Results for “model”

Journal articles (OpenAlex) Michael Moncher, Christoph Paul, Adrian Schletter et al. · Journal of Functional Biomaterials Gadgets

Influence of Controlled Lighting Conditions on Smartphone-Based Augmented Reality Recognition of a 3D-Printed Dental Model for Implantological Applications

Smartphone-based augmented reality (AR) may help dentists visualize an implant axis during treatment or training. Before a virtual overlay can be displayed, however, the application must first recognize the real target reliably. This in vitro study tested how five lighting conditions affected recognition of a two-colored, 3D-printed polylactic acid (PLA) dental model by a Unity/Vuforia smartphone application. The application ran on a Samsung Galaxy S22. A GoPro HERO10…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jia-Chen Zhang SI

Invisible Ink Threats: Adversarial Goals Behind Legitimate Tasks in Computer-Use Agents

Computer-use agents (CUAs), which empower large language models to autonomously operate operating systems and the web, are increasingly vulnerable to indirect prompt injection attacks. A widely adopted defense is the human-in-the-loop paradigm, in which the agent pauses for explicit user confirmation before executing sensitive operations. While effective against conspicuously high-harm attacks, this defense offers little protection against what we term Invisible Ink Threats…

Read at arXiv (research papers)

arXiv (research papers) Qianlong Yang SI

Mitigating Visual Degradation in MLLMs via Spatial-Spectral Visual Anchor Learning

Despite the progress of multimodal large language models (MLLMs), they continue to exhibit deficiencies in visual perception. Following visual instruction tuning, internal MLLM representations rapidly deviate from their original semantic states during inference, causing severe information degradation. While existing methods attempt to leverage external vision foundation models (VFMs) to align internal representations, we find that direct alignment with VFMs enhances visual…

Read at arXiv (research papers)

Journal articles (OpenAlex) Williams Gilberto Jiménez García, Alberto Aziani, Yeison David Toro-Soto · Global Crime Geopolitics

Spatially dependent violence in strategic ports: criminal governance and territorial spillovers in Buenaventura, Colombia

Strategic ports embedded in global cocaine trafficking networks link transnational flows with local criminal governance, which may be associated with territorial competition and violence. We analyse 114 neighbourhoods in Buenaventura, Colombia’s port, using Spatial Durbin Models to capture local effects and spillovers. Homicide is spatially clustered. Drug seizures show the strongest positive association and positive spillovers across neighbouring areas. Extortion is…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) J. Kim, Taehyun Sung, Woonam Hwang et al. · Journal of Spacecraft and Rockets Space

On-Orbit Servicing-Integrated Maintenance Strategy for a Satellite Constellation

This paper proposes a maintenance strategy for a satellite constellation that utilizes on-orbit servicing (OOS). Under this strategy, the constellation operator addresses satellite failures in two ways: by deploying new satellites and by recovering failed satellites through OOS. We develop an inventory management model with a parametric replenishment policy for the maintenance process, which can evaluate the performance of the satellite constellation system. Based on this…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Trang Le, Duy Bui, Anh Pham · Contemporary Management Research Geopolitics

Determinants of Digital Transformation in the Organization: Empirical Evidence from the Vietnam Banking Sector

This study examines the key factors influencing digital transformation within Vietnam’s banking sector. To achieve this objective, the authors employ a quantitative approach that integrates Structural Equation Modeling (SEM) and fuzzy-set Qualitative Comparative Analysis (fsQCA) to analyze data collected from 450 banking employees across Vietnam. The findings reveal that factors such as technological infrastructure, leadership capability, employee competency, digital…

Read at Journal articles (OpenAlex)

arXiv (research papers) Neha Nagaraja SI

When Prompts Control Robots: Prompt Injection Attacks in Multi-Agent Robotic Systems

