Results for “Mali”

arXiv (research papers) Di Lu SI

Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation

Self-hosted computer-use agents (SHCUAs), such as OpenClaw, combine natural-language interaction with direct access to host-side resources, including browsers, files, scripts, system commands, and external communication channels. While useful for automating real tasks, this capability also creates a host-level abuse surface: a legitimately deployed agent may be steered toward unsafe operations through malicious messages, indirect prompt injection, unsafe skills, or tampering…

Read at arXiv (research papers)

arXiv (research papers) Yuyang Gong SI

LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training

Large language models are increasingly embedded into systems that interact with user data, retrieved web content, and external tools, creating a new attack surface: prompt injection, where malicious commands embedded in untrusted data override the trusted command and induce unintended behavior. Existing defenses mainly rely on fine-tuning the model to preserve an explicit boundary between trusted commands and the untrusted data portion, so that the model learns to prioritize…

Read at arXiv (research papers)

arXiv (research papers) Weifei Jin SI

CleanBase: Detecting Malicious Documents in RAG Knowledge Databases

Retrieval-augmented generation (RAG) is vulnerable to prompt injection attacks, in which an adversary inserts malicious documents containing carefully crafted injected prompts into the knowledge database. When a user issues a question targeted by the attack, the RAG system may retrieve these malicious documents, whose injected prompts mislead it into generating attacker-specified answers, thereby compromising the integrity of the RAG system. In this work, we propose…

Read at arXiv (research papers)

The Guardian Mali Eromo Egbejule in Abidjan and Aisha Down

Curfews, conspiracy theories … and a cancelled concert: Mali’s capital tries to shrug off violence on its doorstep

Surprise coordinated attack by jihadists and separatists last weekend has rattled the regime and its security ally Russia “The Grand Ball of Bamako”, as organisers tagged the Saturday evening soiree at the Hotel de l’Amitié in the Malian capital, was meant to provide one of the west African country’s biggest headlines last weekend. Many sponsors including Orange Mali, the local subsidiary of the French telecoms company, had bankrolled the show, which organisers hoped would…

Read at The Guardian Mali

The Guardian Mali Eromo Egbejule West Africa correspondent and Pjotr Sauer Geopolitics

Russia claims its Africa Corps group prevented coup in Mali after rebels seize towns

Kremlin-controlled paramilitaries also alleged it inflicted ‘irreplaceable losses’ on insurgents avoiding civilian casualties Russia’s defence ministry has claimed its Africa Corps – the successor to the former Wagner mercenary group – prevented a coup in Mali over the weekend, avoiding mass civilian casualties and inflicting “irreplaceable losses” on rebel insurgents. It said in a statement that its troops in the desert town of Kidal near the Algerian border had fought for…

Read at The Guardian Mali

arXiv (research papers) Mengyao Du SI

SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents

Web agents have emerged as an effective paradigm for automating interactions with complex web environments, yet remain vulnerable to prompt injection attacks that embed malicious instructions into webpage content to induce unintended actions. This threat is further amplified for screenshot-based web agents, which operate on rendered visual webpages rather than structured textual representations, making predominant text-centric defenses ineffective. Although multimodal…

Read at arXiv (research papers)

The Guardian Mali Jason Burke International security correspondent

Taking power in Mali might be a stretch but insurgents can force hand of weakened regime

Coordinated attack by JNIM and the Tuareg minority inflicted significant casualties on government forces and Russian auxiliaries When al-Qaida-affiliated Islamic militants launched a series of attacks on military bases and raids into major towns in Mali and neighbouring Burkina Faso last summer, observers suggested they had been inspired by their counterparts in Syria, who had overthrown the regime of Bashar al-Assad and taken power six months or so earlier. Despite the…

Read at The Guardian Mali

The Guardian Mali Pjotr Sauer Geopolitics

Mali’s militant attacks expose limits of Putin’s power in Africa

Russian backing for the ruling junta has not stopped rebel fighters striking significant blows in recent days Mali in turmoil after insurgents seize towns and kill defence minister When Assimi Goïta, the leader of Mali’s military junta, sat down with the Russian president, Vladimir Putin, in the Kremlin last summer, it symbolised Moscow’s commanding sway over Mali at the expense of the west. As the two men spoke, roughly 3,500 miles to the south, about 2,000 Russian troops…

