Results for “model”

arXiv (research papers) Jairo Gudiño-Rosero SI

Large Language Models and Augmented Democracy

Artificial intelligence enables computational agents to represent political preferences and take part in collective decision-making. In this thesis, I investigate the opportunities and challenges of digital twins (DTs) based on Large Language Models (LLMs) as intermediaries in augmented democracy, focusing on individual preference representation, collective representation of political organizations, and the vulnerability of those representations to attackers. First, using…

Read at arXiv (research papers)

arXiv (research papers) Zixuan Wang SI

Self-Reflection Fine-Tuning: Enhancing Agent Security against Prompt Injection Attacks from Failure Experience

Large language model (LLM) agents are increasingly deployed in tool-augmented environments, but their reliance on external inputs makes them highly vulnerable to prompt injection attacks that can hijack task objectives. Existing safety alignment methods rely on static expert trajectories or preference optimization, limiting their ability to generalize to adaptive attack patterns. In this work, we propose Self-Reflection Fine-Tuning (SRFT), a training framework that enables…

Read at arXiv (research papers)

Hacker News lucknite SI

Shield: A 118M model for detecting prompt injections and jailbreaks

Article URL: https://huggingface.co/ZeroLeaks/shield-small Comments URL: https://news.ycombinator.com/item?id=49940088 Points: 2 # Comments: 0

Read at Hacker News

Journal articles (OpenAlex) مصطفی محمدی ده چشمه, Ali Cheshmehzangi, Sohrab Ghaedi · Urban Water Journal Geopolitics

The interaction analysis of social conflicts linked with water stress in Iranian cities

Water-related challenges have significant social repercussions within Iran’s urbanization system. Due to the complex and multi-dimensional nature of these issues, this research redefines the interrelationships between social conflicts and water stress in Iranian cities through structural analysis conducted using Mic-Mac model. To identify 24 potential conflicts and their interconnections, we conducted interviews with a group of 50 municipal and academic experts from…

Read at Journal articles (OpenAlex)

arXiv (research papers) Adam Faulkner SI

CorrectGuard: Eyes-Off Correctness Estimation for Black-Box Security Guardrails

AI services increasingly rely on black-box security guardrails, yet privacy-preserving model auditing regimes often cannot measure how well these systems perform in both a human eyes-off production setting, which disallows human inspection of user input, and a machine eyes-off setting, which disallows model inspection of such input. We introduce CorrectGuard, an eyes-off correctness estimation framework for both settings, which involves an independent model-based evaluator…

Read at arXiv (research papers)

arXiv (research papers) Bijeeta Pal SI

Persona Guardrail: A Production-Grade Defense Framework for Agentic Systems

Large language model-based agents are increasingly deployed to perform domain-specific tasks by interacting with enterprise knowledge, tools, and external services. Existing runtime guardrails primarily target prompt injection and other attack-specific behaviors under a black-box threat model, but provide limited guarantees that agents operate within their intended functionality. As a result, production agents remain vulnerable to malicious requests and out-of-domain queries…

Read at arXiv (research papers)

arXiv (research papers) Anubha Gupta SI

LS-AR: Future-Predictive Latent Steering in Autoregressive LLMs

Standard autoregressive (AR) models process high-level task instructions, state history, and transient tokens within a single shared sequence of tokens. Consequently, they lack the architectural mechanisms needed to isolate macro-objectives from context noise. To overcome this single-channel limitation, we introduce Latent-Steered Autoregressive (LS-AR), a dual-channel architecture that decouples continuous goal steering from discrete token decoding via FiLM conditioning. We…

Read at arXiv (research papers)

arXiv (research papers) Zheng Chen SI

SecJev: Bringing Security Expertise to System One Decision Models

Security workflows need models that turn complex observations and explicit policies into decisions. System One models introduced by Jev return typed predictions and probabilities; security specialization supplies the domain expertise behind those predictions. We introduce SecJev, to our knowledge the first family of Jev-style decision models specialized for security, spanning 0.8B to 9B parameters. Built on Kev's single-pass candidate scorer, SecJev learns Boolean, choice…

Read at arXiv (research papers)

arXiv (research papers) Simhadri Podala Narasimha SI

Containing the Autonomous Operator: A Defense-in-Depth Framework and Reference Architecture for Securing AI Agents on Kubernetes

Large language model (LLM) agents are moving from chat interfaces into infrastructure operations, where they read telemetry, call tools, generate and execute code, and change the state of production Kubernetes clusters. This collapses a boundary that conventional cloud-native security assumes: the boundary between data and control. Content that an agent merely reads (a log line, a ticket, a tool description) can redirect what it does. This paper argues that the model must…

Read at arXiv (research papers)

Journal articles (OpenAlex) Hamed Nozari, Zornitsa B. Yordanova · AgriEngineering

An Intelligent LLM–Fuzzy Decision Support and Digital Twin Framework for Adaptive Agricultural Robotics Systems

