Results for “models”

NVIDIA Blog Eva-Maria Hempe SI

NVIDIA Open Models Power a New Wave of European Public Sector Projects

Governments need modern solutions to serve the public while keeping sensitive information under their control. Open models provide a path forward, letting governments evaluate them, adapt them to local languages and public services, run them on infrastructure they control, apply their own safeguards and keep sensitive data within controlled environments. Some open models go further,

Read at NVIDIA Blog

Journal articles (OpenAlex) C. Daniel Antenucci, Andrea Rizzotti · Frontiers The Interdisciplinary Journal of Study Abroad Geopolitics

Geopolítica, asimetrías, colonialidad y justicia epistémica: repensar la educación internacional desde América Latina [Geopolitics, asymmetries, coloniality, and epistemic justice: rethinking international education from Latin America]

The internationalization of higher education, often portrayed as a process of cooperation and global openness, continues to reproduce the structural asymmetries of the world knowledge system. This study analyzes the relationship between geopolitics, coloniality, and epistemic justice from a Latin American perspective, integrating data on academic mobility, educational investment, and national policy models. The results show a strong concentration of international students in…

Read at Journal articles (OpenAlex)

Infosecurity Magazine Security

Symantec Uncovers AI Agent Hijacking Models for Autonomous Cyber-Attacks

Researchers at Symantec have uncovered an AI agent designed to operate a full cyber-attack without human intervention

Read at Infosecurity Magazine

arXiv (research papers) Frank Breitinger SI

Prompt Injection Through Forensic Evidence: A Taxonomy and Proof of Concept of Anti-Forensic Attacks on LLM-Assisted Digital Investigations

Large language models (LLMs) are entering digital forensics as examination assistants and autonomous agents. Digital forensics inverts the usual setting for indirect prompt injection: the evidence under analysis is attacker-controlled by definition, and the examiner is obliged to read it closely. This makes the reasoning layer a new anti-forensic target, next to the classical ones of data and tools. Classical anti-forensic taxonomies do not cover it, and prompt injection…

Read at arXiv (research papers)

arXiv (research papers) Yiheng Li SI

MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning

With the rapid integration of Multi-modal Large Language Models (MLLMs) into real-world applications, Prompt Injection (PI) has emerged as a critical security threat. Attackers can conceal malicious instructions within textual narratives or visual inputs to bypass safety alignment. Existing approaches, such as signature- and perplexity-based methods, rely heavily on pattern matching, making them insufficient to detect sophisticated, cross-modal PI payloads. In this paper, we…

Read at arXiv (research papers)

arXiv (research papers) Peiyang Liu SI

Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint

Retrieval-augmented generation (RAG) systems face security, privacy, and copyright risks including content leakage, source reconstruction, unauthorized access, data poisoning, and prompt injection. Yet RAG protection studies use incompatible evaluation metrics, datasets, and threat models. We present a systematic survey and human-coded evidence map of 118 full-text-confirmed RAG defense papers, organized by measured endpoint rather than claimed goal or defense mechanism. Our…

Read at arXiv (research papers)

Journal articles (OpenAlex) Paolo Muratore-Ginanneschi, Bayan Karimi, Jukka P. Pekola · Journal of Statistical Physics

Decay of the Survival Probability of a Local Excitation in Multi-qubit Platforms

Abstract We present a theoretical study of the survival probability of a state initially prepared in the one-particle sector of a multi-qubit system. The motivation for our work is the ongoing laboratory development of multi-qubit platforms based on superconducting circuits. Using elementary concepts of random matrix theory, we obtain analytic expressions for the survival probability in mathematical models of platforms which, albeit stylized, have been previously shown to…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Bülent Aras, Burcu Fazlioglu · German Politics Geopolitics

Germany’s Diplomatic Pulse: A Data-Driven Examination of Shifting Foreign Policy Priorities (1991–2023)

This article empirically investigates the fundamental reorientation of Germany’s foreign policy from a normative, trade-centric ‘civilian power’ to a pragmatic ‘strategic hedger’ in response to a fragmenting global order. To bridge the gap between political rhetoric and actual state behaviour, the study introduces an original large-N dataset tracking official international bilateral visits by German Chancellors from 1991 to 2023. By utilising logit regression models to…

Read at Journal articles (OpenAlex)

arXiv (research papers) Pedro H. Barcha Correia SI

Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise

The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt injection and jailbreak attacks. By embedding malicious instructions, these exploits manipulate language models to bypass intended behavior and operational boundaries. In traditional chatbots, such attacks are confined to a single session because state memory is not preserved across conversations. However, persistent memory features in modern conversational…

Read at arXiv (research papers)

arXiv (research papers) Abhishek Rai SI

Context-Aware Prompt Injection Detection via Small Language Models in RAG Pipelines: nokast-secureRAG

