Results for “work”

arXiv (research papers) Mohan Zhang SI

Measuring Real-World Prompt Injection Attacks in LLM-based Resume Screening

LLMs are vulnerable to prompt injection attacks. However, this vulnerability has been primarily demonstrated conceptually in academic studies or through a few anecdotal case studies. Its prevalence and impact in real-world LLM-based applications are largely unexplored. In this work, we present the first systematic study of prompt-injection attacks in a widely used application: LLM-based resume screening. Our analysis is based on approximately 200K real-world resumes…

Read at arXiv (research papers)

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)

arXiv (research papers) Yue Liu SI

How Agentic AI Coding Assistants Become the Attacker's Shell

Agentic AI coding assistants can edit files, run commands, and access the internet on behalf of developers. However, their reliance on unvetted external artifacts introduces a new attack vector. Hidden instructions in external artifacts can hijack these assistants, turning them into an attacker's shell to run unauthorized commands. In this article, we examine how these prompt injection attacks work, measure their prevalence, discuss the limitations and challenges of current…

Read at arXiv (research papers)

arXiv (research papers) Dongpeng Zhang SI

Localize and Neutralize: Gradient-guided Token Suppression against Visual Prompt Injection Attack

Adversarial images pose a severe security threat to multimodal large language models through prompt injection. Existing defenses largely lack a principled understanding of the underlying mechanisms and struggle to balance efficiency and defense utility. In this work, we show that successful adversarial attacks do not rely on the entire image uniformly but instead depend on a small subset of critical image tokens. Based on this insight, we propose Gradient Token Masking…

Read at arXiv (research papers)

arXiv (research papers) Dongxu Yang SI

Device Context Protocol: A Compact, Safety-First Architecture for LLM-Driven Control of Constrained Devices

Large language models are increasingly used as orchestrators of external tools via the Model Context Protocol (MCP), but MCP is built for software services with megabytes of memory and does not descend to the microcontrollers that dominate the long tail of physical devices. Recent work (IoT-MCP) ports MCP to edge gateways at 74 KB peak memory; this still excludes the smallest commodity MCUs and, critically, does not address the safety problem of giving an unreliable caller…

Read at arXiv (research papers)

Journal articles (OpenAlex) Lisa J. Wheildon, Asher Flynn, Abby Wild · International Journal for Crime Justice and Social Democracy Geopolitics

Screaming Underwater: Survivor Activism, Co-production and the Limits of Formal Engagement in Gender-Based Violence Policy

Survivors of gender-based violence (GBV) are increasingly engaged in the co-production of public policies and services, yet marginalised survivors remain largely excluded from shaping the decisions that affect them most. Drawing on in-depth interviews with 11 survivor advocates and activists from First Nations, culturally and racially marginalised, LGBTQI+ and disability communities in Australia, this article examines what works for survivors in terms of driving policy…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yuanbo Zhou SI

Prompt Overflow: What the Guardrail Inspects Is Not What the Model Infers

Guardrail models (a.k.a. safety checkers) are widely deployed to screen user inputs before they reach large language models (LLMs), serving as a primary defense against prompt injection attacks. Due to strict context constraints, these models handle overlength prompts through truncation or segmentation-based inspection. While prior work has focused on semantic adversarial inputs, the security implications of these long-input processing mechanisms remain largely unexplored…

Read at arXiv (research papers)

OnCuba News EFE

An inclusive cafe in Havana employs young people with Down’s syndrome and autism amid Cuba’s crisis

The young employees — aged between 20 and 35 — work as waiters or kitchen assistants, earning approximately 1,000 pesos per day. La entrada An inclusive cafe in Havana employs young people with Down’s syndrome and autism amid Cuba’s crisis se publicó primero en OnCubaNews English.

Read at OnCuba News

The Guardian Belarus Jakub Krupa

Russian threats against Baltics ‘unacceptable’ and danger to ‘our entire union’, EU’s von der Leyen says - as it happened

This blog is now closed In Brussels, Rutte begins by stressing the importance of Nato ministers meeting in Sweden, the alliance’s “newest ally” who joined in 2024. “This says a great deal about how fundamentally our security environment has changed, especially when it comes to Europe. It is more dangerous, it is more contested and it makes it all the more important that Nato allies work together to safeguard our freedom and security,” he says.