Large language models are increasingly integrated into autonomous robotic systems for task planning and control, but this integration exposes them to prompt injection attacks that can lead to unsafe decisions and physical harm. Multi-agent settings increase the risks through cross-agent contamination and broader attack surfaces. In this paper, we evaluate prompt injection attacks against an LLM-based multi-agent robotic system, considering both direct injections into task…

Read at arXiv (research papers)

arXiv (research papers) Jianshuo Dong SI

Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States

Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.g., malicious side-tasks hidden in external tool results. While many efforts have sought to address this threat, little is known about the internals of agentic LLMs when they are exposed to IPI attacks. For simplicity, we refer to this condition as IPI exposure. In this paper, we study IPI exposure from three perspectives. (1) Probing: Across eight models, including the 753B-parameter GLM-5.2 and the…

Read at arXiv (research papers)

arXiv (research papers) Minghui Pan SI

Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents

AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions. Yet LLMs often become substantially less safe when deployed as agents, and the source of this degradation remains poorly understood. In this paper, we identify schema-formatted tool specifications as a primary source of agent safety degradation and show, through white-box representation analysis, that…

Read at arXiv (research papers)

Journal articles (OpenAlex) Walter Bazán-Palomino, Diego Winkelried · Financial Innovation Geopolitics

Volatility spillovers from the United States and China to Latin American stock markets

Abstract Traditionally, the United States has been the major trading and financial partner of Latin America. However, since 2000 it has lost its hegemony in the region due to China’s growing influence. China’s emergence as a source of capital for Latin America has increasingly integrated both financial markets, potentially increasing the risk of volatility spillovers. Using a heterogeneous ARDL model, we study volatility transmission from the USA and China to six main Latin…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Daniel Al-Burgan, Jerzy Weremczuk · International Journal of Electronics and Telecommunications Gadgets

Real Time Face-to-Screen Distance Estimation on Smartphones Using Iris Diameter and the Pinhole Camera Model

This paper presents a proof-of-concept architecture that investigates if a standard smartphone front camera can estimate face-to-screen distance in real time by using the average human iris diameter as a biological scale reference within a pinhole camera model. The proposed Android implementation uses automatic eye region localization, camera intrinsic calibration, grayscale preprocessing, and random sample consensus circle fitting to measure iris diameter in pixels. To…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Rita Łabuz, Daniel Baldwin Hess · European Planning Studies Geopolitics

Assessing the 15-minute city in socialist-era housing estates: a multi-threshold pedestrian analysis in Kraków, Poland

This research investigates 24 socialist-era housing estates in Kraków, Poland, constructed between 1949 and 1989. We analyze current accessibility in these districts to essential services within 15-, 10- and 5-minute walking durations by employing a QGIS pedestrian network model to calculate accessibility indices for linking residential locations with neighbourhood amenities. Findings suggest that Kraków's housing estates offer near-universal 15-minute walking access to core…

Read at Journal articles (OpenAlex)

arXiv (research papers) Fazhong Liu SI

Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation

World models give embodied AI a predictive core: they compress observations into states, simulate action-conditioned futures, and enable planning beyond reactive control. This predictive layer, however, opens a new security boundary-compromise can propagate from data, sensors, prompts, or feedback into physical action. Rather than treating world models as an isolated component, this survey traces threats across their entire lifecycle-from data construction and representation…

Read at arXiv (research papers)

arXiv (research papers) Mingxiao Liu Hangzhou Dianzi University SI

Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents

Large Language Model (LLM)-driven multimodal agents are increasingly deployed to execute autonomous tasks via continuous audio interaction. While this paradigm enhances interaction naturalness, it introduces a critical yet under-explored attack surface, as audio inputs inevitably contain environmental noise beyond user control. In this paper, we investigate concurrent audio prompt injection attacks targeting multimodal agents. Distinct from traditional acoustic attacks on…

Read at arXiv (research papers)

Journal articles (OpenAlex) Ngoc‐Son Le · Journal of Contingencies and Crisis Management Geopolitics

