Results for “models”

Journal articles (OpenAlex) Patrick Maluki, Rabecca Kavithe Ndeto · Frontiers in Political Science Geopolitics

Reframing US politics through African lenses: a cross-continental dialogue on electoral systems and political thought

Comparative democratic theory has long assumed that intellectual traffic flows from Western liberal models outward to other traditions. This article reverses the direction. It is, first and foremost, a work of comparative political theory: drawing on Ubuntu political philosophy, Pan-African constitutional scholarship, and the comparative electoral-systems literature, it examines four well-documented structural failures of the American electoral order—the Electoral College…

Read at Journal articles (OpenAlex)

arXiv (research papers) Seyedarmin Azizi SI

One Word Opens the Gate: The Option-Channel Attack on Typed Decision Models as Agent Guardrails

A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short written definition, generating no text. Recent work places these models in agent systems as guardrails: the component that reads a proposed tool call or incoming message and decides whether to allow it. We evaluate seven open-weight models in that role and report the two error directions separately: a fail-open error allows a prohibited action and is a…

Read at arXiv (research papers)

arXiv (research papers) Luman Zhao SI

LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense

Large language models (LLMs) perform remarkably well on complex tasks, yet remain highly vulnerable to prompt injection attacks, where malicious instructions embedded in external data can override user intent. Existing defenses remain limited by model fine-tuning requirements, vulnerability to adaptive attacks, or reliance on brittle handcrafted prompts. We argue that a fundamental source of this vulnerability is the lack of an explicit representation of trust provenance. To…

Read at arXiv (research papers)

Journal articles (OpenAlex) Delante Clark · Journal of International Crisis and Risk Communication Research Geopolitics

The End of Unmeasured Exploitation: How A.S.M., C.A.S., and S.I.A. Challenge Digital Attention Capitalism

Digital attention capitalism generates value through the capture and monetization of human attention, yet it has historically lacked standardized mechanisms for measuring attention-related harm. This paper argues that the Attention Safeguard Models (A.S.M.), Cognitive Attentional Standards (C.A.S.), and Sociological Impact Assessment (S.I.A.) collectively challenge this system by introducing an integrated framework for classifying, measuring, and evaluating digital attention…

Read at Journal articles (OpenAlex)

arXiv (research papers) William Hackett SI

BRANCH: Bypassing Multi-Scanner AI Guardrails

AI systems increasingly rely on Large Language Models (LLMs) as core reasoning engines, making them targets for prompt injection and jailbreaks. Guardrails monitor and validate model inputs and outputs, yet their isolated, task-focused detection leaves gaps in their classification making them susceptible to bypasses. In response, guardrail systems formed by multiple scanners have emerged that collaboratively detect different types of malicious instructions, whereby shared…

Read at arXiv (research papers)

arXiv (research papers) Yichi Zhang SI

Secure Speculative Decoding for Large Language Models

Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by first using a smaller model, referred to as the \emph{draft model}, to generate candidate tokens and then verifying them with the target model for acceptance or rejection. Prior studies primarily focused on the efficiency-utility trade-off of speculative decoding, e.g., lossy speculative decoding, leaving its security implications largely unexplored. In…

Read at arXiv (research papers)

arXiv (research papers) James Peters-Gill SI

Can CaMeLs Talk? Securing Multi-Agent Systems Against Indirect Prompt Injection Attacks

Indirect prompt injection attacks - malicious instructions embedded in content processed by large language models - remain a major obstacle to safely deploying tool-using agents. CaMeL [Debenedetti et al., 2025] mitigates this threat for an individual agent by separating trusted control flow from untrusted data and enforcing capability-based security policies at runtime. In this work, we investigate whether CaMeL's security guarantees compose in hierarchical multi-agent…

Read at arXiv (research papers)

Journal articles (OpenAlex) Imam Adi Nata, Nila Nurlina, Muhammad Rifqi Maarif et al. · Scientific Reports Gadgets

A zero-shot LLM framework for analyzing user preference on product attributes: a case study of smartwatch reviews

The rise of zero-shot learning through Large Language Models (LLMs) opens new opportunities for analyzing consumer feedback without relying on annotated data. This study proposes a zero-shot framework to uncover user preferences on product attributes, using 12,900 Amazon smartwatch reviews as a case study. The framework integrates semantic keyword extraction, LLM-based attribute classification, sentiment analysis, and Importance–Performance Analysis (IPA) to convert…

Read at Journal articles (OpenAlex)

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) 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) 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) 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) 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)

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)

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)

Journal articles (OpenAlex) Dr. Chiragkumar B. Rathod, Sunil Patel, Chirag Rasikbhai Patel et al. · Journal of Information and Optimization Sciences Startups

Strategic funding decisions and startup success : A multi-method empirical study of venture capital, angel investing, crowdfunding, and incubators in the Indian ecosystem

This study examines how venture capital, angel investment, crowdfunding, and incubators influence revenue growth, market expansion, product-market fit, and startup survival in India's rapidly evolving ecosystem.Using fixed-effects panel, logistic, and Cox regression models, and drawing on agency theory, resource orchestration, and selection-bias perspectives, funding choice is treated as a strategic moderator of venture performance.The study introduces the Funding…

Read at Journal articles (OpenAlex)

arXiv (research papers) Rui Wen SI

Where Do LLMs Decide to Break the Rules? Mechanistic Localization of Prompt Injection Compliance

When a prompt injection attack succeeds, a Large Language Model (LLM) abandons its assigned system role to comply with an adversarial instruction. While prior work has extensively quantified how often this occurs, we ask a more fundamental question: where inside the network does the model actually decide to break the rules? Using layer-by-layer causal activation patching across five models (4B to 32B parameters), we find a clear dissociation: attack information is linearly…

