Results for “model”

Journal articles (OpenAlex) Vladimir Miroljub Cvetković, Dalibor Milenković, Jasmina Bašić et al. · Safety Geopolitics

Predictive Model of Community Disaster Resilience Across Serbia: A BRIC–DROP Composite Index and Spatial Patterns

Community disaster resilience is increasingly guiding risk-reduction investments, but in many Southeast European settings, comparable subnational data remain scarce. This study assesses perceived community disaster resilience across Serbia by combining BRIC–DROP dimensions into a single index and analyzing differences across hazard types and sociodemographic factors. A cross-sectional household survey was conducted using multistage random sampling and the “next birthday”…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yanting Wang SI

FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption

Long-context large language models (LLMs)-for example, Gemini-3.1-Pro and Qwen-3.5-are widely used to empower many real-world applications, such as retrieval-augmented generation, autonomous agents, and AI assistants. However, security remains a major concern for their widespread deployment, with threats such as prompt injection and knowledge corruption. To quantify the security risks faced by LLMs under these threats, the research community has developed heuristic-based and…

Read at arXiv (research papers)

arXiv (research papers) Prashant Kulkarni SI

Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection

Multi-turn prompt injection follows a known attack path -- trust-building, pivoting, escalation but text-level defenses miss covert attacks where individual turns appear benign. We show this attack path leaves an activation-level signature in the model's residual stream: each phase shift moves the activation, producing a total path length far exceeding benign conversations. We call this adversarial restlessness. Five scalar trajectory features capturing this signal lift…

Read at arXiv (research papers)

arXiv (research papers) Soheil Khodayari SI

Indirect Prompt Injection in the Wild: An Empirical Study of Prevalence, Techniques, and Objectives

As LLMs are increasingly integrated into systems that browse, retrieve, summarize, and act on web content, webpages have become an untrusted input vector for downstream model behavior. This enables site owners, contributors, and adversaries to embed instructions directly in web resources, i.e., indirect prompt injections. While prior work demonstrates such attacks in controlled settings, their prevalence, deployment, and real-world impact remain unclear. We present one of…

Read at arXiv (research papers)

arXiv (research papers) Yuan Xin SI

SafeReview: Defending LLM-based Review Systems Against Adversarial Hidden Prompts

As Large Language Models (LLMs) are increasingly integrated into academic peer review, their vulnerability to adversarial hidden prompts, i.e., adversarial instructions embedded in submissions to manipulate outcomes, poses a critical threat to scholarly integrity. We propose SafeReview, a co-evolutionary adversarial training framework for defending LLM-based peer review systems against such attacks. SafeReview jointly trains a Generator model to create sophisticated attack…

Read at arXiv (research papers)

Journal articles (OpenAlex) Khadijeh Salimi · Systems Research and Behavioral Science Geopolitics

Contesting Women's Rights Across Regime Types: A System Dynamics Approach

ABSTRACT Many governments around the world enforce discriminatory norms that violate human rights. Interested actors can challenge and, potentially, change these norms via a process known as contestation . In this paper, using mixed‐methods, I developed a system dynamic simulator based on social identity theory and applied that simulator to contrasting regime structures, democratic and non‐democratic, to generate new theoretical predictions. While the basic model for both…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Paula Boniolo, Sebastián Lemos · Frontiers in Sociology Geopolitics

Social stratification factors in educational transitions: a comparative analysis of Argentina, Chile and Mexico

Background: Educational expansion in Latin America has not necessarily led to greater equality of opportunity. Methods: This study analyzes educational transitions in Argentina, Chile, and Mexico using nationally representative surveys and logistic regression models with average marginal effects. Results: Findings show that inequality persists but is reorganized across stages depending on institutional configurations. Conclusion: Educational systems reproduce inequality…

Read at Journal articles (OpenAlex)

arXiv (research papers) Tosin Adewumi SI

BatteryPass-12K: The First Dataset for the Novel Digital Battery Passport Conformance Task

We introduce a novel task of digital battery passport (DBP) conformance classification and introduce the first public benchmark for the task: BatteryPass-12K, created synthetically from real pilot samples. This is as the EU's battery regulation on DBPs comes into effect soon and there exists no public dataset. We evaluated 22 language models (LMs) in zero-shot inference, spanning small LMs (SLMs), mixture of experts (MoEs), and dense LLMs. We also conducted analysis…

Read at arXiv (research papers)

arXiv (research papers) Kemal Bicakci SI

Making AI-Assisted Grant Evaluation Auditable without Exposing the Model

Public agencies are beginning to consider large language models (LLMs) as decision-support tools for grant evaluation. This creates a practical governance problem: the model and scoring rubric should not be exposed in a way that allows applicants to optimize against them, yet the evaluation process must remain auditable, contestable, and accountable. We propose a TEE-based architecture that helps reconcile these requirements through remote attestation. The architecture…