The Political Determinants of Disaster Communication Governance in Diverse Regimes: Comparative Evidence From Typhoon Response in the Philippines and Vietnam

ABSTRACT This article investigates political forces shaping what becomes visible during typhoon disasters across contrasting regime types. Countering dominant assumptions that equate democracy with effective crisis communication, the study develops a Hybrid Crisis Communication System model examining how political structures, patronage systems, propaganda machinery, and media control determine information flows when disasters strike. Drawing on 636 documents collected over…

Read at Journal articles (OpenAlex)

arXiv (research papers) Eric Wallace SI

GPT-Red: Automated Red Teaming via Self-Play at Scale

We introduce \textbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs. The goal of this model is to evaluate and improve the robustness of our production systems. To this end, we use it to adversarially train GPT-5.6, our most robust model to prompt injections to date. To create GPT-Red, we design a scalable self-play algorithm where the model is tasked with attacking a diverse population of…

Read at arXiv (research papers)

arXiv (research papers) Max Landauer SI

Just Testing, Move Along: Evasion of LLM-based System Log Interpretation by Prompt Injection

Large Language Models (LLMs) are increasingly integrated into Security Operations Center (SOC) workflows, where they support analysts in tasks such as the interpretation of system logs. However, the ability of LLMs to directly process untrusted textual input also introduces new attack surfaces. In particular, attackers can inject contextual information or explicit instructions into log entries in order to influence how malicious activity is interpreted by the model. Despite…

Read at arXiv (research papers)

arXiv (research papers) Mohan Manivannan SI

Agentic Cloud Decoys: A Deception-Driven Framework for Autonomous Intrusion Investigation

Cloud telemetry arrives at a scale that, paradoxically, makes intrusion understanding harder rather than easier. Attackers operate through legitimate identity, federated session tokens, and cloud native APIs indistinguishable from routine administration, and analysts spend an incident reconstructing context the logs already contain. We present Cloud Decoy AI Agent, a framework pairing a high fidelity cloud decoy with an autonomous language model agent that compresses the…

Read at arXiv (research papers)

arXiv (research papers) Zhaoxi Zhang SI

Are You Still the Agent I Authorized? Earned Authority under a Fixed Ceiling for Evolving Agents

Long-lived AI agents increasingly evolve after deployment by retaining experience, acquiring skills and tools, revising workflows, delegating work, and moving across task phases. This improves adaptation but creates a distinct authorization problem. Tool-enabled agents can turn model errors and prompt injections into consequential external actions; when evolution occurs under a live grant, the subject exercising that authority or the context in which it acts may no longer…

Read at arXiv (research papers)

Simon Willison SI

Quoting Boris Cherny

More than any of these eval scores, what is most exciting to me is something else: Opus 5 is our least prompt injectable model yet. It is a bit buried in the system card, but across PI evals and red teaming, Opus 5 is very hard to prompt inject successfully. — Boris Cherny, here's that System Card section, page 73 Tags: ai, prompt-injection, generative-ai, llms, anthropic, claude, boris-cherny

Read at Simon Willison

Journal articles (OpenAlex) Thuy Thu Nguyen, Phan Thanh Hoa · Information and Computer Security Geopolitics

Deepfake awareness and privacy protective behaviours: evidence from Vietnamese young faceswap apps users

Purpose Deepfakes are synthetic media (audio recordings, videos or photos) created using artificial intelligence. In recent years, deepfakes have become an increasing concern for internet users; therefore, protecting oneself from cybercrime attacks is vital. The purpose of this study is to use the Technology Acceptance Model and Protection Motivation Theory to build a serial mediation model of the relation between deepfake awareness, perceived security and privacy risks…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jay Barach SI

ResumeShield: Channel Separation and an Open Benchmark for Indirect Prompt Injection in AI Resume Screening