Read at arXiv (research papers)

arXiv (research papers) Minh Nhat Le SI

Self-Evolving Defense: Continual Security Policy Learning for LLM Agents

Large language models (LLMs) increasingly power agents that access sensitive information, use external tools, and modify software repositories. Although these capabilities offer substantial benefits, they also create security risks such as jailbreaks, prompt injection, and vulnerable code generation. Existing defenses often require retraining, fail to adapt to evolving attacks, or address only a single threat pattern. To address these limitations, we propose Self-Evolving…

Read at arXiv (research papers)

arXiv (research papers) Michael Lee SI

Divide and Inject: Can Agents Reconstruct an Indirect Prompt Injection from Fragments?

Agentic systems are now being widely used to orchestrate tools and reason over long contexts. However, the improving capabilities of the large language models powering these agents also create new attack surfaces for indirect prompt injection. In particular, an attacker may not need to place a complete malicious instruction in retrieved content if the agent can reconstruct the objective from incomplete fragments distributed across a long context. In this work, we introduce…

Read at arXiv (research papers)

Journal articles (OpenAlex) Deokmin Kim · Review of Radical Political Economics Geopolitics

Financialization of Nonfinancial Corporations and Structural Transformation Under Neoliberalism: The Cases of Japan and South Korea

This article examines the structural transformation of the Japanese and South Korean economies under neoliberal reform and financialization. Existing research has focused mainly on Western economies, leaving underexplored the trajectories of Japan and Korea, which differ from finance-led models such as the United States and United Kingdom. Drawing on a Marxist framework, the study estimates multiple profit rates, including after-tax rates incorporating financial relations…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jie Zhang SI

Render Before Reading: Visual Rendering as a Prompt Injection Defense

Large language models are vulnerable to prompt injection attacks, where third-party adversarial content can hijack the model's behavior. In this paper, we study the role played by the adversarial data's input modality, and identify a systematic asymmetry: multimodal LLMs are more likely to follow adversarial instruction when they appear as text than when the same instruction is delivered through a non-textual channel (e.g., as an image). We hypothesize that this modality gap…

Read at arXiv (research papers)

arXiv (research papers) Rohit Saxena SI

Nudgeability: Reasoning Models Follow Confidence Signals Without Tracking Their Own Competence

Reasoning language models that can call tools must decide during inference whether to answer unaided or delegate. Any self-reflection mechanism for this must answer three questions: where the reflective signal comes from (verbal reports, output distributions, hidden states, a separate predictor), how it is presented to the model (numerical prediction, confidence token, prompt injection), and whether it changes the model's subsequent action. We isolate the third question. At…

Read at arXiv (research papers)

arXiv (research papers) Chenlong Yin SI

Climbing the Hill: Prompt Injection Red-Teaming Against Frontier Models with Curriculum Reinforcement Learning

Prompt injection is a leading security risk for LLMs and LLM-based applications such as agents. State-of-the-art red-teaming methods for prompt injection leverage reinforcement learning (RL) to train an attacker LLM to generate effective injected prompts. However, when targeting frontier LLMs such as GPT-6-Luna, a major challenge is the cold-start problem: every attack attempt by the attacker LLM fails and thus receives zero reward, providing no signal for learning. In this…

Read at arXiv (research papers)

arXiv (research papers) Yixuan Liu SI

Evaluating System One Models for Agent Security Decisions: Reliability, Calibration, and Selective Automation

Agentic software connects language models to tools that modify files and interact with external services. Developers use model-based security checks to screen external content and user requests before agents act. System One models answer developer-defined questions with probabilities over predefined answers such as safe or unsafe, but classification accuracy alone does not establish whether these probabilities support reliable automation. We evaluate Jev, Laya, Decider, and…

Read at arXiv (research papers)

Journal articles (OpenAlex) Jesús Alexander Pinillos Villamizar, Hugo A. Macías, Luis Fernando Castrillón Quintana et al. · Journal of risk and financial management Geopolitics

Debt Tax Shields and Capital Structure: Panel Evidence from Non-Financial Listed Firms in Chile, Colombia, Mexico, and Peru, 2013–2023

This study examines the association between the debt tax shield (DTS) and corporate leverage in 61 listed non-financial firms from Chile, Colombia, Mexico, and Peru during 2013–2023, using a perfectly balanced panel of 671 firm-year observations obtained from Bloomberg. The DTS is measured as interest expense multiplied by the effective income tax rate and scaled by total assets. Fixed-effects and random-effects panel models are estimated and complemented by a correlated…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jianyi Hu SI

JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models

Typed decision models (TDMs), such as Jev, answer a question about an input with a probability, an option, or an ordinal level. Web services execute these decisions automatically above a confidence threshold. An attacker who writes part of the input can change a decision that the service then executes. Current adversarial benchmarks cannot measure this risk, because they judge generated text. A TDM writes no text, and its wrong decisions have a valid format. We present…

Read at arXiv (research papers)

arXiv (research papers) Srikumar Subramanian SI

Crypto-bound identity-verified capability tokens for coordinating distributed AI agents: A proposal

The prospect of fully autonomous transactional agents did not appear on the horizon until the advent of high capability language models. With such models, the operational benefits of adaptive task orchestration and independent (but constrained) decision making are tantalizing for enterprises and individuals alike. However, each such agent carries with it a serious attack surface in the form of prompt injection which can compromise any soft "guard rails" that may have been…

Read at arXiv (research papers)

Older stories