Results for “Again”

arXiv (research papers) Harsh Shah SI

LogJack: Indirect Prompt Injection Through Cloud Logs Against LLM Debugging Agents

LLM debugging agents that consume cloud logs and execute remediation commands are vulnerable to indirect prompt injection through log content. We present LogJack, a benchmark of 42 payloads across 5 cloud log categories, and evaluate 8 foundation models under 3 prompt conditions with 5 independent trials each (n = 160 per model per condition on 32 attack payloads). Under the active condition, verbatim command execution rates range from 0% (Claude Sonnet 4.6) to 86.2% (Llama…

Read at arXiv (research papers)

Journal articles (OpenAlex) Bama Andika Putra · F1000Research South China Sea

Non-compliance towards Elite Cues: The Persuasion Paths of Perceptions towards China and the US

This study aims to uncover why non-compliance with elite cues occurred between Duterte’s foreign policy outlooks towards the US and China and the Philippine public’s perceptions of the two great powers. Looking at published survey reports in 2020 and 2021, inconsistencies between elite perceptions and the Philippine public’s attitudes occurred with Duterte aligning with China and going against the US during his six-year presidential term (2016–2022) on one side of the…

Read at Journal articles (OpenAlex)

arXiv (research papers) Junyu Ren SI

DeepSeek Robustness Against Semantic-Character Dual-Space Mutated Prompt Injection

Prompt injection has emerged as a critical security threat to large language models (LLMs), yet existing studies predominantly focus on single-dimensional attack strategies, such as semantic rewriting or character-level obfuscation, which fail to capture the combined effects of multi-space perturbations in realistic scenarios. In addition, systematic black-box robustness evaluations of recent Chinese LLMs, such as DeepSeek, remain limited. To address these gaps, we propose…

Read at arXiv (research papers)

arXiv (research papers) Wei Zhao SI

ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection

Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by embedding malicious instructions within tool-returned content, which agents directly incorporate into their conversation history as trusted observations. To address these vulnerabilities, we introduce \textsc{ClawGuard}, a novel runtime security…

Read at arXiv (research papers)

Journal articles (OpenAlex) Anastasia Mgaloblishvili · Journal of European Public Policy Geopolitics

Countering autocratization in a contested liberal international order: comparing the role of EU conditionality in Georgia (2022–2024) and Slovakia (1994–1998)

This paper analyzes the conditions under which EU conditionality can counter autocratization through a comparative case study of Slovakia (1994–1998) and Georgia (2022–2024). In both cases, the EU employed negative conditionality against autocratizing candidate states ahead of pivotal elections. Given high public support for EU integration and vibrant civil societies, EU’s ‘sticks’ created favourable conditions for public mobilisation. Drawing on participant observation and…

Read at Journal articles (OpenAlex)

arXiv (research papers) Guangyu Gong SI

PlanGuard: Defending Agents against Indirect Prompt Injection via Planning-based Consistency Verification

Large Language Model (LLM) agents are increasingly integrated into critical systems, leveraging external tools to interact with the real world. However, this capability exposes them to Indirect Prompt Injection (IPI), where attackers embed malicious instructions into retrieved content to manipulate the agent into executing unauthorized or unintended actions. Existing defenses predominantly focus on the pre-processing stage, neglecting the monitoring of the model's actual…

Read at arXiv (research papers)

Journal articles (OpenAlex) Federica Valerio · Violence Against Women Geopolitics

Reframing Institutional Responsibility for Gender-Based Violence Against Women: Feminist Legal Theory, International Law and Due Diligence

Feminist legal theory exposes how laws and institutions have historically reproduced patriarchal power and gender-based violence. Within international law, the principle of due diligence has become a key framework for redefining state responsibility, requiring not only the punishment of individual perpetrators but also the prevention and redress of structural forms of harm. Through a feminist and intersectional lens, due diligence moves beyond formal compliance to demand…

