Results for “oPt”

Journal articles (OpenAlex) Geertjan Holtrop · Asian Journal of Philosophy Geopolitics

The problem of mutual defeat in Strong Phenomenal Conservatism

Abstract Strong Phenomenal Conservatism, as defended by Michael Huemer, says that having an appearance that p is a necessary and sufficient condition for having a justified belief that p in the absence of defeaters. I argue that the no-defeater condition is problematic in Strong Phenomenal Conservatism because it leads to the problem of mutual defeat due to conflicting appearances, a problem that becomes especially clear with optical illusions. I show that the problem of…

Read at Journal articles (OpenAlex)

arXiv (research papers) Igor Bogdanov SI

FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast

Can LLM agents improve decision-making through self-generated memory without gradient updates? We propose FORGE (Failure-Optimized Reflective Graduation and Evolution), a staged, population-based protocol that evolves prompt-injected natural-language memory for hierarchical ReAct agents. FORGE wraps a Reflexion-style inner loop, where a dedicated reflection agent (using the same underlying LLM, no distillation from a stronger model) converts failed trajectories into reusable…

Read at arXiv (research papers)

arXiv (research papers) Zhichao Liu SI

WebTrap: Stealthy Mid-Task Hijacking of Browser Agents During Navigation

Browser agents are increasingly deployed in long-horizon tasks, which require executing extended action chains to accomplish user goals. However, this prolonged execution process provides attackers with more opportunities to inject malicious instructions. Existing prompt injection attacks against browser agents expose two key gaps: (1) low effectiveness, as attacks optimized for toy baselines fail to achieve end-to-end goals in real-world scenarios with complex environments…

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)

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)

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

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

Journal articles (OpenAlex) Magdalena Souto, Marcello Picollo, Giovanni Bartolozzi et al. · Colorants Geopolitics

Sustainable Preservation of Medieval Greens Through Historical Reproduction and Spectroscopy

By examining historical recipes from the medieval treatise The Montpellier Liber Diversarum Arcium, the creation of bottle green and verdigris pigments involved various types of tempera, such as parchment glue and gum arabic. Malachite was also prepared. These references and paints were analysed using infrared spectroscopy and visible spectroscopy techniques, such as micro-Infrared Spectroscopy (microFTIR) and Fibre Optic Reflectance Spectroscopy, (FORS) over the 350–1000 nm…

Read at Journal articles (OpenAlex)

arXiv (research papers) Geert Trooskens XY.AI Labs, Palo Alto, CA SI

Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation

We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which workflows execute deterministically without further model invocation. This paradigm has antecedents in prior work on declarative pipeline optimization (DSPy) and hybrid neural-symbolic planning (LLM+P); our contribution is a systems-oriented study of its application to high-stakes enterprise workflows, with particular emphasis on…

Read at arXiv (research papers)

OnCuba News Milena Recio

What those who don’t want “reforms” in Cuba actually want

As I have stated on other occasions — and continue to maintain — the only option offered to the Cuban people cannot be the example of Numantia. La entrada What those who don’t want “reforms” in Cuba actually want se publicó primero en OnCubaNews English.

Read at OnCuba News

Journal articles (OpenAlex) Oliver P. Richmond, Roger Mac Ginty · Global Change Peace & Security Geopolitics

Peace and the debacles of Afghanistan and Iraq: Lessons for future peacemaking and peacebuilding scholarship

Critical knowledge production and the accumulated knowledge and practices around peace and intervention was largely ignored in relation to the Western interventions in Iraq and Afghanistan. Subsequent stabilisation exercises indicated a continuing tendency to adopt a Western epistemic lens and ignore local and regional contexts and perspectives. This was either ignored or co-opted by ‘global’ security concerns (seen through an American prism), and has laid the way for the…

Read at Journal articles (OpenAlex)

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) Chenlong Yin SI

PISmith: Reinforcement Learning-based Red Teaming for Prompt Injection Defenses

Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks remains insufficiently evaluated, potentially creating a false sense of security. In this work, we propose PISmith, a reinforcement learning (RL)-based red-teaming framework that systematically assesses existing prompt-injection defenses by training an attack LLM to optimize injected…

