Results for “model”

arXiv (research papers) Yanting Wang SI

AgentWatcher: A Rule-based Prompt Injection Monitor

Large language models (LLMs) and their applications, such as agents, are highly vulnerable to prompt injection attacks. State-of-the-art prompt injection detection methods have the following limitations: (1) their effectiveness degrades significantly as context length increases, and (2) they lack explicit rules that define what constitutes prompt injection, causing detection decisions to be implicit, opaque, and difficult to reason about. In this work, we propose…

Read at arXiv (research papers)

Journal articles (OpenAlex) Jessica Barría Meneses · Land Geopolitics

Consequences of Chilean Neoliberal Policy on Rural Territories: A Case Study of the Rise in Land Transactions in the Commune of Hualaihué (Los Lagos Region)

Chile’s economic development model, which was shattered by the military coup, restructured under the dictatorship, and institutionalised under democracy as a neoliberal model, gave rise to a liberalisation process that affects the country’s natural resources and commercial dynamics and, by extension, places society itself at the service of the system. This model, enshrined in the 1980 Political Constitution, was founded on the principles of external openness, private…

Read at Journal articles (OpenAlex)

arXiv (research papers) Cormac Guerin SI

KAIJU: An Executive Kernel for Intent-Gated Execution of LLM Agents

Tool-calling autonomous agents based on large language models using ReAct exhibit three limitations: serial latency, quadratic context growth, and vulnerability to prompt injection and hallucination. Recent work moves towards separating planning from execution but in each case the model remains coupled to the execution mechanics. We introduce a system-level abstraction for LLM agents which decouples the execution of agent workflows from the LLM reasoning layer. We define two…

Read at arXiv (research papers)

arXiv (research papers) Chong Xiang SI

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our vision for system-level defenses against indirect prompt injection attacks. We articulate three positions: (1) dynamic replanning and security policy updates are often necessary for dynamic tasks and realistic environments; (2) certain…

Read at arXiv (research papers)

arXiv (research papers) Meiwen Ding SI

Covert Visual Prompt Injection against Commercial Multimodal Large Language Models

Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks. Existing prompt injection methods predominantly rely on textual prompts or perceptible visual prompts that are observable by human users. In this work, we study imperceptible visual prompt injection against powerful closed-source MLLMs, where adversarial instructions are embedded in…

Read at arXiv (research papers)

arXiv (research papers) Duanyi Yao SI

Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models

Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this recommendation-seeking behavior to inject unauthorized advertisements. Unlike traditional pattern-triggered backdoors that rely on artificial triggers such as pixel patches or special tokens, Hidden Ads activates on natural user behaviors: when users…

Read at arXiv (research papers)

arXiv (research papers) Surada Suwansathit SI

A Security Analysis of the OpenClaw AI Agent Framework

AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a systematic taxonomy of 470 advisories filed against OpenClaw, an open-source AI agent runtime, organized by architectural layer and trust-violation type. Vulnerabilities cluster along two orthogonal axes: (1) the system axis, reflecting the…

Read at arXiv (research papers)

Latinoamérica21 Xavier Rodríguez-Franco Geopolitics

¿Cambio político inminente en Cuba?

Durante el primer trimestre 2026, Cuba ocupa un lugar central en la conversación política de América Latina. A más de seis décadas del triunfo de la Revolución Cubana, el modelo político de la isla enfrenta una convergencia creciente de presiones internas y externas que plantean un desafío para la continuidad de la dictadura de partido único más antigua del hemisferio. Y es que el debate sobre un eventual cambio político tiene más repercusión que nunca tanto dentro como…

Read at Latinoamérica21

arXiv (research papers) Hieu Xuan Le SI

Prompt Attack Detection with LLM-as-a-Judge and Mixture-of-Models

Prompt attacks, including jailbreaks and prompt injections, pose a critical security risk to Large Language Model (LLM) systems. In production, guardrails must mitigate these attacks under strict low-latency constraints, resulting in a deployment gap in which lightweight classifiers and rule-based systems struggle to generalize under distribution shift, while high-capacity LLM-based judges remain too slow or costly for live enforcement. In this work, we examine whether…

Read at arXiv (research papers)

arXiv (research papers) Haozhen Wang SI

PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications. However, their practical deployment is often hindered by issues such as outdated knowledge and the tendency to generate hallucinations. To address these limitations, Retrieval-Augmented Generation (RAG) systems have been introduced, enhancing LLMs with external, up-to-date knowledge sources. Despite their advantages, RAG systems remain vulnerable to adversarial attacks…

Read at arXiv (research papers)

Journal articles (OpenAlex) Adolfo Donoso, Jorge González, Jaime Otárola · Chilean journal of agricultural research Geopolitics

Economic assessment of Chilean agricultural land use, labor demand and input requirements using the Delphi method. Part A: Fruits and nuts for fresh consumption