Read at Journal articles (OpenAlex)

arXiv (research papers) Zhuowen Yuan SI

ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems

Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. However, as agents increasingly rely on third-party tools and MCP servers, a new class of supply-chain threats has emerged, where malicious behaviors are embedded in seemingly benign tools, silently hijacking agent execution, leaking sensitive data, or triggering unauthorized actions. Despite their growing impact, there is currently no comprehensive benchmark for…

Read at arXiv (research papers)

Journal articles (OpenAlex) Max Haiven · Distinktion Journal of Social Theory Geopolitics

The speculative imagination within, against and beyond Amazon: the Worker as Futurist project in an increasingly fascist context

Amazon, which might be said to emblematize the Silicon Valley ethos of mobilizing massive capital to ‘disrupt’ capitalist industries and everyday life, is today among the world’s largest employers, retailers and providers of cloud computing services. But the firm was in no small part built through science and speculative fiction, not only as a genre of entertainment it sells, but as a set of ideas, narratives, tropes and ideologies that have facilitated its internal and…

Read at Journal articles (OpenAlex)

arXiv (research papers) Jackson Wang SI

AttackEval: A Systematic Empirical Study of Prompt Injection Attack Effectiveness Against Large Language Models

Prompt injection has emerged as a critical vulnerability in large language model (LLM) deployments, yet existing research is heavily weighted toward defenses. The attack side -- specifically, which injection strategies are most effective and why -- remains insufficiently studied.We address this gap with AttackEval, a systematic empirical study of prompt injection attack effectiveness. We construct a taxonomy of ten attack categories organized into three parent groups…

Read at arXiv (research papers)

Journal articles (OpenAlex) Felipe Almeida, Beliza Borba de Almeida · Journal of Economic Issues Geopolitics

Fascism, Technofeudalism, or Market Socialism? An Institutional Perspective on the Possible Future of Capitalism

Capitalism once again stands at a crossroads. Contemporary neoliberalism has witnessed a resurgence of fascist values, raising the prospect that the future may resemble a troubling past. At the same time, technofeudalism has gained prominence as a potential successor to capitalism, describing a transformation into a rent-extractive regime in which technology corporations accumulate wealth through monopolistic predation. A further alternative form of economic organization in…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Saadia Farooq, Victoria Ann Newsom, Lara Martin Lengel · Online Media and Global Communication Geopolitics

Diasporic social media activism as discursive resistance: Afghan women contest the Taliban’s strategic narratives

Abstract Purpose This study examines how women in the Afghan diaspora deploy social media activism as discursive resistance against the Taliban’s strategic narratives following the 2021 resurgence of Taliban rule. It investigates how Afghan women within the diaspora and inside Afghanistan use social media visibility to contest discursive cleansing and erasure, reclaim suppressed voices, and reassert their identities within transnational public spheres…

Read at Journal articles (OpenAlex)

arXiv (research papers) Chong Xiang SI

Architecting Secure AI Agents: Perspectives on System-Level Defenses Against Indirect Prompt Injection Attacks

AI agents, predominantly powered by large language models (LLMs), are vulnerable to indirect prompt injection, in which malicious instructions embedded in untrusted data can trigger dangerous agent actions. This position paper discusses our vision for system-level defenses against indirect prompt injection attacks. We articulate three positions: (1) dynamic replanning and security policy updates are often necessary for dynamic tasks and realistic environments; (2) certain…

Read at arXiv (research papers)

InSight Crime Gavin Voss

From Airstrikes to Cooperation: Will the ‘New Phase’ of Ecuador’s Drug War Deliver?

From Airstrikes to Cooperation: Will the ‘New Phase’ of Ecuador’s Drug War Deliver? Ecuador's revamping of old security measures like curfews and mass arrests of suspected gang collaborators are now being complemented with airstrikes backed by the United States and operations against transatlantic drug trafficking organizations in tandem with European agencies. But will this new phase be any better than the old one?