Read at arXiv (research papers)

Dialogue Earth (formerly Diálogo Chino) Rosilena Lindo Geopolitics

For Latin America, the Gulf conflict is making the case for clean energy

Escalating conflicts show that renewables are not just a climate option, they are a security strategy, writes Panama’s former energy secretary

Read at Dialogue Earth (formerly Diálogo Chino)

arXiv (research papers) Frank Li SI

OpenClaw PRISM: A Zero-Fork, Defense-in-Depth Runtime Security Layer for Tool-Augmented LLM Agents

Tool-augmented LLM agents introduce security risks that extend beyond user-input filtering, including indirect prompt injection through fetched content, unsafe tool execution, credential leakage, and tampering with local control files. We present OpenClaw PRISM, a zero-fork runtime security layer for OpenClaw-based agent gateways. PRISM combines an in-process plugin with optional sidecar services and distributes enforcement across ten lifecycle hooks spanning message…

Read at arXiv (research papers)

arXiv (research papers) Nanzi Yang SI

Compatibility at a Cost: Systematic Discovery and Exploitation of MCP Clause-Compliance Vulnerabilities

The Model Context Protocol (MCP) is a recently proposed interoperability standard that unifies how AI agents connect with external tools and data sources. By defining a set of common client-server message exchange clauses, MCP replaces fragmented integrations with a standardized, plug-and-play framework. However, to be compatible with diverse AI agents, the MCP specification relaxes many behavioral constraints into optional clauses, leading to misuse-prone SDK…

Read at arXiv (research papers)

Journal articles (OpenAlex) Stefano Bruzzo-Gallardo, Josefa Henríquez, Mesfin Geremew Genie · Health Policy and Technology Geopolitics

Jabs and lockdowns: Public preferences for vaccination programmes in Chile

• Chile had world’s highest COVID-19 vaccination rate • A Discrete Choice Experiment (DCE) was conducted to understand vaccine programme preferences • Results reveal the most preferred vaccine program characteristics • Analysis identified 81% preferred vaccine programmes, and 19% preferred to opt out Chile achieved the world’s highest COVID-19 vaccination rate by March 2021, reflecting a strong vaccination culture. Nevertheless, coverage rates alone do not fully capture…

Read at Journal articles (OpenAlex)

arXiv (research papers) Aradhye Agarwal SI

Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause irreversible harm. Existing alignment methods, largely optimized for static generation and task completion, break down in these settings due to sequential decision-making, adversarial tool feedback, and overconfident intermediate reasoning…

Read at arXiv (research papers)

arXiv (research papers) Qianxun Xu SI

SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls

Recent advances in text-to-video diffusion models have enabled high-fidelity and temporally coherent videos synthesis. However, current models are predominantly optimized for single-event generation. When handling multi-event prompts, without explicit temporal grounding, such models often produce blended or collapsed scenes that break the intended narrative. To address this limitation, we present SwitchCraft, a training-free framework for multi-event video generation. Our…

Read at arXiv (research papers)

Journal articles (OpenAlex) Mustafa Tevfik Kartal, Dilvin Taşkın, Marco Mele et al. · Scientific Reports Geopolitics

Marginal effect of clean energy, nuclear energy-related R&D investment, energy security risk, and policy uncertainty on the environment in the USA

Environmental problems have been attracting the interest of all relevant parties because of the increasing negative effects on humanity. At this point, further clean, especially nuclear, energy consumption (EC) is seen as a strategic option to combat environmental deterioration (ED). Because clean energy, nuclear energy-related R&D investments (NRD), energy security risk (ESR), as well as increasing economic policy uncertainty (EPU) and trade policy uncertainty (TPU) in…

Read at Journal articles (OpenAlex)

arXiv (research papers) Aashish Kolluri SI

Optimizing Agent Planning for Security and Autonomy

Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe actions by enforcing confidentiality and integrity policies, but currently appear costly: they reduce task completion rates and increase token usage compared to probabilistic defenses. We argue that existing evaluations miss a key benefit of system-level defenses: reduced reliance on human oversight…

Read at arXiv (research papers)