Fresh fruit production plays a central role in the agricultural sector of Chile, particularly under an export-led growth (ELG) model.This study aimed to examine the dynamics of Chilean fresh fruit production and market structure between 2017 and 2021, focusing on labor demand, agrochemical inputs, and export value evolution.Using a modified Delphi method, we estimated yield ranges and full-production area equivalents for key fruit crops, based on internal consumption…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Camila Ponce Lara · Human Geography Geopolitics

Lithium and green extractivism in Chile: Discourses and practices during Gabriel Boric's government

This article analyzes green extractivism during Gabriel Boric's government in Chile, focusing on lithium policies. We examine the tension between environmentalist rhetoric and extractive practices by analyzing the lithium policy implementation, where negotiations with Chinese companies for value-added production coexist with agreements that consolidate the traditional extractive model, extending exploitation rights in the Atacama Salt Flat until 2050. Using discourse…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yulin Shen SI

Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search

Recent advances in the Model Context Protocol (MCP) have enabled large language models (LLMs) to invoke external tools with unprecedented ease. This creates a new class of powerful and tool augmented agents. Unfortunately, this capability also introduces an under explored attack surface, specifically the malicious manipulation of tool responses. Existing techniques for indirect prompt injection that target MCP suffer from high deployment costs, weak semantic coherence, or…

Read at arXiv (research papers)

Simon Willison SI

Auto mode for Claude Code

Auto mode for Claude Code Really interesting new development in Claude Code today as an alternative to --dangerously-skip-permissions: Today, we're introducing auto mode, a new permissions mode in Claude Code where Claude makes permission decisions on your behalf, with safeguards monitoring actions before they run. Those safeguards appear to be implemented using Claude Sonnet 4.6, as described in the documentation: Before each action runs, a separate classifier model reviews…

Read at Simon Willison

arXiv (research papers) Qianlong Lan SI

The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense

Deploying large language models (LLMs) as autonomous browser agents exposes a significant attack surface in the form of Indirect Prompt Injection (IPI). Cloud-based defenses can provide strong semantic analysis, but they introduce latency and raise privacy concerns. We present the Cognitive Firewall, a three-stage split-compute architecture that distributes security checks across the client and the cloud. The system consists of a local visual Sentinel, a cloud-based Deep…

Read at arXiv (research papers)

arXiv (research papers) Ali Dehghantanha SI

SoK: The Attack Surface of Agentic AI - Tools and Autonomy

Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation (RAG), and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly enlarges the attack surface. In this systematization, we map out the trust boundaries and security risks of agentic LLM-based systems. We develop a comprehensive taxonomy of attacks spanning prompt-level injections, knowledge-base…

Read at arXiv (research papers)

arXiv (research papers) Michael Hind SI

LLMON: An LLM-native Markup Language to Leverage Structure and Semantics at the LLM Interface

Textual Large Language Models (LLMs) provide a simple and familiar interface: a string of text is used for both input and output. However, the information conveyed to an LLM often has a richer structure and semantics, which is not conveyed in a string. For example, most prompts contain both instructions ("Summarize this paper into a paragraph") and data (the paper to summarize), but these are usually not distinguished when passed to the model. This can lead to model…

Read at arXiv (research papers)

arXiv (research papers) Charoes Huang SI

Model Context Protocol Threat Modeling and Analyzing Vulnerabilities to Prompt Injection with Tool Poisoning

The Model Context Protocol (MCP) has rapidly emerged as a universal standard for connecting AI assistants to external tools and data sources. While MCP simplifies integration between AI applications and various services, it introduces significant security vulnerabilities, particularly on the client side. In this work we conduct threat modelings of MCP implementations using STRIDE (Spoofing, Tampering, Repudiation, Information Disclosure, Denial of Service, Elevation of…

Read at arXiv (research papers)

arXiv (research papers) Marco Arazzi SI

SecureBreak -- A dataset towards safe and secure models

Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Although previous related works focused primarily on model architectures and alignment methodologies, these approaches alone cannot ensure the complete elimination of harmful generations. This concern is reinforced by the growing body of scientific literature showing that attacks, such…

Read at arXiv (research papers)

arXiv (research papers) Charoes Huang SI

Are AI-assisted Development Tools Immune to Prompt Injection?