Local Retrieval-Augmented Generation (RAG) systems are vulnerable to indirect prompt injection and retrieval poisoning, where malicious instructions in retrieved content are mistaken for trusted input. We present nokast-secureRAG, a roughly 0.5B-parameter small language model that acts as a semantic firewall between retrieval and generation. It jointly evaluates the user query and retrieved context, classifying the pair as safe, suspicious, or malicious. The model is trained…

Read at arXiv (research papers)

arXiv (research papers) Vasisht Duddu SI

KNOX: Hardware-assisted Regulatory Sandbox for Generative Models

Regulations require companies to run AI models in a regulatory sandbox, an isolated environment that enables monitoring model behavior by regulators, prior to deployment. But, they do not spell out the technical mechanisms to design such a sandbox. Ideally, a regulatory sandbox should show (i) compliance (checks against regulations, and deviations from intended behavior, i.e., unauthorized tool and system calls); (ii) confidentiality (protects model weights from regulators)…

Read at arXiv (research papers)

SiliconANGLE AI James Farrell SI

Trump administration orders ban on DeepSeek in federal agencies

The Department of Homeland Security has ordered artificial intelligence technology from the Chinese company DeepSeek Ltd. be removed from all federal civilian agencies. The order, published on the Federal Register website today, warned that DeepSeek’s AI models present “multiple threat vectors,” that could give the Chinese Communist Party “extensive authority” to access American government infrastructure.

Read at SiliconANGLE AI

arXiv (research papers) Yuchen Chen SI

RAGLeak: Supply-Chain Privacy Backdoors in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) enables large language models to access external knowledge during inference, but its reliance on external knowledge bases also introduces new attack surfaces. Existing data extraction attacks against RAG systems rely on either prompt injection, which heavily depends on the generator's instruction-following capability, or backdoors that reproduce or paraphrase retrieved documents but struggle to balance extraction fidelity and…

Read at arXiv (research papers)

Journal articles (OpenAlex) S. Suganya, T. Manikandan · African Journal of Science Technology Innovation and Development Space

Scalable and robust deep learning models for space debris detection across orbital regimes and observation platforms

Space debris poses a significant threat to space missions, requiring accurate and real-time detection across multiple orbital regimes and observation platforms. This study aims to develop a scalable YOLOv12-PSO framework for accurate space debris detection and to investigate its effectiveness in improving real-time performance, robustness, and detection accuracy across orbital environments. A publicly available space debris image dataset containing synthetic and real images…

Read at Journal articles (OpenAlex)

MIT News AI Zach Winn | MIT News SI

Giving AI a “crystal clear” view of the materials world

New research can help AI models understand crystalline materials in 3D and reason about their properties.

Read at MIT News AI

Journal articles (OpenAlex) Trung Thanh Bui · Asian-Pacific Economic Literature Geopolitics

Monetary Policy in Vietnam: Changes Over Time

ABSTRACT In the past decades, Vietnam has experienced a prolonged period of rapid economic growth. Many argued that the State Bank of Vietnam (SBV), which is an essential part of the Vietnamese government, makes a significant contribution to that achievement. However, high inflation in certain periods raises doubts about that compliment. Furthermore, studies of monetary policy in Vietnam mostly relied on constant‐parameter models such as VAR, which may not be proper as…

Read at Journal articles (OpenAlex)

MIT News AI Shafaq Zia | Whitehead Institute SI

AI model decodes the language cells use to communicate

A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.

Read at MIT News AI

Just Security Bulelani Jili Geopolitics

The Mythos of Digital Sovereignty

AI models such as Anthropic's Claude Mythos raise questions about access to frontier AI and institutional capacity.

Read at Just Security

arXiv (research papers) Qianlong Lan SI

From Detection to Decision: Calibration and Deferral for Prompt-Injection Detection

Prompt-injection defenses are commonly evaluated as binary detectors, although deployed LLM applications must make operational decisions about whether to allow, block, or escalate potentially malicious inputs. Recent probabilistic decision models aim to support such decisions through calibrated confidence estimates, but their reliability under distribution shift remains uncertain. We evaluate a native probabilistic decision model (Jev), two Llama Prompt Guard 2 classifiers…

Read at arXiv (research papers)

Google DeepMind blog SI

Google DeepMind and Singapore Government collaborate to build fine-tuned AI model for scam detection

Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.