Read at arXiv (research papers)

arXiv (research papers) Ravikumar Balakrishnan SI

One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations

Typographic prompt injection exploits vision language models' (VLMs) ability to read text rendered in images, posing a growing threat as VLMs power autonomous agents. Prior work typically focus on maximizing attack success rate (ASR) but does not explain \emph{why} certain renderings bypass safety alignment. We make two contributions. First, an empirical study across four VLMs including GPT-4o and Claude, twelve font sizes, and ten transformations reveals that multimodal…

Read at arXiv (research papers)

arXiv (research papers) Nay Myat Min SI

Layerwise Convergence Fingerprints for Runtime Misbehavior Detection in Large Language Models

Large language models deployed at runtime can misbehave in ways that clean-data validation cannot anticipate: training-time backdoors lie dormant until triggered, jailbreaks subvert safety alignment, and prompt injections override the deployer's instructions. Existing runtime defenses address these threats one at a time and often assume a clean reference model, trigger knowledge, or editable weights, assumptions that rarely hold for opaque third-party artifacts. We introduce…

Read at arXiv (research papers)

arXiv (research papers) Zonghao Ying SI

AgentVisor: Defending LLM Agents Against Prompt Injection via Semantic Virtualization

Large Language Model (LLM) agents are increasingly used to automate complex workflows, but integrating untrusted external data with privileged execution exposes them to severe security risks, particularly direct and indirect prompt injection. Existing defenses face significant challenges in balancing security with utility, often encountering a trade-off where rigorous protection leads to over-defense, or where subtle indirect injections bypass detection. Drawing inspiration…

Read at arXiv (research papers)

arXiv (research papers) Jiaqi Li SI

Poster: ClawdGo: Endogenous Security Awareness Training for Autonomous AI Agents

Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat judgement entirely untrained. We present ClawdGo, a framework for endogenous security awareness training: we teach the agent to recognise and reason about threats from the inside, at inference time, with no model modification. Four…

Read at arXiv (research papers)

arXiv (research papers) Priyal Deep SI

Evaluation of Prompt Injection Defenses in Large Language Models

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense configurations across more than 20,000 attacks. Every defense that relied on the model to protect itself eventually broke. The only defense that held was output filtering, which checks the model's responses via hardcoded rules in separate…

Read at arXiv (research papers)

arXiv (research papers) Jialiang Wang SI

When AI reviews science: Can we trust the referee?

The volume of scientific submissions continues to climb, outpacing the capacity of qualified human referees and stretching editorial timelines. At the same time, modern large language models (LLMs) offer impressive capabilities in summarization, fact checking, and literature triage, making the integration of AI into peer review increasingly attractive -- and, in practice, unavoidable. Yet early deployments and informal adoption have exposed acute failure modes. Recent…

Read at arXiv (research papers)

arXiv (research papers) Yuandao Cai SI

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents

Autonomous Large Language Model (LLM) agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorized tool execution. Securing these systems requires effective information flow tracking. Yet, traditional taint analysis that is designed for program memory states fundamentally…

Read at arXiv (research papers)

arXiv (research papers) Shuxu Chen SI

CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning

Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However, CoT reasoning can be unstable across runs on long, multi-step problems, leading to inconsistent answers for unchanged task. Most prior work focuses on improving the forward reasoning chain within a single pass, with less attention to iterative and contrastive correction. To address this gap, we propose CAP-CoT, a Cycle…

Read at arXiv (research papers)

Journal articles (OpenAlex) Van Kien Pham, Vipin Gupta, Linh Le Phuong Giao · International Journal of Sport Policy and Politics Geopolitics

From admiration to policy partnership: a seven-stage model of football diplomacy and soft power in Vietnam–South Korea relations

This study examines football diplomacy as a policy facilitating instrument and soft power resource in Vietnam – South Korea relations, rather than a deterministic source of influence. Moving beyond views of sport as symbolic or episodic engagement, it conceptualises football diplomacy as a sequential, negotiated, and institutionally embedded process linking cultural, economic, and governance dimensions of bilateral cooperation. Using a convergent mixed methods design, the…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Emre Gündoğdu, Burçin Çakır Gündoğdu · Bulletin of Science Technology & Society Geopolitics

Are Liberal Democracies Failing to Mitigate Climate Change?: A Case Study of OECD Countries

This study examines the relationship between liberal democracy and climate performance. In the econometric analysis conducted using the panel ARDL model, the long-term effects of liberal democracy, climate change performance, urban population, and per capita gross domestic product (GDP) on carbon emissions (CO 2 ) are analyzed based on OECD member countries. We find that an increase in the level of liberal democracy increases carbon emissions in the long term, while improved…

Read at Journal articles (OpenAlex)

arXiv (research papers) Hoang Nguyen SI

Anchor-and-Resume Concession Under Dynamic Pricing for LLM-Augmented Freight Negotiation

Freight brokerages negotiate thousands of carrier rates daily under dynamic pricing conditions where models frequently revise targets mid-conversation. Classical time-dependent concession frameworks use a fixed shape parameter $β$ that cannot adapt to these updates. Deriving $β$ from the live spread enables adaptation but introduces a new problem: a pricing shift can cause the formula to retract a previous offer, violating monotonicity. LLM-powered brokers offer flexibility…

Read at arXiv (research papers)

Latinoamérica21 Juliana Montani Geopolitics

The War in the Middle East: The Destruction of a Fiction

The conflict lays bare the exhaustion of a global model based on stability, cheap energy, and supply chains optimized for cost. O post The War in the Middle East: The Destruction of a Fiction apareceu primeiro em Latinoamérica 21.