Read at InSight Crime

arXiv (research papers) Meiwen Ding SI

Covert Visual Prompt Injection against Commercial Multimodal Large Language Models

Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks. Existing prompt injection methods predominantly rely on textual prompts or perceptible visual prompts that are observable by human users. In this work, we study imperceptible visual prompt injection against powerful closed-source MLLMs, where adversarial instructions are embedded in…

Read at arXiv (research papers)

Journal articles (OpenAlex) Amedeo Osti Guerrazzi · Small Wars and Insurgencies Geopolitics

Fascist anti partisans strategies in the Italian civil war, 1943–1945

Between 1943 and 1945, the armed forces of the Italian Social Republic (RSI), created by Mussolini in September 1943, were engaged in a fierce counterinsurgency war against partisan forces. Despite the efforts of the fascists, the RSI failed to create an efficient army capable of crushing the Resistance and managed to maintain control of part of its territory only with the help of the German armed forces. The essay analyses the structural, cultural and ideological…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Diego Leiva Van De Maele · International Affairs Geopolitics

Explaining the belated US response to China's advances in Latin America

Abstract China has become a major actor in Latin America. It has increased its influence within the region at an unprecedented pace without facing significant contestation from the United States during most of the first 20 years of the twenty-first century. The US response came during Donald Trump's first administration (2017–2021), when it adopted significant measures to counterbalance against China's regional advances. Which factors explain Washington's belated response?…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Federico Tarragoni · Sociology Lens Geopolitics

From Populism to Fascism? On Our Present‐Time Political Categories

ABSTRACT With the global rise of far‐right governments, two categories are available to describe this aspect of our current times: populism and fascism. This raises a twofold question: analytically, which is the most accurate to describe these authoritarian governments? Performatively, which is the most effective in encouraging citizens to fight against them? This paper assesses their respective advantages and disadvantages, emphasizing their conceptual and historical…

Read at Journal articles (OpenAlex)

arXiv (research papers) Surada Suwansathit SI

A Security Analysis of the OpenClaw AI Agent Framework

AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a systematic taxonomy of 470 advisories filed against OpenClaw, an open-source AI agent runtime, organized by architectural layer and trust-violation type. Vulnerabilities cluster along two orthogonal axes: (1) the system axis, reflecting the…

Read at arXiv (research papers)

The Guardian Belarus Agence France-Presse Geopolitics

North Korea and Belarus sign ‘friendship and cooperation’ treaty

Kim Jong-un welcomed Alexander Lukashenko with lavish ceremony, including artillery salute and goose-stepping soldiers before a large flag-waving crowd North Korea and Belarus’s strongmen leaders signed a “friendship and cooperation” treaty on Thursday, state media reported, after Kim Jong-un “warmly” welcomed president Alexander Lukashenko to Pyongyang for a maiden visit. Besides supporting Russia’s war against Ukraine – about 2,000 North Korean soldiers are thought to have…

Read at The Guardian Belarus

arXiv (research papers) Alexander Panfilov SI

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injection evaluations. We deploy frontier agents, such as Claude Code and Codex, in an autoresearch loop with access to a library of 30+ prior methods and an evaluation script with a fixed compute budget. We show this pipeline to be effective in jailbreaking OpenAI's GPT-OSS-Safeguard-20B and in prompt…

Read at arXiv (research papers)

arXiv (research papers) Qianlong Lan SI

The Cognitive Firewall:Securing Browser Based AI Agents Against Indirect Prompt Injection Via Hybrid Edge Cloud Defense

Deploying large language models (LLMs) as autonomous browser agents exposes a significant attack surface in the form of Indirect Prompt Injection (IPI). Cloud-based defenses can provide strong semantic analysis, but they introduce latency and raise privacy concerns. We present the Cognitive Firewall, a three-stage split-compute architecture that distributes security checks across the client and the cloud. The system consists of a local visual Sentinel, a cloud-based Deep…

