Results for “model”

arXiv (research papers) Chia-Pei Janet SI

IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection

Web-browsing AI agents are increasingly deployed in enterprise settings under strict whitelists of approved domains, yet adversaries can still influence them by embedding hidden instructions in the HTML pages those domains serve. Existing red-teaming resources fall short of this scenario: prompt-injection benchmarks ship pre-built adversarial pages that whitelisted agents cannot reach, and generic LLM scanners probe the model API rather than its retrieved content. We present…

Read at arXiv (research papers)

arXiv (research papers) Pranshav Gajjar SI

Agents Should Replace Narrow Predictive AI as the Orchestrator in 6G AI-RAN

This position paper argues that to achieve Level 5 autonomous 6G networks, the next generation of Artificial Intelligence in Radio Access Networks (AI-RAN) should transition away from fragmented, narrow predictive models and instead adopt multimodal Large Language Models (LLMs) as central reasoning agents. Current AI-RAN architectures rely on disjointed Deep Neural Networks (DNNs) and Deep Reinforcement Learning (DRL) agents that operate in isolated domains. These narrow…

Read at arXiv (research papers)

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) Joel Rorseth SI

RUBEN: Rule-Based Explanations for Retrieval-Augmented LLM Systems

This paper demonstrates RUBEN, an interactive tool for discovering minimal rules to explain the outputs of retrieval-augmented large language models (LLMs) in data-driven applications. We leverage novel pruning strategies to efficiently identify a minimal set of rules that subsume all others. We further demonstrate novel applications of these rules for LLM safety, specifically to test the resiliency of safety training and effectiveness of adversarial prompt injections.

Read at arXiv (research papers)

arXiv (research papers) Farzad Nourmohammadzadeh Motlagh SI

When Prompts Become Payloads: A Framework for Mitigating SQL Injection Attacks in Large Language Model-Driven Applications

Natural language interfaces to structured databases are becoming increasingly common, largely due to advances in large language models (LLMs) that enable users to query data using conversational input rather than formal query languages such as SQL. While this paradigm significantly improves usability and accessibility, it introduces new security risks, particularly the amplification of SQL injection vulnerabilities through the prompt-to-SQL translation process. Malicious…

Read at arXiv (research papers)

Journal articles (OpenAlex) Douglas de Castro · Humanities and Social Sciences Communications Geopolitics

Decolonizing climate resilience: unveiling the role of the Asian Infrastructure Investment Bank in the Global South

This article critically analyzes the function of the Asian Infrastructure Investment Bank (AIIB) in funding climate resilience in the Global South, contrasting it with the conventional development framework of the Bretton Woods Institutions (BWIs). Utilizing Third World Approaches to International Law (TWAIL), the study initially critiques the BWI model, contending that its transition towards green conditionalities represents a form of green structural adjustment. We argue…

Read at Journal articles (OpenAlex)

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) Strick Sheng SI

When Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agents

Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations influence tool use, state tracking, and action sequencing, yet their reliability and authority are often uncertain. Environmental grounding is therefore a systems-level problem involving context admission, evidence provenance, freshness checking, verification policy, action gating, and model reasoning. Existing agent…

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)

arXiv (research papers) Peiran Yun SI

LLM Advertisement based on Neuron Auctions

As Large Language Models (LLMs) transition into conversational agents, generative advertising emerges as a crucial monetization strategy. However, embedding advertisements within unstructured LLM outputs introduces a critical trilemma: balancing advertiser payoffs, platform revenue, and user experience. Existing methods, such as prompt injection or rigid position slots, disrupt semantic coherence and lack a parametric framework for independent control, rendering rigorous…

Read at arXiv (research papers)

Berkeley AI Research blog SI

Adaptive Parallel Reasoning: The Next Paradigm in Efficient Inference Scaling

Overview of adaptive parallel reasoning. What if a reasoning model could decide for itself when to decompose and parallelize independent subtasks, how many concurrent threads to spawn, and how to coordinate them based on the problem at hand? We provide a detailed analysis of recent progress in the field of parallel reasoning, especially Adaptive Parallel Reasoning. Disclosure: this post is part landscape survey, part perspective on adaptive parallel reasoning. One of the…