Read at Latinoamérica21

arXiv (research papers) Sahil Rajesh Dhayalkar SI

Overcoming the Impedance Mismatch: A Theoretical Roadmap for Fusing Foundation Models and Knowledge Graphs

Modern artificial intelligence remains fundamentally divided between the continuous, probabilistic spaces of Foundation Models and the discrete, deterministic structures of Knowledge Graphs. While Retrieval-Augmented Generation (RAG) attempts to connect them by serializing graph data into text, we argue this lexical bridging is merely a superficial patch. In this paper, we formalize the underlying structural and geometric friction as the \textit{Impedance Mismatch}. By…

Read at arXiv (research papers)

arXiv (research papers) Robert Sorab Stanley SI

An AI Agent Execution Environment to Safeguard User Data

AI agents promise to serve as general-purpose personal assistants for their users, which requires them to have access to private user data (e.g., personal and financial information). This poses a serious risk to security and privacy: an AI model may hallucinate or make mistakes, and adversaries may attack it (e.g., via prompt injection) to exfiltrate user data. This paper presents GAAP (Guaranteed Accounting for Agent Privacy), an execution environment for AI agents that…

Read at arXiv (research papers)

arXiv (research papers) Jiamin Chang SI

If you're waiting for a sign... that might not be it! Mitigating Trust Boundary Confusion from Visual Injections on Vision-Language Agentic Systems

Recent advances in embodied Vision-Language Agentic Systems (VLAS), powered by large vision-language models (LVLMs), enable AI systems to perceive and reason over real-world scenes. Within this context, environmental signals such as traffic lights are essential in-band signals that can and should influence agent behavior. However, similar signals could also be crafted to operate as misleading visual injections, overriding user intent and posing security risks. This duality…

Read at arXiv (research papers)

arXiv (research papers) Yanzhen Lu SI

A Control Architecture for Training-Free Memory Use

Prompt-injected memory can improve reasoning without updating model weights, but it also creates a control problem: retrieved content helps only when it is applied in the right state. We study this problem in a strict training-free setting and formulate it as applicability control: when to trigger a memory-assisted second pass, when to trust it, and how to maintain the memory bank over time. Our method combines uncertainty-based routing, confidence-based selective…

Read at arXiv (research papers)

arXiv (research papers) Dongcheng Zhang SI

Owner-Harm: A Missing Threat Model for AI Agent Safety

Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own deployers. Real-world incidents illustrate the gap: Slack AI credential exfiltration (Aug 2024), Microsoft 365 Copilot calendar-injection leaks (Jan 2024), and a Meta agent unauthorized forum post exposing operational data (Mar 2026). We propose…

Read at arXiv (research papers)

Berkeley AI Research blog SI

Gradient-based Planning for World Models at Longer Horizons

GRASP is a new gradient-based planner for learned dynamics (a “world model”) that makes long-horizon planning practical by (1) lifting the trajectory into virtual states so optimization is parallel across time, (2) adding stochasticity directly to the state iterates for exploration, and (3) reshaping gradients so actions get clean signals while we avoid brittle “state-input” gradients through high-dimensional vision models. Large, learned world models are becoming…

Read at Berkeley AI Research blog

arXiv (research papers) Hailin Liu SI

SafeAgent: A Runtime Protection Architecture for Agentic Systems

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection. This paper presents SafeAgent, a runtime security architecture that treats agent safety as a stateful decision problem over evolving interaction trajectories. The proposed design separates execution governance from semantic risk reasoning…

Read at arXiv (research papers)

arXiv (research papers) İpek Abasıkeleş Turgut SI

Evaluating a Layered Prompt-Injection Defence for the Model Context Protocol: A Record-Level Audit of Decision Conventions, Corpus Provenance and Reproducibility

The Model Context Protocol (MCP) extends the prompt-injection attack surface of large language model applications to tool descriptions, parameter schemas and tool outputs. Defences for it report detection figures that are not comparable, because each is measured on its authors' own corpus under a decision convention that is rarely stated. This paper audits one such evaluation at the level of individual decision records. Its object is CASCADE, a fully local layered defence…

Read at arXiv (research papers)

arXiv (research papers) Jiachen Qian SI

Visual Inception: Compromising Long-term Planning in Agentic Recommenders via Multimodal Memory Poisoning

The evolution from static ranking models to Agentic Recommender Systems (Agentic RecSys) empowers AI agents to maintain long-term user profiles and autonomously plan service tasks. While this paradigm shift enhances personalization, it introduces a vulnerability: reliance on Long-term Memory (LTM). In this paper, we uncover a threat termed "Visual Inception." Unlike traditional adversarial attacks that seek immediate misclassification, Visual Inception injects triggers into…

Read at arXiv (research papers)

Older stories