Results for “Again”

Journal articles (OpenAlex) Nguyen Thi Phuong · F1000Research Geopolitics

Political and Ideological Work in the Southern Battlefield and the Construction of the Vietnamese Revolutionary Image in Foreign Affairs (1954–1975)

Background: The resistance war against the United States was not merely a military struggle but also a diplomatic and international public opinion battle. In this context, constructing the image of the Vietnamese Revolution played a particularly crucial role in consolidating legitimacy and garnering international support. Consequently, the ideological, cultural, and social fronts within revolutionary battlefields became an organic component of the revolutionary foreign…

Read at Journal articles (OpenAlex)

arXiv (research papers) Chuan Guo Michael Pokorny SI

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

Instruction hierarchy (IH) defines how LLMs prioritize system, developer, user, and tool instructions under conflict, providing a concrete, trust-ordered policy for resolving instruction conflicts. IH is key to defending against jailbreaks, system prompt extractions, and agentic prompt injections. However, robust IH behavior is difficult to train: IH failures can be confounded with instruction-following failures, conflicts can be nuanced, and models can learn shortcuts such…

Read at arXiv (research papers)

arXiv (research papers) Meenatchi Sundaram Muthu Selva Annamalai SI

CLIOPATRA: Extracting Private Information from LLM Insights

The widespread adoption of AI assistants has encouraged the development of privacy-aware platforms designed to extract insights from real-world usage. Their privacy protections primarily rely on layering multiple heuristic techniques, such as PII redaction, clustering, aggregation, and LLM-based privacy auditing. In this paper, we put their privacy claims to the test by presenting CLIOPATRA, the first attack against "privacy-preserving" LLM-based insights systems. Our attack…

Read at arXiv (research papers)

Journal articles (OpenAlex) Martin Holbraad · Journal of the Royal Anthropological Institute Geopolitics

Cuban anthropology at a conjuncture: Introduction to a special theme section

This short introduction contextualizes the three articles assembled for this special feature on Cuban anthropology by placing them against the backdrop of the precarious political and economic position in which Cuba finds itself at present. This raises questions as to how far and in what ways the kinds of phenomena and analyses put forward in the three articles in this section may serve as the basis for understanding the radical shifts in Cuban society that may lie ahead…

Read at Journal articles (OpenAlex)

Simon Willison SI

Clinejection — Compromising Cline's Production Releases just by Prompting an Issue Triager

Clinejection — Compromising Cline's Production Releases just by Prompting an Issue Triager Adnan Khan describes a devious attack chain against the Cline GitHub repository, which started with a prompt injection attack in the title of an issue opened against the repo. Cline were running AI-powered issue triage using the anthropics/claude-code-action@v1 action, configured to run Claude Code with --allowedTools "Bash,Read,Write,..." any time any user opened an issue in their…

Read at Simon Willison

The Conversation James Dwyer, Lecturer, School of Social Sciences, University of Tasmania Geopolitics

The US just torpedoed an Iranian ship. Here’s why this old tech is hard to defend against

Torpedoes are hard to stop – and harder to see coming.

Read at The Conversation

Atlantic Council ibarrero Geopolitics

The fight for influence in Venezuela against Russia, China, Iran, and Cuba

Experts unpack the impact of foreign influence in Venezuela as the US role increases.

Read at Atlantic Council

arXiv (research papers) Junchen Li SI

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG

Retrieval-Augmented Generation (RAG) systems are vulnerable to blocking attacks, in which poisoned documents cause large language models (LLMs) to refuse benign queries. Existing attacks rely on adversarial suffixes or explicit instructions, which are increasingly ineffective against modern LLMs, susceptible to prompt injection filtering, or require feedback from the target system. We observe overlapping risk categories and refusal criteria across safety-aligned LLMs, a…

Read at arXiv (research papers)

Journal articles (OpenAlex) Michelle Patch, Christine Garinger, Susan Michelle Jack · Journal of Advanced Nursing Geopolitics

Responding to Gender‐Based Violence in a Changing World: Prevention, Advocacy and Action

Nurses and midwives have long been at the forefront of advancing the evidence base, shaping policy initiatives and implementing interventions aimed at preventing and responding to violence against women. This long-standing leadership was powerfully reflected in the kinetic energy generated by the more than 180 delegates who convened for the 26th Nursing Network on Violence Against Women International (NNVAWI) conference in Niagara-on-the-Lake, Ontario, Canada (October 6–8…