Prompt injection is listed as the number-one vulnerability class in the OWASP Top 10 for LLM Applications that can subvert LLM guardrails, disclose sensitive data, and trigger unauthorized tool use. Developers are rapidly adopting AI-assisted development tools built on the Model Context Protocol (MCP). However, their convenience comes with security risks, especially prompt-injection attacks delivered via tool-poisoning vectors. While prior research has studied prompt…

Read at arXiv (research papers)

Journal articles (OpenAlex) Bülent Aras, Pınar Akpinar · Contemporary Politics Geopolitics

Beyond liberal peace? Qatar’s ’hybrid’ mediation and the politics of peacemaking in Afghanistan

This article examines the State of Qatar’s distinctive diplomatic strategy as a non-Western mediator in the protracted Afghan conflict, offering a structural critique of the traditional liberal peacebuilding model. Guided by foreign policy role theory, the study operationalises the concept of ‘hybrid mediation’ to demonstrate how Qatar analytically bridges the non-threatening ideational posture of a small state with the infrastructural capacity typically reserved for great…

Read at Journal articles (OpenAlex)

arXiv (research papers) Abed K. Musaffar SI

Detection of adversarial intent in Human-AI teams using LLMs

Large language models (LLMs) are increasingly deployed in human-AI teams as support agents for complex tasks such as information retrieval, programming, and decision-making assistance. While these agents' autonomy and contextual knowledge enables them to be useful, it also exposes them to a broad range of attacks, including data poisoning, prompt injection, and even prompt engineering. Through these attack vectors, malicious actors can manipulate an LLM agent to provide…

Read at arXiv (research papers)

arXiv (research papers) Shawn Li SI

The Autonomy Tax: Defense Training Breaks LLM Agents

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against prompt injection attacks that manipulate agent behavior through malicious observations or retrieved content. We reveal a fundamental \textbf{capability-alignment paradox}: defense training designed to improve safety systematically destroys…

Read at arXiv (research papers)

arXiv (research papers) Md Takrim Ul Alam SI

Prompt Control-Flow Integrity: A Priority-Aware Runtime Defense Against Prompt Injection in LLM Systems

Large language models (LLMs) deployed behind APIs and retrieval-augmented generation (RAG) stacks are vulnerable to prompt injection attacks that may override system policies, subvert intended behavior, and induce unsafe outputs. Existing defenses often treat prompts as flat strings and rely on ad hoc filtering or static jailbreak detection. This paper proposes Prompt Control-Flow Integrity (PCFI), a priority-aware runtime defense that models each request as a structured…

Read at arXiv (research papers)

InSight Crime Juan Carlos Garzon

5 Models of Criminal Control Over Fentanyl Markets in Northern Mexico

5 Models of Criminal Control Over Fentanyl Markets in Northern Mexico In various parts of Mexico, local drug markets do not operate according to supply-and-demand logics alone. What is sold, how it is sold, how much it costs, where it is

Read at InSight Crime

arXiv (research papers) Haocheng Li SI

Parameter-Efficient Modality-Balanced Symmetric Fusion for Multimodal Remote Sensing Semantic Segmentation

Multimodal remote sensing semantic segmentation enhances scene interpretation by exploiting complementary physical cues from heterogeneous data. Although pretrained Vision Foundation Models (VFMs) provide strong general-purpose representations, adapting them to multimodal tasks often incurs substantial computational overhead and is prone to modality imbalance, where the contribution of auxiliary modalities is suppressed during optimization. To address these challenges, we…

Read at arXiv (research papers)

arXiv (research papers) Yuntong Zhang SI

VeriGrey: Greybox Agent Validation

Agentic AI has been a topic of great interest recently. A Large Language Model (LLM) agent involves one or more LLMs in the back-end. In the front end, it conducts autonomous decision-making by combining the LLM outputs with results obtained by invoking several external tools. The autonomous interactions with the external environment introduce critical security risks. In this paper, we present a grey-box approach to explore diverse behaviors and uncover security risks in LLM…

Read at arXiv (research papers)

arXiv (research papers) Saikat Maiti SI

Caging the Agents: A Zero Trust Security Architecture for Autonomous AI in Healthcare

Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research demonstrates that these agents exhibit critical vulnerabilities in realistic settings: unauthorized compliance with non-owner instructions, sensitive information disclosure, identity spoofing, cross-agent propagation of unsafe practices, and indirect…

Read at arXiv (research papers)

arXiv (research papers) Yi Ting Shen SI

MCP-38: A Comprehensive Threat Taxonomy for Model Context Protocol Systems (v1.0)

The Model Context Protocol (MCP) introduces a structurally distinct attack surface that existing threat frameworks, designed for traditional software systems or generic LLM deployments, do not adequately cover. This paper presents MCP-38, a protocol-specific threat taxonomy consisting of 38 threat categories (MCP-01 through MCP-38). The taxonomy was derived through a systematic four-phase methodology: protocol decomposition, multi-framework cross-mapping, real-world incident…

Read at arXiv (research papers)

arXiv (research papers) Gengxin Sun SI

CoMAI: A Collaborative Multi-Agent Framework for Robust and Equitable Interview Evaluation

Ensuring robust and fair interview assessment remains a key challenge in AI-driven evaluation. This paper presents CoMAI, a general-purpose multi-agent interview framework designed for diverse assessment scenarios. In contrast to monolithic single-agent systems based on large language models (LLMs), CoMAI employs a modular task-decomposition architecture coordinated through a centralized finite-state machine. The system comprises four agents specialized in question…

Read at arXiv (research papers)

Older stories