Read at The Guardian Mali

The Guardian Mali Eromo Egbejule in Abidjan Geopolitics

Mali in turmoil after insurgents seize towns and kill defence minister

Military intelligence chief reportedly also killed in sweeping attacks by jihadists and separatist rebels Mali’s militant attacks expose limits of Putin’s power in Africa Mali has been left reeling from sweeping attacks by jihadists and separatist rebels who seized several towns and military bases and killed the defence minister and military intelligence chief. The weekend assault on the west African state’s security architecture was coordinated by al-Qaida-affiliated…

Read at The Guardian Mali

The Guardian Mali Reuters Geopolitics

Mali defence minister killed amid flurry of insurgent attacks

Car bomb kills Sadio Camara at home during coordinated assaults by rebel groups including West African al-Qaida affiliate Mali’s defence minister was killed in an attack on his residence, the government said on Sunday, a high-profile fatality during coordinated assaults staged the previous day by insurgents including the West African affiliate of al-Qaida. A car laden with explosives driven by a suicide attacker drove into Sadio Camara’s residence in the town of Kati, the…

Read at The Guardian Mali

The Guardian Mali Associated Press

Militants and separatists launch coordinated attacks across Mali

Al-Qaida-linked group JNIM claims responsibility for strikes on airport in capital, Bamako and four other cities Islamic militants and separatists attacked several locations in Mali’s capital and other cities on Saturday in one of the largest coordinated attacks in the country in recent years. The al-Qaida-linked militant group JNIM claimed responsibility for the attacks on Bamako’s international airport and four other cities in central and northern Mali on its website…

Read at The Guardian Mali

arXiv (research papers) Wenjie Xiao SI

RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents

Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hide malicious instructions inside a dense, action-oriented skill that already functions as a legitimate instruction source. We study pre-execution skill-poison detection and show that successful skill poisoning induces a structured internal effect, attention hijacking, in which response-time attention shifts from trusted context…

Read at arXiv (research papers)

arXiv (research papers) Meng Chen SI

Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection

Modern Large audio-language models (LALMs) power intelligent voice interactions by tightly integrating audio and text. This integration, however, expands the attack surface beyond text and introduces vulnerabilities in the continuous, high-dimensional audio channel. While prior work studied audio jailbreaks, the security risks of malicious audio injection and downstream behavior manipulation remain underexamined. In this work, we reveal a previously overlooked threat…

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)

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)

arXiv (research papers) Guiyao Tie SI

BadSkill: Backdoor Attacks on Agent Skills via Model-in-Skill Poisoning

Agent ecosystems increasingly rely on installable skills to extend functionality, and some skills bundle learned model artifacts as part of their execution logic. This creates a supply-chain risk that is not captured by prompt injection or ordinary plugin misuse: a third-party skill may appear benign while concealing malicious behavior inside its bundled model. We present BadSkill, a backdoor attack formulation that targets this model-in-skill threat surface. In BadSkill, an…

Read at arXiv (research papers)

arXiv (research papers) Hengkai Ye SI

TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation

Large language models (LLMs) increasingly rely on external tools to perform time-sensitive tasks and real-world actions. While tool integration expands LLM capabilities, it also introduces a new prompt-injection attack surface: tool poisoning attacks (TPAs). Attackers manipulate tool descriptions by embedding malicious instructions (explicit TPAs) or misleading claims (implicit TPAs) to influence model behavior and tool selection. Existing defenses mainly detect anomalous…

Read at arXiv (research papers)

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)

arXiv (research papers) Wenhui Zhu SI

Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs

The rapid deployment of open-source frameworks has significantly advanced the development of modern multi-agent systems. However, expanded action spaces, including uncontrolled privilege exposure and hidden inter-system interactions, pose severe security challenges. Specifically, Indirect Prompt Injections (IPI), which conceal malicious instructions within third-party content, can trigger unauthorized actions such as data exfiltration during normal operations. While current…

Read at arXiv (research papers)

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)

arXiv (research papers) Yulin Shen SI

Invisible Threats from Model Context Protocol: Generating Stealthy Injection Payload via Tree-based Adaptive Search

Recent advances in the Model Context Protocol (MCP) have enabled large language models (LLMs) to invoke external tools with unprecedented ease. This creates a new class of powerful and tool augmented agents. Unfortunately, this capability also introduces an under explored attack surface, specifically the malicious manipulation of tool responses. Existing techniques for indirect prompt injection that target MCP suffer from high deployment costs, weak semantic coherence, or…