Journal of Democracy Geopolitics

Why Iran’s Mullahs Are Running Out of Options

Iran has been plagued by economic turmoil and popular unrest in recent years as international sanctions stiffened and citizens bucked against the regime’s grip on civil life. Source

Read at Journal of Democracy

arXiv (research papers) Xin Chen SI

Learning to Inject: Automated Prompt Injection via Reinforcement Learning

Prompt injection is a critical vulnerability in LLM agents, yet the strongest methods still rely on human red-teamers and hand-crafted prompts. Adapting automated jailbreak optimizers does not close this gap: jailbreaks shape models toward generic compliance, while prompt injection requires emitting specific tool calls with correct parameters. The success signal is binary, and randomly sampled suffixes almost never trigger it, so standard optimizers have no gradient to…

Read at arXiv (research papers)

Journal articles (OpenAlex) Shang-Su Wu, Ryo Hinata-Yamaguchi · Defense and Security Analysis Geopolitics

Restricted Deterrence by denial: Japan’s Military role in a Taiwan Contingency

China's increasingly assertive posture towards Taiwan in recent years has raised Japan's security concerns. Due to its proximity, Tokyo may play a critical role in preventing or shaping conflict in the Taiwan Strait, though it does not have many options due to its legal and political constraints, limited military capability, and unofficial relationship with Taipei. This paper examines Japan's potential security role in the case of a Taiwan Strait contingency. It discusses…

Read at Journal articles (OpenAlex)

arXiv (research papers) Ching-Yun Ko SI

vLLM Hook v1: A Plug-in for Programming Model Internals on vLLM

Modern artificial intelligence models are deployed on inference engines to optimize runtime efficiency and resource allocation, particularly for transformer-based large language models. The vLLM project is a major open-source library to support model serving and inference. However, the current implementation of vLLM limits programmability of the internal states of deployed models. This prevents the use of popular test-time model alignment and enhancement methods. For…

Read at arXiv (research papers)

OnCuba News OnCuba Staff

Germán Mesa and his players optimistic ahead of upcoming World Baseball Classic

The Cuban manager believes the team can advance to the semifinals again, regardless of the absence of players who play in Major League Baseball. La entrada Germán Mesa and his players optimistic ahead of upcoming World Baseball Classic se publicó primero en OnCubaNews English.

Read at OnCuba News

arXiv (research papers) Henry Chen SI

Proactive Hardening of LLM Defenses with HASTE

Prompt-based attack techniques are one of the primary challenges in securely deploying and protecting LLM-based AI systems. LLM inputs are an unbounded, unstructured space. Consequently, effectively defending against these attacks requires proactive hardening strategies capable of continuously generating adaptive attack vectors to optimize LLM defense at runtime. We present HASTE (Hard-negative Attack Sample Training Engine): a systematic framework that iteratively engineers…

Read at arXiv (research papers)

OnCuba News OnCuba Staff

Venezuela today: scenarios and urgent challenges for the Cuban economy

Is there room to negotiate with new oil suppliers? The Cuban government is probably evaluating options, but the problem lies in the scarcity of foreign currency. La entrada Venezuela today: scenarios and urgent challenges for the Cuban economy se publicó primero en OnCubaNews English.

Read at OnCuba News

arXiv (research papers) Masahiro Kaneko SI

Paraphrasing Adversarial Attack on LLM-as-a-Reviewer

The use of large language models (LLMs) in peer review systems has attracted growing attention, making it essential to examine their potential vulnerabilities. Prior attacks rely on prompt injection, which alters manuscript content and conflates injection susceptibility with evaluation robustness. We propose the Paraphrasing Adversarial Attack (PAA), a black-box optimization method that searches for paraphrased sequences yielding higher review scores while preserving…

Read at arXiv (research papers)

Berkeley AI Research blog SI

Information-Driven Design of Imaging Systems

An encoder (optical system) maps objects to noiseless images, which noise corrupts into measurements. Our information estimator uses only these noisy measurements and a noise model to quantify how well measurements distinguish objects. Many imaging systems produce measurements that humans never see or cannot interpret directly. Your smartphone processes raw sensor data through algorithms before producing the final photo. MRI scanners collect frequency-space measurements that…

Read at Berkeley AI Research blog

Older stories