since the 2021 coup, and a pattern of gender-based abuses is becoming clear In August 2021, news spread across a Myanmar protesters’ network that Thazin*, an activist and former university student, had been killed. The protest she attended that summer in Mandalay had been broken up by soldiers shooting and driving cars into the crowds. Most of the demonstrators were able to jump on to their motorcycles and…

Read at The Guardian Myanmar

Journal articles (OpenAlex) Gunel A. Alasgarova, Turana Abdullayeva · Central Asian Survey Geopolitics

Girls’ education in rural Azerbaijan: a co-autoethnographic study of societal ‘norms’ and postcolonial legacies

This co/autoethnographic study examines the educational experiences of two women from rural Azerbaijan, focusing on how societal ‘norms’, gendered expectations and post-Soviet transformations shaped their access to education from the 1990s onward. Using a co/autoethnographic methodology, we draw on collaboratively narrated memories, reflective memos and thematic analysis to analyse lived experiences across childhood, adolescence and early adulthood. This qualitative approach…

Read at Journal articles (OpenAlex)

Oxfam International Nesrine Aly

More Palestinians killed by Israeli military and settlers across occupied West Bank in last 3 years since Gaza hostilities than previous 17 combined

More Palestinians killed by Israeli military and settlers across occupied West Bank in last 3 years since Gaza hostilities than previous 17 combined Nesrine Aly Wed, 06/10/2026 - 21:00 Off More than one in five killed over last 20 years were children More Palestinians have been killed by the Israeli military and settlers across the occupied West Bank in the last three years than in the previous 17 years combined, analysis from Oxfam has found. The number of children killed…

Read at Oxfam International

arXiv (research papers) David Hofer SI

Assessing Automated Prompt Injection Attacks in Agentic Environments

Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain underexplored in realistic agentic settings. We present a comprehensive empirical evaluation of automated prompt injection attacks against LLM agents, adapting both white-box (GCG) and black-box (TAP) methods to the agentic setting within the AgentDojo framework. We evaluate across 80 task pairs…

Read at arXiv (research papers)

arXiv (research papers) Saeid Jamshidi SI

Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs

Large Language Models (LLMs) in multi-turn interactions maintain evolving context rather than generating isolated responses, making them vulnerable to prompt-injection and context-poisoning attacks in which locally plausible adversarial fragments gradually distort reasoning trajectories. Existing defenses mainly filter individual outputs and often ignore context evolution across turns, leaving long-horizon reasoning exposed. Although the Model Context Protocol (MCP)…

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) Mudit Sinha SI

Hiding in Plain Floats: Steganographic Carriers for Indirect Prompt and Content Injection

Text-centered prompt-injection defenses assume that the malicious signal is visible in one of the inspected text views. We study a reproducible LLM01-style indirect prompt/content-injection failure mode where that assumption breaks: a payload caught in plain English slips past the same detector when it is transported as structured float parameters and reconstructed only as fragmented telemetry. Across 14,400 attacked real-model trials on three commercial LLM APIs from…

Read at arXiv (research papers)

arXiv (research papers) Harshil Patel SI

VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation

As the Model Context Protocol (MCP) standardizes tool-calling for autonomous agents, it introduces a critical, unexamined attack surface: the error-handling loop. We hypothesize that tool error messages possess implicit authority, triggering corrective reasoning modes that bypass standard safety heuristics. We introduce VATS (Vulnerability Analysis of Tool Streams), a mutation-driven framework that systematically evolves adversarial payloads across seven structural and…

Read at arXiv (research papers)

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)

arXiv (research papers) Pritam Dash SI

From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents

Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance. However, persistent memory introduces the risk of memory poisoning, where a single adversarial memory write can exert long-term influence over agent behavior. We present a systematic study of memory poisoning in LLM-based agents. We identify four memory write channels and nine structural vulnerabilities in model capabilities, system prompt design, and…

Read at arXiv (research papers)

arXiv (research papers) Yingqi Zhang SI

Agent libOS: A Runtime Substrate for Capability-Controlled Self-Evolving LLM Agents

Large language model (LLM) agents can persist across tasks, acquire memory, activate Skills, synthesize tools, fork child processes, attach remote resources, and commit checkpoints as reusable images. These mechanisms expand the action surface after deployment and create authority-escalation and data-exfiltration risks when visibility is mistaken for permission. We present Agent libOS, an agent-native library OS substrate that separates three planes. Operation admission…

Read at arXiv (research papers)