Read at arXiv (research papers)

arXiv (research papers) Abed K. Musaffar SI

Detection of adversarial intent in Human-AI teams using LLMs

Large language models (LLMs) are increasingly deployed in human-AI teams as support agents for complex tasks such as information retrieval, programming, and decision-making assistance. While these agents' autonomy and contextual knowledge enables them to be useful, it also exposes them to a broad range of attacks, including data poisoning, prompt injection, and even prompt engineering. Through these attack vectors, malicious actors can manipulate an LLM agent to provide…

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)

The Guardian Mali Ammar Kalia

‘Villages are burned, animals slaughtered. We have to let the world know what’s happening’: Tinariwen and Imarhan fight for Tuareg music

Tinariwen went from Saharan weddings to Grammy-winning acclaim – but violence has forced the desert blues masters into exile. Now, a new generation is stepping in to help Since their formation in 1979, Tuareg guitar band Tinariwen have been constantly moving. Based variously in Mali, Libya and Algeria, the Grammy-winning group have used their desert blues music as a lament for a wandering refugee status that continues to this day. Co-founder Abdallah Ag Alhousseyni says the…

Read at The Guardian Mali

arXiv (research papers) Yu He SI

AttriGuard: Defeating Indirect Prompt Injection in LLM Agents via Causal Attribution of Tool Invocations

LLM agents are highly vulnerable to Indirect Prompt Injection (IPI), where adversaries embed malicious directives in untrusted tool outputs to hijack execution. Most existing defenses treat IPI as an input-level semantic discrimination problem, which often fails to generalize to unseen payloads. We propose a new paradigm, action-level causal attribution, which secures agents by asking why a particular tool call is produced. The central goal is to distinguish tool calls…

Read at arXiv (research papers)

arXiv (research papers) Sumit Ranjan SI

VoiceSHIELD-Small: Real-Time Malicious Speech Detection and Transcription

Voice interfaces are quickly becoming a common way for people to interact with AI systems. This also brings new security risks, such as prompt injection, social engineering, and harmful voice commands. Traditional security methods rely on converting speech to text and then filtering that text, which introduces delays and can ignore important audio cues. This paper introduces VoiceSHIELD-Small, a lightweight model that works in real time. It can transcribe speech and detect…

Read at arXiv (research papers)

arXiv (research papers) Xiaoyi Pang SI

DualSentinel: A Lightweight Framework for Detecting Targeted Attacks in Black-box LLM via Dual Entropy Lull Pattern

Recent intelligent systems integrate powerful Large Language Models (LLMs) through APIs, but their trustworthiness may be critically undermined by targeted attacks like backdoor and prompt injection attacks, which secretly force LLMs to generate specific malicious sequences. Existing defensive approaches for such threats typically rely on high access rights, impose prohibitive costs, and hinder normal inference, rendering them impractical for real-world scenarios. To solve…

Read at arXiv (research papers)

arXiv (research papers) Qianlong Lan SI

Silent Egress: When Implicit Prompt Injection Makes LLM Agents Leak Without a Trace

Agentic large language model systems increasingly automate tasks by retrieving URLs and calling external tools. We show that this workflow gives rise to implicit prompt injection: adversarial instructions embedded in automatically generated URL previews, including titles, metadata, and snippets, can introduce a system-level risk that we refer to as silent egress. Using a fully local and reproducible testbed, we demonstrate that a malicious web page can induce an agent to…

Read at arXiv (research papers)

arXiv (research papers) Che Wang SI

ICON: Indirect Prompt Injection Defense for Agents based on Inference-Time Correction

Large Language Model (LLM) agents are susceptible to Indirect Prompt Injection (IPI) attacks, where malicious instructions in retrieved content hijack the agent's execution. Existing defenses typically rely on strict filtering or refusal mechanisms, which suffer from a critical limitation: over-refusal, prematurely terminating valid agentic workflows. We propose ICON, a probing-to-mitigation framework that neutralizes attacks while preserving task continuity. Our key insight…

Read at arXiv (research papers)

Journal articles (OpenAlex) Rowan Alcock · Journal of Law and Society Geopolitics

Polanyi on crisis: The United States, fascism and ecological break‐down

Abstract This article uses Karl Polanyi's understanding of the crisis inherent in liberal economics to analyse a contemporary crisis—Trump's global tariff agenda. It argues that Trump's tariff agenda conforms to Polanyi's interpretation of how the crisis of liberal economics can disintegrate into more malignant forces. However, this article argues the Trump tariff agenda is a response to a larger crisis of contemporary liberal economics—climate breakdown. The slowing of…

Read at Journal articles (OpenAlex)

Older stories