Read at Journal articles (OpenAlex)

arXiv (research papers) Piyush Jaiswal SI

Analysis of LLMs Against Prompt Injection and Jailbreak Attacks

Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same time, LLMs are vulnerable to prompt-based attacks. Thus, analyzing this risk has become a critical security requirement. This work evaluates prompt-injection and jailbreak vulnerability using a large, manually curated dataset across…

Read at arXiv (research papers)

arXiv (research papers) Lei Ba SI

CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agents

LLM-based code interpreter agents are increasingly deployed in critical workflows, yet their robustness against risks introduced by their code execution capabilities remains underexplored. Existing benchmarks are limited to static datasets or simulated environments, failing to capture the security risks arising from dynamic code execution, tool interactions, and multi-turn context. To bridge this gap, we introduce CIBER, an automated benchmark that combines dynamic attack…

Read at arXiv (research papers)

Asia Times Gabriel Honrada South China Sea

China’s submarine surge testing Pacific’s undersea balance

China’s accelerating nuclear submarine buildup is no longer just a shipyard story, but a strategic test of whether faster production can be converted into real leverage against US sea power in the Pacific. This month, the International Institute for Strategic Studies (IISS) released a report stating that China has sharply accelerated nuclear-powered submarine production over the

Read at Asia Times

Journal articles (OpenAlex) Bertrand Marilier · Time & Society Geopolitics

Fashion as spatial disorder: German conservatism and the reordering of dress

From the Renaissance onward, German conservatism has defended space, a locus of stability, against the temporalization associated with Western European modernity. Attempts to map nations and occupations onto an atlas of changeless types were ultimately thwarted by social and technical change, and because it so easily spreads across classes and territories, fashion most readily registered this temporal erosion. But fashion simultaneously undermines and affirms timeless…

Read at Journal articles (OpenAlex)

Latinoamérica21 Ángel Arellano Geopolitics

The map of the aligned: what is the relationship between Latin American countries and the United States?

Latin America is once again dividing between the aligned and the punished on a regional chessboard where Washington imposes loyalties as a condition for stability. O post The map of the aligned: what is the relationship between Latin American countries and the United States? apareceu primeiro em Latinoamérica 21.

Read at Latinoamérica21

Rappler Herbie Gomez South China Sea

[Pastilan] How many Filipinos learned to love China’s puppet show

This explains why certain senators parade their pro-China loyalties with brazen shamelessness. They are not bold out of principle, but because they are already calculating that the next president will be China-backed again.

Read at Rappler

arXiv (research papers) Peiran Wang SI

The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis

The evolution of Large Language Models (LLMs) has resulted in a paradigm shift towards autonomous agents, necessitating robust security against Prompt Injection (PI) vulnerabilities where untrusted inputs hijack agent behaviors. This SoK presents a comprehensive overview of the PI landscape, covering attacks, defenses, and their evaluation practices. Through a systematic literature review and quantitative analysis, we establish taxonomies that categorize PI attacks by…

Read at arXiv (research papers)

Journal of Democracy Geopolitics

Why Iran’s Mullahs Are Running Out of Options

Iran has been plagued by economic turmoil and popular unrest in recent years as international sanctions stiffened and citizens bucked against the regime’s grip on civil life. Source

Read at Journal of Democracy

arXiv (research papers) Georgios Syros SI

MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks

Large language model (LLM) based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behalf. While these agents offer powerful capabilities, their design exposes them to indirect prompt injection attacks embedded in untrusted web content, enabling adversaries to hijack agent behavior and violate user intent. Despite growing awareness of this threat, existing evaluations rely on fixed…

Read at arXiv (research papers)

Journal articles (OpenAlex) Flavia Batista da Silva, Carolina F. T. Batista, Ernesto F. Calvo · Latin American Politics and Society Geopolitics

Partisan Messages and Support for Democratic Institutions: Evidence from Survey Experiments in Brazil, Chile, and Colombia

ABSTRACT We examine the relationship between partisan social media messages and voters’ support for undemocratic transgressions against the president and Congress. Our survey experiments in Brazil, Chile, and Colombia randomly exposed respondents to partisan messages about contentious and consensus issues such as inflation, abortion, crime, and protests. We then assessed whether these messages increased support for undemocratic transgressions. Our findings reveal distinct…

Read at Journal articles (OpenAlex)

OnCuba News OnCuba Staff

Germán Mesa and his players optimistic ahead of upcoming World Baseball Classic

The Cuban manager believes the team can advance to the semifinals again, regardless of the absence of players who play in Major League Baseball. La entrada Germán Mesa and his players optimistic ahead of upcoming World Baseball Classic se publicó primero en OnCubaNews English.