This study develops an integrated LLM–fuzzy decision-support and digital twin framework for adaptive agricultural robotics, combining semantic reasoning, fuzzy inference, multi-objective optimization, and feedback-driven state updating. Numerical sensor data, operational information, and textual field knowledge are transformed into validated decision rules and model-ready parameters, enabling coordinated decisions across economic, operational, crop-stress, and…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Maksym Razumei, Halyna RAZUMEI, Viktor Kovalov · World Customs Journal Geopolitics

Challenges and Opportunities of the Implementation of the Authorised Economic Operator Program in Ukraine

This article examines the implementation of the Authorised Economic Operator (AEO) program in Ukraine amidst ongoing military aggression by the Russian Federation. It introduces the concept of a crisis-driven AEO model to explain how trusted trader mechanisms shift from mere trade facilitation to core elements of national economic resilience during existential state emergencies. Aligning national legislation with the European Union (EU) Customs Union framework is critical…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Achmad Rifa'i · Social Sciences & Humanities Open Geopolitics

Trump's trade protectionism and the vulnerability of Indonesia's export-oriented MSMEs

This study investigates the impact of the United States' tariff policy during the Trump era of trade protectionism on MSME-intensive export sectors in Indonesia using the Global Trade Analysis Project (GTAP) model. The analysis focuses on three sectoral proxies for MSME-intensive export sectors: wearing apparel, leather products, and wood products. Three simulation scenarios are used: a 10% US global tariff, a 19% specific tariff on Indonesia, and an escalation of the…

Read at Journal articles (OpenAlex)

arXiv (research papers) Narek Maloyan SI

Evaluating and Improving the Robustness of Large Language Models to Input Sequence Variations

Large language models (LLMs) in production systems face prompt injections, trojans (backdoors), and manipulation of automatic quality metrics. This thesis develops models, methods, and algorithms for evaluating and improving LLM robustness to adversarial input sequence variations. We propose R_stab(f), a generative robustness metric based on the Jensen-Shannon divergence between per-step output distributions under small input perturbations. For localized attacks we prove…

Read at arXiv (research papers)

arXiv (research papers) Elad David SI

Prompted to Discriminate: Generalizing Malicious-Input Probes in the Wild

LLM agents increasingly rely on activation probes as runtime monitors for prompt injection, jailbreaks, and unsafe requests, reading the model's own hidden state to catch a harmful input before the agent acts on it. A cheap, increasingly common move, borrowed from LLM-as-judge prompting, is to append a short classification instruction after the user's turn and read the probe at that point, to sharpen it: the instruction asks the model to represent the incoming request as a…

Read at arXiv (research papers)

arXiv (research papers) Alessandro Pegoraro SI

The Innocent Courier: Covert Exfiltration Through Legitimate LLM Web Fetching

With the increasing capabilities of Large-Language-Models (LLMs) and LLM-based agents, users are increasingly using them to solve everyday problems, such as answering e-mails or providing programming support. Existing work has extensively investigated security and privacy risks, such as prompt injections and the disclosure of sensitive data to chatbot providers. While various solutions were developed to address these risks, including input structuring to prevent prompt…

Read at arXiv (research papers)

Journal articles (OpenAlex) B. J. Santhosh, C. Balarengadurai, Boddu Ravi Prasad · IAES International Journal of Artificial Intelligence

A feature-enhanced deep learning model for multi-class paddy ailment prediction in smart farming

Paddy is an essential staple food crop eaten by more than 50% of the world population, particularly in Asia, where countries like China and India account for over 50% of both production and consumption. However, paddy cultivation is frequently threatened by numerous ailments that badly impact crop production and quality. Normal ailment identification approaches are often manual, time-consuming, and error-prone. To address these challenges, deep learning (DL)-based approaches…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) S Bogdanov, K Harbar, V Chernobrovkin et al. · European Journal of Public Health Geopolitics

Implementing a multilayered school-based psychosocial support model in wartime Ukraine: SAFE SPACE

Abstract Background Since the full-scale invasion, schools in Ukraine have had to provide psychosocial support under conditions of insecurity, disruption, overload, and limited access to specialist care. SAFE SPACE was developed as a multilayered school-based model in which teachers used resilience-supporting skills in daily work with children, school psychologists delivered a structured 7-session group intervention, and children with more severe difficulties could be…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Maryna Dolzhenko, Наталя Анатоліївна Білоусова, T V Mahanova et al. · European Heart Journal Geopolitics

Value-based cardiovascular care in Ukraine: transitioning from generic monotherapy to branded fixed-dose combinations (FDCs) and pharmaceutical support

Abstract Background Coronary Artery Disease (CAD) remains a significant clinical and economic burden in Ukraine. Despite the "Affordable Medicines" reimbursement program, the current focus on generic monotherapy is often undermined by poor patient adherence, leading to suboptimal outcomes and high rates of Major Adverse Cardiovascular Events (MACE). Objectives To evaluate the pharmacoeconomic viability of transitioning from a "generic-only" model to a value-based model…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Sirinart Chomean, Noppmats Khemtonglang, Ekchol Mukda et al. · Scientific Reports Gadgets

Cloud-deployable deep learning for smartphone-based body fluid cytology: a multi-architecture evaluation of YOLO and RT-DETR models

