Results for “work”

Journal articles (OpenAlex) Rohan Kit Bains Stevenson · Critical Studies on Terrorism Geopolitics

Filling in the blind spot? Problematisations of ‘right-wing extremism’ in German federal-level P/CVE policy

This article interrogates how “right-wing extremism” is problematised in German federal-level policies to prevent and counter violent extremism (P/CVE). While scholarship has critiqued European P/CVE for its disproportionate focus on “Islamist extremism” and its “blind spot” regarding “right-wing extremism”, comparatively little work has examined how the latter is problematised once it enters the policy agenda. Employing Carol Bacchi’s What’s the Problem Represented to Be?…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Oliver Melbourne Allen, Yi Zu, Milo Z. Trujillo et al. · Social Media + Society Geopolitics

From Flowers to Fascism? The Cottagecore to Tradwife Pipeline on Tumblr

In this work, we collected and analyzed social media posts to investigate an aesthetic-based pipeline where users searching for Cottagecore content may find Tradwife content co-opted by white supremacists. Through quantitative analysis of over 200,000 Tumblr posts and qualitative coding of about 2350 Tumblr posts, we did not find evidence of an explicit radicalization. We found that problematic Tradwife posts found in the literature may be confined to Tradwife-only spaces…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jingyu Zhang SI

Language Model Agents Under Attack: A Cross Model-Benchmark of Profit-Seeking Behaviors in Customer Service

Customer-service LLM agents increasingly make policy-bound decisions (refunds, rebooking, billing disputes), but the same ``helpful'' interaction style can be exploited: a small fraction of users can induce unauthorized concessions, shifting costs to others and eroding trust in agentic workflows. We present a cross-domain benchmark of profit-seeking direct prompt injection in customer-service interactions, spanning 10 service domains and 100 realistic attack scripts grouped…

Read at arXiv (research papers)

arXiv (research papers) Panagiotis Theocharopoulos SI

Multilingual Hidden Prompt Injection Attacks on LLM-Based Academic Reviewing

Large language models (LLMs) are increasingly considered for use in high-impact workflows, including academic peer review. However, LLMs are vulnerable to document-level hidden prompt injection attacks. In this work, we construct a dataset of approximately 500 real academic papers accepted to ICML and evaluate the effect of embedding hidden adversarial prompts within these documents. Each paper is injected with semantically equivalent instructions in four different languages…

Read at arXiv (research papers)

Journal articles (OpenAlex) Mercedes A. Muñoz, Sophia H. Jenkins, Iván Carbajal et al. · Analyses of Social Issues and Public Policy Geopolitics

Intersecting Identities and Ideologies: Sociodemographic Predictors of 2024 Voting Among Mexican and Cuban Americans

Abstract Despite Latino Americans’ consistent support for the Democratic Party over the last five decades, the number of Latino Americans who voted for Donald Trump in the 2024 presidential election grew by 10% compared to the 2020 election. What ideological and sociodemographic factors apart from ethnic identity may have influenced their voting behavior in the 2024 Presidential Election? Although previous work has demonstrated a person's Latino identity strength can…

Read at Journal articles (OpenAlex)

arXiv (research papers) Kerem Zaman SI

Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization

Recent work, using the Biasing Features metric, labels a CoT as unfaithful if it omits a prompt-injected hint that affected the prediction. We argue this metric adopts a narrow notion of faithfulness and confuses unfaithfulness with incompleteness, the lossy compression needed to turn distributed transformer computation into a linear natural language narrative. On multi-hop reasoning tasks with instruct-tuned and reasoning models, many CoTs flagged as unfaithful by Biasing…

Read at arXiv (research papers)

arXiv (research papers) Kanchon Gharami SI

ChatGPT: Excellent Paper! Accept It. Editor: Imposter Found! Review Rejected

Large Language Models (LLMs) like ChatGPT are now widely used in writing and reviewing scientific papers. While this trend accelerates publication growth and reduces human workload, it also introduces serious risks. Papers written or reviewed by LLMs may lack real novelty, contain fabricated or biased results, or mislead downstream research that others depend on. Such issues can damage reputations, waste resources, and even endanger lives when flawed studies influence…

Read at arXiv (research papers)

The Guardian Socialism Keith Flett

Megan Davies obituary

My partner, Megan Davies, who has died aged 67, was for many years Cardiff’s highly regarded branch secretary of the Society of Telecom Executives, now part of the Prospect union. She was a lifelong socialist, a supporter of Socialist Worker and, until her recent ill health, was a regular at Palestine, anti-war and anti-racist protests. At her funeral Cor Cochion, a socialist choir, gave a passionate rendition of Nkosi Sikelel’ iAfrika, the South African national anthem. She…

Read at The Guardian Socialism

arXiv (research papers) Richard Helder Moulton SI

Quantifying Return on Security Controls in LLM Systems

Although large language models (LLMs) are increasingly used in security-critical workflows, practitioners lack quantitative guidance on which safeguards are worth deploying. This paper introduces a decision-oriented framework and reproducible methodology that together quantify residual risk, convert adversarial probe outcomes into financial risk estimates and return-on-control (RoC) metrics, and enable monetary comparison of layered defenses for LLM-based systems. A…

Read at arXiv (research papers)

Inter-American Dialogue Yifang Wang Geopolitics

Myers, The New York Times (16 Dec 2025)