Read at Berkeley AI Research blog

arXiv (research papers) Saisai Hu SI

Research on Security Enhancement Methods for Adversarial Robust Large Language Model Intelligent Agents for Medical Decision-Making Tasks

Motivated by the challenge to improve the adversarial robustness, security, and trust of medical decision making intelligent agents, this study develops a full-link security enhancement framework, which describes "input risk perception - medical evidence constraint - knowledge consistency verification - decision confidence reweighting - security output control - adversarial feedback update." We propose ARSM-Agent and define a weighted joint objective consisting of decision…

Read at arXiv (research papers)

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)

arXiv (research papers) Krti Tallam SI

Authorization Propagation in Multi-Agent AI Systems: Identity Governance as Infrastructure

The security discussion around agentic AI focuses heavily on prompt injection. This paper argues that multi-agent systems also create a distinct authorization problem: maintaining authorization invariants as non-human principals retrieve data, delegate tasks, and synthesize results across changing boundaries. We call this problem authorization propagation. It is not reducible to prompt injection and is not fully addressed by classical access-control models such as RBAC…

Read at arXiv (research papers)

arXiv (research papers) Tejasvi C. Addagada SI

Semalith v1.4: A Calibrated 184M Safety Classifier Achieving State-of-the-Art Prompt-Injection Detection at 44x Fewer Parameters than Llama-Guard-3-8B

Deploying large language models in financial-services and agentic settings requires safety classifiers that simultaneously handle prompt injection, regulatory compliance, and general harm, a combination no existing open guardrail addresses in a single inference pass. Semalith v1.4 is a 184M-parameter DeBERTa-v3-base classifier performing simultaneous three-axis safety classification including prompt injection, general harm, and financial-services regulatory compliance, in a…

Read at arXiv (research papers)

arXiv (research papers) Wonbae Kim SI

SecureMCP: A Policy-Enforced LLM Data Access Framework for AIoT Systems via Model Context Protocol

The deployment of Large Language Model (LLM)-generated SQL queries in Artificial Intelligence of Things (AIoT) systems introduces critical security risks, as prompt injection attacks can manipulate LLMs into producing unauthorized queries that expose sensitive data or execute destructive operations. Existing NL2SQL research focuses on query accuracy, while MCP server implementations provide only SQL-level protections without fine-grained role-based access control. This paper…

Read at arXiv (research papers)

Journal articles (OpenAlex) Ana García Juanatey, Daniel Rajmil, Lucía Morales · Citizenship Social and Economics Education Geopolitics

Exploring political discourses in the EU Parliament on nuclear weapons: A simulation-based learning experience

This study examines how simulation based learning in higher education can help students enhance their understanding of global risks amid rising political tensions and uncertainty. It presents a model for a simulation exercise on political discourses regarding nuclear weapons within the EU Parliament. Despite the legal limitations that existing EU parliament nuclear politics entail, the simulations aimed to raise students’ awareness of the existential risks associated with…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jie Zhang SI

Laundering AI Authority with Adversarial Examples

Vision-language models (VLMs) are increasingly deployed as trusted authorities -- fact-checking images on social media, comparing products, and moderating content. Users implicitly trust that these systems perceive the same visual content as they do. We show that adversarial examples break this assumption, enabling \emph{AI authority laundering}: an attacker subtly perturbs an image so that the VLM produces confident and authoritative responses about the \emph{wrong} input…

Read at arXiv (research papers)

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)

arXiv (research papers) Shihao Weng SI

ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection

Large Language Model (LLM) agents are increasingly deployed as task-oriented software systems that use runtime context to decide and act on behalf of users. This delegation model makes prompt injection especially dangerous: an attacker can hide a context-aware instruction inside evidence the agent must use to decide what to do. Existing benchmarks and defenses largely miss this setting. Benchmarks often use context-insensitive tasks where the user prompt already specifies…

Read at arXiv (research papers)

Journal articles (OpenAlex) Dejan Živkov, Slavica Manić, Marina Gajić Glamočlija · Post-Communist Economies Geopolitics

Interdependence between stock and exchange rate markets in former communist economies