Read at The Guardian Belarus

Journal articles (OpenAlex) Cam-Tu Hoang Tran, Phương Nhật Vũ, Thanh Tran · Higher Education Skills and Work-based Learning Geopolitics

Developing a work-based learning competency framework for future ready logistics graduates in Vietnam

Purpose This study develops a context-sensitive competency framework to support work-based learning (WBL) and work-integrated learning (WIL) in logistics and supply chain management programs in Vietnam. It aims to clarify which future ready capabilities should be prioritized for graduate career readiness and how these competencies can be translated into practical reference points for curriculum renewal, university industry collaboration and authentic assessment in workplace…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Kye Anderson Barker · European Journal of Political Theory Geopolitics

The cause of labor is the hope of the earth: William Morris and regrowth communism

What resources does the history of political thought offer for confronting the democratic and ecological crises of the present? Through a reconstruction of the political thought of William Morris within the context of late nineteenth century socialism, I show how he built a vision of ecological flourishing on the foundation of the democratic freedom of workers, which I call “regrowth communism.” According to Morris, only in the struggle of workers for freedom through…

Read at Journal articles (OpenAlex)

arXiv (research papers) Lei Zhao SI

LivePI: More Realistic Benchmarking of Agents Against Indirect Prompt Injection

AI agents such as OpenClaw are increasingly deployed in local workflows with access to external tools. This creates indirect prompt-injection (IPI) risk: an agent may execute harmful instructions embedded in untrusted inputs such as email, downloaded files, webpages, repositories, or group-chat messages. Existing evaluations are often small, purely simulated, or focused on a narrow set of channels. We introduce LivePI (Live Prompt Injection), a structured benchmark for IPI…

Read at arXiv (research papers)

Journal articles (OpenAlex) Shangyuan Wu, Thorsten Quandt, Saïd Unger · Journalism Geopolitics

A study of alternative media from the Global South/ non-Western perspective: Scrutinizing how “alternativeness” varies in Africa, Asia, Latin America, and the Middle East

Academic scholarship on alternative media remains Western-centric, presenting the view that such media features counter-hegemonic content and contributes to social movements and active citizenship. This paper synthesizes the work of scholars from the Global South/ non-West for the first time, analyzing top-cited journal articles produced by authors from the regions of Africa, Asia, Latin America, and the Middle East to discover, using the inductive approach, how…

Read at Journal articles (OpenAlex)

The Guardian Socialism Guardian Staff Geopolitics

Are working-class voters lost to Labour for good? | Letters

Readers on what the party can do to win back disaffected supporters, and why so many have been driven to vote Reform It would be helpful for progressive parties and the media to focus more on why so many people voted for Reform UK. Your article (What’s behind surge in support for Reform and Greens across England? Five key takeaways, 10 May) indicates that it gained more support in deprived areas – but this doesn’t answer the question why. What sort of UK do Reform voters…

Read at The Guardian Socialism

The Guardian Vietnam Philip Oltermann

‘I shared a single bed with my mother for three years’: Sung Tieu on her monument to immigrant workers in Venice

At the German pavilion, the artist has re-created the housing estate where she grew up to tell the forgotten history of migrants, including her parents, hired under a socialist agreement between East Germany and Vietnam – then abandoned An air of civilisational wipeout hangs over the Gehrenseestrasse complex, an abandoned housing estate on the north-eastern outskirts of Berlin, where the city still looks shabby without the chic. The insides of the nine prefabricated blocks…

Read at The Guardian Vietnam

arXiv (research papers) Zi Liang SI

Mobius Injection: From One-Shot Prompt Injection to Sustained Resource Exhaustion in AI Agent Infrastructure