Abstract Accurate cytological evaluation of body fluid specimens is essential for diagnosing inflammatory and malignant conditions, yet manual interpretation remains labor-intensive and subject to inter-observer variability. This study developed and deployed a smartphone-based deep learning framework for multi-class body fluid cell classification integrating object detection, ROI-based classification, and explainable artificial intelligence (XAI). Three hundred…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Tanishq Kekre, Sumit K. Mandal · IEEE Embedded Systems Letters

Energy-Efficient Checkpointing for IMC-Based AI Accelerators Using 3.5 D Packaging

In-memory computing (IMC) techniques provides an energy-efficient way to train artificial intelligence (AI) and machine learning (ML) models. Furthermore, 2.5-D integration made it possible to store the weights of a large AI model on the compute system itself. However, resistive random access memory (ReRAM)-based IMC devices may fail abruptly due to frequent memory writes during training, coupled with their low endurance. Since the training of an AI model is an iterative…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) F. Arbabifar, Asra Lak · Physics Education Geopolitics

The 5E model with history of science in exam-focused Iranian physics classrooms

Abstract This mixed-methods study examined the challenges and strategies for integrating the history of science (HOS) into the 5E instructional model within an exam-driven Iranian high school physics classroom. Data were collected through field observations, student worksheets, teacher reflections, and a Likert-scale questionnaire during a unit on electromagnetic induction in a Tehran girls’ school. Qualitative analysis revealed three core tensions: conflict between…

Read at Journal articles (OpenAlex)

arXiv (research papers) Birk Torpmann-Hagen SI

Memetic Trojans: Social Contagions as Carriers of Adversarial Payloads in Agent Networks

Autonomous large language model (LLM) agents increasingly interact in network environments where adversarial content can propagate between agents. Known attacks include agent worms, which spread through self-replicating prompt injections or configuration compromises. We introduce \emph{memetic trojans}, a distinct class of network-mediated attack that exploits agents' tendencies to retransmit and amplify content. Unlike agent worms, whose propagation is adversarially…

Read at arXiv (research papers)

arXiv (research papers) Jieke Shi SI

Aletheia: Permission-Minimality Testing for Coding-Agent Rules

Coding agents powered by Large Language Models (LLMs) read repository rules (e.g., AGENTS.md and Cursor rules) to learn project conventions and development procedures. An attacker can exploit the same files to mislead the agent into requesting excessive permissions or performing unrelated operations, such as accessing credentials or transferring data. We present Aletheia, a framework for permission-minimality testing of coding-agent rules. It tests whether the permissions…

Read at arXiv (research papers)

The Guardian Liberal Democrats Antonio Voce and Ashley Kirk Geopolitics

How could Great Britain look under proportional representation? See the results for your area

These visualisations from exclusive polling modelling show how the UK parliament could change under different voting systems New analysis produced exclusively for the Guardian reveals how different voting systems would return significantly different seat totals in the UK parliament, based on recent polling. While the current first past the post (FPTP) system could leave Labour short of a majority with 250 seats, the modelling shows how proportional systems would be likely to…

Read at The Guardian Liberal Democrats

arXiv (research papers) Yuelin Han SI

Measuring LLM Agent Defenses by Layer: GDA Measurement and an Envelope-Layer Attack-Defense Model

Agent interaction protocols such as ACP and A2A let a remote peer deliver a task the receiving agent treats as legitimate, opening a channel for indirect prompt injection. Evaluating and defending such agents is difficult because the attack success rate (ASR) cannot distinguish an LLM recognition failure from an agent-layer block, and so cannot indicate which layer to strengthen. We contribute three artifacts. (1) GDA Measurement, a red-team method that captures the raw…

Read at arXiv (research papers)

China-US Focus Sujit Kumar Datta Geopolitics

Xi’s Washington Visit and the Global Order

The summit showed that differences can be bridged on competitive issues such as AI governance, trade stability, climate change, public health and transnational crime. That that bridge can model ways of working together that can help solve other problems.

Read at China-US Focus

Journal articles (OpenAlex) Xi Chen, Julien Cumin, Fano Ramparany et al. · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies Gadgets

Multi-Resident Data Association in Smart Homes via MDP Modeling and Behavior Cloning

Ambient sensors offer a privacy-preserving solution for activity recognition in smart homes, yet they face a critical challenge in multi-resident environments known as Data Association, which aims to identify the resident triggering a specific anonymous sensor event. Existing approaches fundamentally fail to maintain global consistency by often yielding conflicting associations for silent residents. Additionally, these methods frequently suffer from severe trajectory…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Ahmad Mohammadpour, Nariman Mohammadi · Territory Politics Governance Geopolitics

Decolonising space: necro-ecological governance in Rojhelat (Iranian Kurdistan)

This article examines the racialised destruction of the Kurdish eco-world in Rojhelat (Iranian/Eastern Kurdistan) through the lens of necro-ecological governance, arguing that environmental devastation is a structural hallmark of colonial rule in a stateless territory. Moving beyond state-centred models of environmental racism and reformist environmental justice, it conceptualises water governance, mining extraction, landmines, wildfires and colonial tourism as…

Read at Journal articles (OpenAlex)

Older stories