This study explores the short-term interconnection between stock and foreign exchange markets in five post-communist countries – Poland, Czechia, Hungary, Romania, and Kazakhstan, with a focus on assessing whether their relationship conforms more closely to the flow-oriented model or the portfolio-balance framework. Utilising a bivariate cDCC-GJR-GARCH approach, the analysis creates daily time varying correlations. To further investigate how market volatilities influence…

Read at Journal articles (OpenAlex)

arXiv (research papers) Javad Forough SI

When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI

Agentic AI systems, specifically LLM-driven agents that plan, invoke tools, maintain persistent memory, and delegate tasks to peer agents via protocols such as MCP and A2A, introduce a threat surface that differs materially from standalone model inference. Agents accumulate sensitive context, hold credentials, and operate across pipelines no single party fully controls, enabling prompt injection, context exfiltration, credential theft, and inter-agent message poisoning…

Read at arXiv (research papers)

arXiv (research papers) Mingshuo Liu SI

PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization

Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style personally identifiable information (PII) from public pages. Many prior defenses are deployed at the model, service, or agent layer rather than at the webpage itself, leaving ordinary page owners with limited deployable options. We present PIIGuard, a webpage-level defense that repurposes indirect prompt injection as a protective…

Read at arXiv (research papers)

Journal articles (OpenAlex) Claudia Beatriz Murray, Luis Vergara, José María Zingoni et al. · Housing Policy Debate Geopolitics

Translating Community Land Trusts: Institutional Barriers and Stakeholder Sense-Making in Argentina and Chile

This paper investigates the potential for community land trust (CLT) adoption in two Latin American contexts: Bahía Blanca, Argentina, and Temuco, Chile, where housing systems are shaped by neoliberal legacies, legal centralism, and cultural attachments to individual ownership. Drawing on two multi-stakeholder focus groups where participants were largely unfamiliar with the CLT model, the findings capture a crucial early stage of sense-making in which stakeholders interpret…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yuyang Gong SI

LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training

Large language models are increasingly embedded into systems that interact with user data, retrieved web content, and external tools, creating a new attack surface: prompt injection, where malicious commands embedded in untrusted data override the trusted command and induce unintended behavior. Existing defenses mainly rely on fine-tuning the model to preserve an explicit boundary between trusted commands and the untrusted data portion, so that the model learns to prioritize…

Read at arXiv (research papers)

arXiv (research papers) Pang Liu SI

VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models

Universal adversarial attacks on aligned multimodal large language models are increasingly reported with attack success rates in the 60-80% range, suggesting the visual modality is highly vulnerable to imperceptible perturbations as a prompt-injection channel. We argue that this number conflates two distinct events: (i) the model's output was perturbed (Influence), and (ii) the attacker's chosen target concept was actually emitted (Precise Injection). We compose two existing…

Read at arXiv (research papers)

arXiv (research papers) Murali Ediga SI

Trace: Unmasking AI Attack Agents Through Terminal Behavior Fingerprinting

AI-driven penetration testing agents are now capable of autonomously executing attacks within compromised networks. Identifying the model family that controls the active sessions of such agents provides valuable information towards understanding the intent of the attack and further developing attack countermeasures. In this paper, we introduce Trace, a novel multi-stage attribution and forensic framework for AI attack agents using terminal command sequences. Once Trace…

Read at arXiv (research papers)

arXiv (research papers) Sheldon Yu SI

A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents

Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also introduces a new attack surface: adversarial interactions can manipulate agent behavior through direct prompt injection, indirect content attacks, and multi-turn escalation strategies. Existing defense strategies focus on prompt-level filtering and rule-based guardrails, which are often…

Read at arXiv (research papers)

Journal articles (OpenAlex) Ирина Дмитриевна Тургель, Olga A. Chernova · Publications Geopolitics

Economic Journals of the BRICS Countries: Assessment of Academic Influence

The BRICS countries are playing an increasingly significant role in shaping a multipolar model of global science. This study aims to assess the academic influence of economic journals published in BRICS countries from the following key perspectives: academic standing, relevance, influence sustainability, internationalization, and external institutional recognition (lack of isolation). The methods of bibliometric, comparative, and cluster analysis were used. The study…

Read at Journal articles (OpenAlex)

Older stories