Read at OnCuba News

Simon Willison SI

Moltbook is the most interesting place on the internet right now

The hottest project in AI right now is Clawdbot, renamed to Moltbot, renamed to OpenClaw. It's an open source implementation of the digital personal assistant pattern, built by Peter Steinberger to integrate with the messaging system of your choice. It's two months old, has over 114,000 stars on GitHub and is seeing incredible adoption, especially given the friction involved in setting it up. (Given the inherent risk of prompt injection against this class of software it's my…

Read at Simon Willison

Journal articles (OpenAlex) Bama Andika Putra · Frontiers in Political Science South China Sea

Interpreting changes in the Philippines’ South China Sea policy: insights from the foreign and public policy literatures

The alterations in the Philippines’ South China Sea policies across different Philippine leaders are puzzling. The display of decisiveness against China identified in Aquino and Marcos’ terms was undermined under Duterte’s leadership by the downplaying of the arbitral tribunal’s significance, harsh rhetoric against the US, and a series of appeasement policies to maintain warm relations with China. Bridging the foreign and public policy literatures, this study argues for the…

Read at Journal articles (OpenAlex)

arXiv (research papers) Pedro H. Barcha Correia SI

A Systematic Literature Review on LLM Defenses Against Prompt Injection and Jailbreaking: Expanding NIST Taxonomy

The rapid advancement and widespread adoption of generative artificial intelligence (GenAI) and large language models (LLMs) has been accompanied by the emergence of new security vulnerabilities and challenges, such as jailbreaking and other prompt injection attacks. These maliciously crafted inputs can exploit LLMs, causing data leaks, unauthorized actions, or compromised outputs, for instance. As both offensive and defensive prompt injection techniques evolve quickly, a…

Read at arXiv (research papers)

Dialogue Earth (formerly Diálogo Chino) Mengnan Jiang, Daniel Cressey, Lam Regina Geopolitics

China enters race to host High Seas Treaty HQ

Considered a “significant escalation” in its global governance aims, China is up against Chile and Belgium to host the treaty’s secretariat

Read at Dialogue Earth (formerly Diálogo Chino)

arXiv (research papers) Henry Chen SI

Proactive Hardening of LLM Defenses with HASTE

Prompt-based attack techniques are one of the primary challenges in securely deploying and protecting LLM-based AI systems. LLM inputs are an unbounded, unstructured space. Consequently, effectively defending against these attacks requires proactive hardening strategies capable of continuously generating adaptive attack vectors to optimize LLM defense at runtime. We present HASTE (Hard-negative Attack Sample Training Engine): a systematic framework that iteratively engineers…

Read at arXiv (research papers)

Rappler Tatiana Maligro South China Sea

‘Our house, our terms’: Senators condemn Chinese embassy remarks vs PH officials

At least 15 senators sign a proposed Senate resolution condemning the Chinese embassy's word wars against several Philippine officials

Read at Rappler

Rappler Bea Cupin South China Sea

PH files protest vs China embassy: Sobriety, respect not against national interest

The Department of Foreign Affairs says 'circumspection in language and actions are necessary’

Read at Rappler

Rappler Bea Cupin South China Sea

Beijing says Manila should ‘undo negative impact’ of WPS spokesperson’s talk

China doubles down on its pressure campaign against the Philippines, this time through a diplomatic protest in Beijing. Philippine Coast Guard Commodore Jay Tarriela responds: Exit the West Philippine Sea, then let’s talk.

Read at Rappler

Journal articles (OpenAlex) Kostiantyn Serhiiovych Fomichov, Hanzha Oleksandr, Сергій Андрійович Германов et al. · Journal of Drug and Alcohol Research Geopolitics

Legal regulation of counteraction and investigation of crimes committed by organized criminal groups in the field of drug trafficking

Aim: The paper’s goal is to conduct a comprehensive analysis of the features of legal governance with regard to the prevention of illegal drug trafficking and the investigation of crimes committed by organized crime groups in the field of drug distribution. Methods: The research’s methodological basis consists of a variety of general scientific and specialized legal procedures that ensure the methodical and unbiased scholarly examination of problems in the fight against…

Read at Journal articles (OpenAlex)

Older stories