Chinese officials and executives have become more cautious when engaging with Venezuela, while still looking for ways to work with Mr. Maduro’s government,

Read at Inter-American Dialogue

arXiv (research papers) Viet K. Nguyen SI

Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworks

Agentic AI introduces security vulnerabilities that traditional LLM safeguards fail to address. Although recent work by Unit 42 at Palo Alto Networks demonstrated that ChatGPT-4o successfully executes attacks as an agent that it refuses in chat mode, there is no comparative analysis in multiple models and frameworks. We conducted the first systematic penetration testing and comparative evaluation of agentic AI systems, testing five prominent models (Claude 3.5 Sonnet, Gemini…

Read at arXiv (research papers)

arXiv (research papers) Safwan Shaheer SI

Detecting Prompt Injection Attacks Against Application Using Classifiers

Prompt injection attacks can compromise the security and stability of critical systems, from infrastructure to large web applications. This work curates and augments a prompt injection dataset based on the HackAPrompt Playground Submissions corpus and trains several classifiers, including LSTM, feed forward neural networks, Random Forest, and Naive Bayes, to detect malicious prompts in LLM integrated web applications. The proposed approach improves prompt injection detection…

Read at arXiv (research papers)

OWASP GenAI Security Project John Sotiropoulos Security

OWASP Top 10 for Agentic Applications – The Benchmark for Agentic Security in the Age of Autonomous AI

Introducing the OWASP Top 10 for Agentic AI Applications - our community’s actionable framework for securing autonomous, tool-using AI systems. Built at global scale informed by real incidents, and based on our work already adopted across industry, this release marks a pivotal moment in turning insight into action, and advancing the security of Agentic Applications at the pace of innovation.

Read at OWASP GenAI Security Project

Journal articles (OpenAlex) Tom W. Etienne, Michal Onderčo, Sandra Destradi et al. · International Studies Quarterly Geopolitics

Populist Publics’ Affinity for Nuclear Weapons? Explaining Opposition to the Nuclear Sharing Weapons in European Populist Publics

Abstract Extant work studying the relationship between populism and nuclear weapons policy predicts a populist affinity for nuclear weapons. However, this relationship may not be so straightforward in Europe, which relies in part on the nuclear umbrella of the United States for its deterrence. We present a theory which asserts that the anti-elitism and popular sovereignty dimensions of populism may manifest as anti-Americanism and an affinity for Putin’s Russia, leading to…

Read at Journal articles (OpenAlex)

arXiv (research papers) Guanquan Shi SI

SoK: Trust-Authorization Mismatch in LLM Agent Interactions

Large Language Models (LLMs) are evolving into autonomous agents capable of executing complex workflows via standardized protocols (e.g., MCP). However, this paradigm shifts control from deterministic code to probabilistic inference, creating a fundamental Trust-Authorization Mismatch: static permissions are structurally decoupled from the agent's fluctuating runtime trustworthiness. In this Systematization of Knowledge (SoK), we survey more than 200 representative papers to…

Read at arXiv (research papers)

arXiv (research papers) Omar Farooq Khan Suri SI

Securing Large Language Models (LLMs) from Prompt Injection Attacks

Large Language Models (LLMs) are increasingly being deployed in real-world applications, but their flexibility exposes them to prompt injection attacks. These attacks leverage the model's instruction-following ability to make it perform malicious tasks. Recent work has proposed JATMO, a task-specific fine-tuning approach that trains non-instruction-tuned base models to perform a single function, thereby reducing susceptibility to adversarial instructions. In this study, we…

Read at arXiv (research papers)

arXiv (research papers) K. J. Kevin Feng SI

On the Regulatory Potential of User Interfaces for AI Agent Governance

AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target system-level safeguards (e.g., prompt injection monitors) or agent infrastructure (e.g., agent IDs). In this work, we explore a complementary approach: regulating user interfaces of AI agents as a way of enforcing transparency and behavioral…

Read at arXiv (research papers)

Simon Willison SI

Google Antigravity Exfiltrates Data

Google Antigravity Exfiltrates Data PromptArmor demonstrate a concerning prompt injection chain in Google's new Antigravity IDE: In this attack chain, we illustrate that a poisoned web source (an integration guide) can manipulate Gemini into (a) collecting sensitive credentials and code from the user’s workspace, and (b) exfiltrating that data by using a browser subagent to browse to a malicious site. The attack itself is hidden in 1px font on a web page claiming to offer an…

Read at Simon Willison

arXiv (research papers) Kaiyuan Zhang SI

BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents

The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application threat models. Prior work has identified prompt injection as a new attack vector for web agents, yet the resulting impact within real-world environments remains insufficiently understood. In this work, we examine the landscape of prompt injection attacks and synthesize a benchmark of attacks embedded in realistic HTML payloads…

Read at arXiv (research papers)

arXiv (research papers) Atharv Singh Patlan SI

Cross-User Poisoning: User-Task Boundary Failures in Multi-User Collaborative Language Agents

Language agents are moving from single-user assistants to shared collaborators in workspaces, forums, and group chats. A shared agent observes interleaved messages from multiple users, maintains persistent context, and executes tool actions, creating a boundary problem absent from standard single-user agents: the agent must decide not only whether an instruction is safe, but which user or task it is allowed to govern. We identify cross-user poisoning (CUP), where an…

Read at arXiv (research papers)