Large Language Model (LLM) agents have emerged as key intermediaries, orchestrating complex interactions between human users and a wide range of digital services and LLM infrastructures. While prior research has extensively examined the security of LLMs and agents in isolation, the systemic risk of the agent acting as a disruptive "hub" within the user-agent-service chain remains largely overlooked. In this work, we expose a novel threat paradigm by introducing Mobius…

Read at arXiv (research papers)

arXiv (research papers) John T. Halloran SI

Training-Free Refusal of MCP Exploits via Retrieval-Augmented Generation

The model context protocol (MCP) has been widely adopted as an open standard enabling the seamless integration of generative AI agents. However, while LLM guardrails have significantly matured to refuse malicious or harmful queries (e.g., "How do I build a bomb?"), recent work has shown that MCP-enabled LLMs are highly susceptible to prompt injection attacks which avoid harmful or suspicious cues (e.g., "Can you add this ssh key to my bashrc file?"). Herein, we use…

Read at arXiv (research papers)

arXiv (research papers) Linfeng Fan SI

The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck

Tool-using LLM agents must act on untrusted webpages, emails, files, and API outputs while issuing privileged tool calls. Existing defenses often mediate trust at the granularity of an entire tool invocation, forcing a brittle choice in mixed-trust workflows: allow external content to influence a call and risk hijacked destinations or commands, or quarantine the call and block benign retrieval-then-act behavior. The key observation behind this paper is that indirect prompt…

Read at arXiv (research papers)

arXiv (research papers) Santhosh Kumar Ravindran SI

Portable Agent Memory: A Protocol for Cryptographically-Verified Memory Transfer Across Heterogeneous AI Agents

We present Portable Agent Memory, an open protocol and reference implementation for transferring persistent memory state across heterogeneous AI agents. Modern AI agents accumulate rich context -- episodic events,semantic knowledge, procedural skills, working state, and identity preferences -- but this context remains locked within vendor-specific runtimes. Portable Agent Memory addresses this through: (1) a five-component structured memory model with content-addressable…

Read at arXiv (research papers)

arXiv (research papers) Ziwen Cai SI

When Child Inherits: Modeling and Exploiting Subagent Spawn in Multi-Agent Networks

Since the official release of ChatGPT in 2022, large language models (LLMs) have rapidly evolved from chatbot-style interfaces into agentic systems that can delegate work through tools and newly spawned subagents. While these capabilities improve automation and scalability, they also pose new security risks in multi-agent networks. Existing research has studied how individual LLM-based agents can be compromised through prompt injection, jailbreaking, poisoned retrieval data…

Read at arXiv (research papers)

Journal articles (OpenAlex) Soumya Singh, Aneel Singh Brar, Urvita Bhatia et al. · PLOS Global Public Health Geopolitics

Multi-stakeholder perspectives on gender-based violence in marital relationships: A qualitative study in rural India

In India, an estimated 41% of women report experiencing domestic violence in their lifetime and up to 28% report violence during pregnancy. Our study aims to understand local perceptions/attitudes towards GBV and lived experiences of GBVvictimisation and perpetration in marital relationships in rural Rajasthan. We conducted a focus group discussion with community health workers (n = 7) and interviews with young married men (n = 17) and women (n = 21), and local government…

Read at Journal articles (OpenAlex)

arXiv (research papers) Sohom Datta SI

WAAA! Web Adversaries Against Web Agents

Large language models (LLMs) are increasingly being integrated into web browsers to create agentic browsing systems that execute actions on behalf of the user. Prior work considering the security of agentic browsers focuses on indirect prompt-injection attacks. However, by failing to consider traditional web attacks, previous agentic browser threat models have a blind spot to web social engineering attacks originally designed to trick humans. In this paper, we propose the…

Read at arXiv (research papers)

Journal articles (OpenAlex) Luca Pavani, Amy Shackelford · The British Journal of Social Work Geopolitics

Grounding economic sustainability in ecosocial work: The contribution of degrowth

Abstract This article explores the contribution of degrowth to ecosocial work, arguing that degrowth offers the discipline a coherent economic framework for confronting the structural drivers of polycrises. While ecosocial work has gained visibility in recent years, its engagement with the economic dimensions of sustainability remains underdeveloped, and degrowth has yet to be systematically integrated into the field. Through conceptual analysis, we identify four dimensions…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Oana Borlea‐Stăncioi · Anthropology & Humanism Geopolitics