An AI resume screener reads a document supplied by the person it is evaluating, inverting the usual trust relationship between an assessor and the material it assesses. Candidates exploit this by concealing instructions inside a resume using white text, zero font size, hidden elements, markup comments, document metadata, or zero width characters. A human reviewer sees nothing, while a naive extraction pipeline places the concealed text into the model prompt, where it is read…

Read at arXiv (research papers)

arXiv (research papers) Tejaswi V. Panchagnula SI

Inference-Time Mitigation of Adversarial Political Bias in Large Language Models

As Large Language Models (LLMs) become the mainstay for information retrieval and summarization tasks, ensuring that they are always non-partisan and invulnerable to political bias is a critical step towards safer and more trustworthy Artificial Intelligence (AI). Current model alignment paradigms, such as reinforcement learning from human feedback (RLHF), make LLMs follow overarching safety instructions. However, this instruction tuning can be exploited via adversarial…

Read at arXiv (research papers)

arXiv (research papers) Yedidel Louck SI

Protocol-Level Attacks on Agentic Commerce Platforms: A Cross-Platform Taxonomy, AIP-Bench, and Unified Defense

Agentic commerce platforms let AI agents autonomously discover services, move payments, and wield user credentials on their users' behalf, and they already handle real money. Their security has so far been studied almost entirely at the level of the AI model, through prompt injection and misalignment. We show that the more consequential risks lie one layer down, in the protocol between agents and commerce services. There, vulnerabilities are structural : exploitation is…

Read at arXiv (research papers)

arXiv (research papers) Zhetong Zhang SI

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure

As Video Large Language Models are increasingly deployed in real-world applications, ensuring their safety alignment has become critical. Counterintuitively, we find that harmful videos paired with benign queries achieve higher attack success rates than the same videos paired with explicitly harmful queries. To understand the underlying mechanism of this vulnerability, we present V-DEAL, a three-level diagnostic framework that jointly analyzes this failure across model…

Read at arXiv (research papers)

arXiv (research papers) Yanyu Chen SI

Reinforcement Learning for Large Language Model Selective Evidence Adoption from Contaminated Retrieval Results

Retrieval-augmented large language models frequently face contexts that interleave useful evidence with misleading statements or instruction-like content. Blanket refusal discards valid evidence, whereas uncritical adoption yields incorrect or unsafe answers. The ability to selectively adopt relevant information while rejecting deceptive or harmful content is therefore critical for reliable deployment in real-world retrieval settings. We introduce SelectBench, a controlled…

Read at arXiv (research papers)

arXiv (research papers) Or Zion Eliav SI

Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents

Traditional pentesting uses reconnaissance at each step to uncover unseen weaknesses, build stronger attacks, and advance the objective; we argue that AI agents require the same treatment. We formalize agent reconnaissance by modeling the process and identifying the knowledge assets it seeks to extract: what they are, how they are used, and which agent weaknesses they exploit to give adversaries leverage in indirect prompt injection attacks. We instantiate these insights in…

Read at arXiv (research papers)

arXiv (research papers) Zhanhao Hu SI

Twin Agent: Context Residual Compression for Privilege Separated Agents

Large language model (LLM) agents are vulnerable to security risks, such as prompt injection attacks from untrusted context that manipulate downstream reasoning and tool use. Existing secure-by-design approaches mitigate this risk by separating untrusted observations from privileged execution and careful control of information flow, but often degrade utility and require extensive task-specific engineering. We thus propose Twin Agent, a general privilege separation design…

Read at arXiv (research papers)

arXiv (research papers) Xinting Liao SI

CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization

Textual Collaborative Prompt Optimization (TCPO) extends TextGrad (Yuksekgonul et al., 2025) to a decentralized setting by allowing multiple clients to jointly improve prompts for large language models (LLMs) while keeping their data locally. Its reliance on free-form textual updating and aggregation introduces a new and largely unexplored attack surface, i.e., malicious instructions can be injected into local prompts and propagated through server-side prompt aggregation…

Read at arXiv (research papers)

Older stories