Read at Google DeepMind blog

Journal articles (OpenAlex) John Willoughby · Review of Radical Political Economics Geopolitics

Introduction to the Symposium: Assessing David Gordon’s Contributions to Contemporary American Capitalism Thirty Years After His Death

It has been thirty years since David Gordon’s untimely passing from heart disease at the age of fifty-one. He wrote on urban economics, poverty, labor market segmentation, the political economy of racism, the dynamics of capitalist evolution over long periods, and neo-Marxist models of the macroeconomy. This symposium consists of four articles by younger and older scholars who extend and critique Gordon’s contributions. Our hope is that this symposium will stimulate others…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yifan Lan SI

DecisionRobust: Benchmarking Robustness for JEV Style Decision Models Across Text and Vision

Emerging decision models such as JEV provide typed interfaces that map task instructions and observations directly to choices, judgments, and scores. As these models are increasingly used for automated decision-making, understanding their reliability under adversarial manipulation becomes critical. We introduce DecisionRobust, a benchmark for systematically evaluating the robustness of decision models across textual and visual inputs. Our benchmark covers practical…

Read at arXiv (research papers)

Journal articles (OpenAlex) Piotr Żuk, Paweł Żuk · Health Care Analysis Geopolitics

Between Postmodernism and Medical Populism: Cultural Determinants of Conspiracy Theories on Vaccination After Experience of the COVID-19 Pandemic

The primary objective of the study was to analyse the correlations between belief in and acceptance of vaccine-related conspiracy theories and prevailing cultural models. The authors emphasise that not only right-wing populism and fundamentalist beliefs, but also postmodern relativism, may contribute to the rejection of established medical knowledge and practices. Drawing on a survey conducted among a representative sample of 1000 members of the Polish population using…

Read at Journal articles (OpenAlex)

Microsoft Research blog SI

Simulating student learning for better AI tutoring

StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across subjects like chess, writing, and mathematics.

Read at Microsoft Research blog

arXiv (research papers) Anning Hu SI

StableJudge: A Lightweight Adversarial Defense Framework for LLM-as-a-Judge

Large language models (LLMs) are increasingly used as judges to assign scalar scores that drive downstream decision-making, including tasks such as paper review and recommendation. However, LLM-as-a-Judge pipelines are vulnerable to score-hijacking prompt injection embedded in evaluated content, which corrupts scoring signals and distorts induced rankings. Existing defenses often enforce robustness by modifying the judge model itself, making safety dependent on a specific…

Read at arXiv (research papers)

arXiv (research papers) Quanyan Zhu SI

Computational Reflective Equilibrium for Agentic AI: A Rawlsian Alignment Scaffold for Governance

The rapid deployment of agentic AI has introduced complex challenges for the ethics and governance of AI systems. Agents built on large language models act through tools on behalf of people, and each deployment case brings its own instructions, policies, evidence, and stakeholders, so alignment must be formed case by case. To this end, this work proposes agentic reflective equilibrium (ARE), a computational reflective equilibrium framework that serves as an ethical alignment…

Read at arXiv (research papers)

Journal articles (OpenAlex) Anna Karwińska, Dorota Jopek, Michał Kudłacz et al. · Acta Polytechnica CTU Proceedings Geopolitics

Specific conditions for the post-socialist cities’ operation and development in the context of contemporary challenges

The article presents the specific economic, social, and spatial conditions of post-socialist cities, comparing them with the development models characteristic of Western European cities (the welfare-state model). Particular attention is given to historical and structural factors that continue to influence the functioning and adaptability of these cities. Subsequently, the authors identify major contemporary challenges facing European cities, including globalization, the…

Read at Journal articles (OpenAlex)

arXiv (research papers) Michael Cardei SI

Only What You've Signed up For: Secure Workflows with Constrained Diffusion Agents

As agentic AI systems take on increasingly complex and consequential tasks, securing them against prompt injection becomes critical. Existing defenses often rely on detecting or reasoning about injected malicious instructions and can therefore remain vulnerable to adaptive attacks that optimize the injection itself. Diffusion language models (dLLMs), an emerging framework for language generation, offer a new opportunity for security enforcement: by iteratively refining their…

Read at arXiv (research papers)

Journal articles (OpenAlex) Jun Wu, Zhewei Mao · International Journal of Offender Therapy and Comparative Criminology Geopolitics

A Social Network Analysis of the Structure and Leadership Roles of a Drug Trafficking Group in China: A Case Study

Despite the proliferation of social network analysis (SNA) in criminological research, our understanding of criminal leadership remains heavily skewed toward Western organized crime group models. This study contributes a descriptive case study of an underrepresented context by examining the structure and leadership of a domestic drug trafficking group in China ( N = 27), using data from a publicly available court verdict. Unlike the insulated shot-callers often found in…

Read at Journal articles (OpenAlex)

China-US Focus Christopher A. McNally Geopolitics

The U.S.-China AI Rivalry is Being Upended

The U.S.-China AI rivalry is being reshaped by the rapid advance of frontier models and a widening divide between U.S.-led closed systems and China’s increasingly competitive open-weight ecosystem. As AI systems become more autonomous and capable, the race for technological leadership is creating r

Read at China-US Focus

Older stories