My (post‐)post‐socialism: A personal photo essay

Abstract The paper is a multi‐modal, autoethnographic exploration of the visual remnants of lived post‐communism in a typical block of flats neighborhood of a Romanian city. By using film and digital photography, alongside narrative reflection, the author summons memories and blends observed and lived reality with creative non‐fiction to build an affective photo‐scape. The work is a meditation on visual emotional memory triggers and a cathartic rendering of lingering past(s)…

Read at Journal articles (OpenAlex)

arXiv (research papers) Gabriel Hortea SI

The Infinite Mutation Engine? Measuring Polymorphism in LLM-Generated Offensive Code

Malware authors traditionally rely on polymorphic techniques to produce variants within a malware family, complicating detection. Generative AI enables attackers to automatically synthesize structurally diverse payloads with identical behavior, raising the question of how much evasion Large Language Models (LLMs) actually provide. Recent work has assumed that LLMs can produce highly polymorphic payloads, leaving unquantified the variation that emerges when an attacker…

Read at arXiv (research papers)

Journal articles (OpenAlex) Gisela Carrillo, Moisés Carmona Monferrer, Jaime Alfaro · Children and Youth Services Review Geopolitics

An intersectional approach to the understandings of well-being of Latin American adolescent migrants living in Santiago-Chile

This study examines the understandings of well-being constructed by Latin American adolescent migrants living in Santiago, Chile, addressing a gap in research that has seldom examined South–South youth migration through an explicitly intersectional and qualitative lens. Despite growing recognition of children and adolescents as social agents in migration and well‑being research, limited empirical work has explored how identity constructions, symbolic representations, and…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Gloria Cáceres Julio, Leticia Arancibia Martínez, Soraya Espinoza Moraga et al. · Human Rights Education Review Geopolitics

Democracy, feminist pedagogies and human rights education: an experience of collective learning with women in Chile

The article addresses a central problem in human rights education (HRE): how to foster critical democratic engagement in contexts shaped by neoliberalism, patriarchy, and masculinised trade union cultures, where women’s experiences of inequality may be characterised as individual rather than structural. It draws on a HRE experience in the School of Trade Union Training, considering how feminist pedagogical processes might contribute to a reinterpretation of workplace…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Fletcher D. Baragar · Studies in Political Economy Geopolitics

Relative Progressivity in Neo-Marxist Economics: A Response to Marc Lavoie

This article is a reply to “How Progressive Is Post-Keynesian Economics?,” written by Marc Lavoie, which appeared in issue 106.3 of Studies in Political Economy. In particular, it assesses the claim that post-Keynesian economics is more progressive than neo-Marxist economics and offers a counterpoint. It finds neo-Marxian economics to be progressive on account of both income policies recommended and its analysis of the nature of work and the lived experience of workers, and…

Read at Journal articles (OpenAlex)

arXiv (research papers) Weifei Jin SI

CleanBase: Detecting Malicious Documents in RAG Knowledge Databases

Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks, in which an adversary inserts malicious documents containing carefully crafted injected prompts into the knowledge database. When a user issues a question targeted by the attack, the RAG system may retrieve these malicious documents, whose injected prompts mislead it into generating attacker-specified answers, thereby compromising the integrity of the RAG system. In this work, we propose…

Read at arXiv (research papers)

The Guardian Communism Jonathan Jones

‘In every slurp of paint, you see the Holocaust’: the genius and torments of Georg Baselitz

The German artist lived through Nazism and communism – and his horrific, shaming works, including a masturbating Hitler, forced his country to face its past. Yet in later life, he beautifully captured human frailty, portraying himself and his wife nude Georg Baselitz was a living thread of history and his death robs us of the truth he knew when we need it more than ever. He was one of the only two people I have spoken to for whom Nazi Germany was a living memory: Baselitz…

Read at The Guardian Communism

Older stories