Read at arXiv (research papers)

arXiv (research papers) Vincent Siu SI

A Framework for Formalizing LLM Agent Security

Security in LLM agents is inherently contextual. For example, the same action taken by an agent may represent legitimate behavior or a security violation depending on whose instruction led to the action, what objective is being pursued, and whether the action serves that objective. However, existing definitions of security attacks against LLM agents often fail to capture this contextual nature. As a result, defenses face a fundamental utility-security tradeoff: applying…

Read at arXiv (research papers)

arXiv (research papers) Shawn Li SI

The Autonomy Tax: Defense Training Breaks LLM Agents

Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks. Practitioners deploy defense-trained models to protect against prompt injection attacks that manipulate agent behavior through malicious observations or retrieved content. We reveal a fundamental \textbf{capability-alignment paradox}: defense training designed to improve safety systematically destroys…

Read at arXiv (research papers)

arXiv (research papers) Md Takrim Ul Alam SI

Prompt Control-Flow Integrity: A Priority-Aware Runtime Defense Against Prompt Injection in LLM Systems

Large language models (LLMs) deployed behind APIs and retrieval-augmented generation (RAG) stacks are vulnerable to prompt injection attacks that may override system policies, subvert intended behavior, and induce unsafe outputs. Existing defenses often treat prompts as flat strings and rely on ad hoc filtering or static jailbreak detection. This paper proposes Prompt Control-Flow Integrity (PCFI), a priority-aware runtime defense that models each request as a structured…

Read at arXiv (research papers)

Journal articles (OpenAlex) Ana Victoria Martner-Castillo, Antonio-José González-Jiménez · Discourse & Society Geopolitics

Anti-Latin American migrant hate speech on X: A comparative study of Spain and the United States

This study examines hate speech against Latin American migrants on social media through a comparative analysis of Spain and the United States. Using a qualitative content analysis of 2405 tweets posted on X (formerly Twitter) between January and April 2025, it explores discursive patterns, stereotypes, and ideological structures. Grounded in theories of otherness, symbolic power, and digital propaganda, the research applies open, axial, and selective coding to identify…

Read at Journal articles (OpenAlex)

arXiv (research papers) Zijian Ling SI

Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs

Speech-driven large language models (LLMs) are increasingly accessed through speech interfaces, introducing new security risks via open acoustic channels. We present Sirens' Whisper (SWhisper), the first practical framework for covert prompt-based attacks against speech-driven LLMs under realistic black-box conditions using commodity hardware. SWhisper enables robust, inaudible delivery of arbitrary target baseband audio-including long and structured prompts-on commodity…

Read at arXiv (research papers)

Journal articles (OpenAlex) Cristóbal Karle, Felipe Sánchez Barría, René Arnoldo Osorio Canales · Sociological Quarterly Geopolitics

When Protest Becomes Institutionalized: Evidence from the Chilean Student Movement Under Military Rule, 1982–1989

For decades, rival theories have argued about the role and effects of the institutionalization of social movements. In this article, we present a detailed case study of a unique experience of social movement institutionalization and organization building under an authoritarian regime: the institutional reconstruction of the Chilean University Student Movement (USM) from 1983 to 1985 and its aftermath, in the midst of an intense protest cycle against Augusto Pinochet’s…

Read at Journal articles (OpenAlex)

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)

arXiv (research papers) Darren Cheng SI

Agent Privilege Separation in OpenClaw: A Structural Defense Against Prompt Injection

Prompt injection remains one of the most practical attack vectors against LLM-integrated applications. We replicate the Microsoft LLMail-Inject benchmark (Greshake et al., 2024) against current generation models running inside OpenClaw, an open source multitool agent platform. Our proposed defense combines two mechanisms: agent isolation, implemented as a privilege separated two-agent pipeline with tool partitioning, and JSON formatting, which produces structured output that…

Read at arXiv (research papers)

Older stories