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)

arXiv (research papers) Hiskias Dingeto SI

AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations

Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed through tool calls) whose response content the user neither writes nor controls. Existing benchmarks under-measure the threat: most cover only a handful of integrations with the same attack payload replayed across runs, and open-source guards are trained on chat-style data rather than tool-response…

Read at arXiv (research papers)

Journal articles (OpenAlex) Óscar Rafael Boude Figueredo, Jessica Meza-Jaque, Luis Peréz · F1000Research Geopolitics

Towards a New Learning Ecology: The Mediator Role of Teachers Facing Generative AI in the University Context of Peru, Chile, and Colombia

Background The emergence of Generative Artificial Intelligence (GenAI) has created an ontological disruption in higher education, challenging traditional pedagogical mediation and academic production. This study examines the transformation of the teaching role in university environments across Peru, Chile, and Colombia, addressing a knowledge gap in Latin American empirical research regarding faculty perceptions and daily practices with Large Language Models. Methods The…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Yuanyuan Cui · English Language Teaching Geopolitics

Multilingual Practices in China-Vietnam Borderlands: A Case of Supermarket at Hekou

Against the backdrop of increasingly frequent cross-border mobility, language plays an important role in catering to the needs of foreign migrants who come to China for various purposes. This study selected a supermarket in Hekou, a China-Vietnam border town, as a research site for examining how different languages are displayed across different areas of the supermarket and what functions these languages serve. Based on the content analysis of 127 multilingual signs and…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jiejun Tan SI

From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors

LLM agents are evolving from conversational chatbots to operational tools in real-world workspaces. In local agentic harnesses, an LLM can read and write files, call tools, and reuse workspace state across sessions. While such capabilities enhance utility, they also expose a new attack surface for attackers. Attackers can embed a prompt injection within a file or tool output. Agents may read this hidden instruction, store it, and execute it later. In this multi-step trojan…

Read at arXiv (research papers)

arXiv (research papers) Syed Nazmus Sakib SI

The Surface You Test Is Not the Surface That Breaks

Prompt-injection benchmarks for LLM agents typically test attacks through a single injection surface and report the resulting attack success rate as a property of the model. We ask whether those robustness conclusions remain stable when the same adversarial content enters through a different part of the agent interface. Using AgentDojo, we evaluate 13 LLMs across four task suites and place a byte-identical payload either in a tool output or in the tool description. This…

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) Avidan Shah SI

Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training

As LLMs gain stronger reasoning capabilities, their extended chain-of-thought introduces new degrees of complexity for defending against adversarial jailbreaks and prompt injection. We study consistency training, a family of fine-tuning objectives that enforce identical behavior on clean prompts and adversarial rewrites, and evaluate its two main variants, output-level (BCT) and activation-level (ACT), across five reasoning models. We formulate both methods as a prompt…

Read at arXiv (research papers)

Journal articles (OpenAlex) Kimberly Hsiu-Chin Lee, Jiunn-Liang Guo, Wen-Jer Chang · Australian Feminist Studies Geopolitics

Shattering the Seafaring Stereotype: An Ethnographic Exploration of Gender Equality on Taiwan's Domestic Oil Tanker Fleet

Despite the global hegemonic masculinity of the maritime sector, this ethnographic study investigates a ‘critical anomaly’ within a Taiwanese product oil tanker fleet where women occupy a majority of key navigational roles, including Master. Grounded in Feminist Standpoint Theory and the Hegelian dialectical method, the research utilises longitudinal field observations across two separate voyages (totaling 15 days) and is enriched by five in-depth interviews and one focus…

Read at Journal articles (OpenAlex)

arXiv (research papers) Akindoyin Akinrele SI

Prompt Injection Detection is Regime-Dependent: A Deployment-Aware Evaluation with Interpretable Structural Signals

Prompt injection poses a critical threat to the safe deployment of large language models, yet existing detection approaches are typically evaluated under limited settings that do not reflect real-world operating constraints. In this work, we present a deployment-aware evaluation of prompt injection detection using a multi-model and multi-regime experimental framework. We compare lexical, semantic, structural, and transformer-based detectors across multiple…

Read at arXiv (research papers)

Asia Times Gabriel Honrada South China Sea

Type 004: China’s nuclear carrier fast-forged to face down the US

As China rapidly builds its largest and potentially first nuclear-powered aircraft carrier, the Type 004 may mark a decisive shift from regional sea denial toward sustained blue-water power projection across the Indo-Pacific. This month, the Center for Strategic and International Studies (CSIS) released a report showing that China is rapidly constructing its fourth aircraft carrier,

Read at Asia Times

Older stories