Results for “Mali”

arXiv (research papers) Ahmad Hashmi SI

Prompt Injection Detection for Email Agents Through Attack Chain Modeling

Large language model email assistants are particularly vulnerable to indirect prompt injection because untrusted email content can be retrieved into the model context and influence subsequent tool use. Existing prompt injection detectors mainly formulate this problem as binary malicious text classification, which overlooks the important factor that harmful agent behavior often arises through a sequence of stages. We propose a detection framework that models this attack chain…

Read at arXiv (research papers)

arXiv (research papers) Tiantong Wu SI

Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions

Most studies of prompt injection focus on generative agents, leaving their effects on models with schema-defined outputs unclear. We examine these effects in Jev, a non-generative decision model, using 510 reconstructed InjecAgent cases. Malicious content shifts action probabilities but rarely causes Jev to select the attacker's target. Override markers reduce this influence, while claims of contextual relatedness have small effects. Adaptive attacks using score feedback…

Read at arXiv (research papers)

South Asia @ LSE blog Sarkar,N Geopolitics

Tech-Facilitated Gender-Based Violence in Pakistan

While access to internet and social media platforms can be empowering, it brings along new forms of aggression and violence. Fatima Hayat Malik discusses how women and other marginalised groups in Pakistan have become victims of tech-facilitated violence, and how it can be addressed. * Over the last few years, digital technologies have completely transformed … Continued The post Tech-Facilitated Gender-Based Violence in Pakistan first appeared on South Asia @ LSE.

Read at South Asia @ LSE blog

arXiv (research papers) Alex Remedios SI

Red-Teaming Auto Mode: Improving Blocking Classifiers Against Malign Coding Agents

To keep coding agents from going off the rails, production systems now review each proposed action with a blocking monitor that can reject it before it runs (Auto Mode in Claude Code, Guardian in OpenAI's Codex). Prior evaluations of such monitors largely measure robustness to accidental harm or prompt injections from untrusted sources looking to hijack the agent. Less understood is how they hold up when the agent they monitor is persistently misaligned. To understand this…

Read at arXiv (research papers)

arXiv (research papers) Anna Gazani SI

Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation

The integration of Large Language Models (LLMs) into Security Operations Centers (SOCs) streamlines threat intelligence but introduces critical vulnerabilities, notably indirect prompt injection via log poisoning. Adversaries exploit this vector to execute multistep ``promptware'' kill chains by embedding malicious payloads within system logs to hijack the LLM's operational logic. Securing this pipeline presents a dichotomy: deterministic defenses are computationally…

Read at arXiv (research papers)

The Guardian Sudan

From the archive: Sudan’s outsider: how a paramilitary leader fell out with the army and plunged the country into war – podcast

We are raiding the Guardian long read archives to bring you some classic pieces from years past, with new introductions from the authors. This week, from 2023: The civilians of Sudan have been trying to throw off military rule for decades, but now find themselves caught in the middle of a deadly power struggle between former allies turned bitter opponents Written and read by Nesrine Malik Read the text version here Support the Guardian today: theguardian.com/longreadpod

Read at The Guardian Sudan

Journal articles (OpenAlex) Qingsong Zou, Zhiyao Xu, Jingyu Xiao et al. · IEEE Transactions on Mobile Computing Gadgets

HomeGuardian: Detecting Behavioral Anomalies Through Implicit Profiling in Smart Home Systems

Smart homes, enabled by the Internet of Things (IoT), offer substantial convenience but also introduce security challenges. These often stem from anomalous behaviors, including improper user interactions and malicious attacks. Although various behavior-modeling methods have been proposed, userdevice interactions are often unobservable in practice due to encrypted traffic and limited vendor access, while anomaly detection models suffer severe degradation during cold start…

Read at Journal articles (OpenAlex)

arXiv (research papers) Shiqian Zhao SI

ECLIPSE: Self-Evolving Stealthy Prompt Injection Attack against Long-Horizon Agentic Systems

Recently, large language model (LLM) agents, such as Codex, Claude Code, and OpenClaw, have become capable of planning and executing long-horizon tasks through repeated tool calls. This capability also creates new opportunities for prompt injection. Existing attacks either place the malicious objective in one explicit instruction, making it easy to detect, or distribute the intent across multiple execution stages, making successful completion unreliable. In this work, we…

Read at arXiv (research papers)

The Guardian Sudan Nesrine Malik

The Nepal floods seem a world away – but make no mistake, climate breakdown will affect us all | Nesrine Malik

Richer countries might have more resources to deal with catastrophe, but this problem grips the entire planet, however much leaders may want to deny it Climate breakdown is happening on one Earth, but two different worlds. In one, its impacts increasingly encroach on everyday life; longer periods of discomfort and shorter periods of sharp pain. Endless, hotter summers, and within them sudden wildfires, evacuations, homes burned to cinders in a matter of hours. In another…

Read at The Guardian Sudan

arXiv (research papers) Zhenhua Zou SI

AgentKernel: The Trust-Native Agentic Operating System

Modern AI agents routinely cross trust boundaries: they ingest untrusted content, combine it with privileged instructions, persist intermediate beliefs in long-term memory, and invoke privileged tools. This creates an attack surface in which malicious payloads can enter through model inputs and cause harmful tool actions. Yet current governance stacks remain application-level middleware that share a process trust boundary with the agents they monitor. We argue that agents…

Read at arXiv (research papers)

arXiv (research papers) Zi Liang SI

CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?

Prompt injection attacks on Large Language Model (LLM) agents seek to introduce malicious instructions or content into external text sources retrieved by agents, forcing the underlying LLMs to execute harmful actions outside their benign scope. While current defenses effectively counter known injection attacks, deploying them in LLM agent environments remains challenging due to attack variants and emerging threats. Moreover, existing solutions typically suffer from an…

Read at arXiv (research papers)

arXiv (research papers) Xinhang Ma SI

ROPE: Routed Origin Policy Enforcement against Indirect Prompt Injection

Indirect prompt injection (IPI) plants instructions in the content a tool-using LLM agent reads, steering the agent into harmful tool calls. The strongest defenses are system-level, leveraging techniques such as task-conditional tool screening to prevent execution of malicious tools, and information-flow control to avoid tool execution with untrusted parameters. However, as agents grow more capable, users delegate more to automation. Consequently, tool execution sequences…

Read at arXiv (research papers)

arXiv (research papers) Yichao Gao SI

What Guides the Agent? Adjudicating Unauthorized Behavior via Localizing Behavior-Guiding Instructions

LLM agents integrated with external resources gain complex task capabilities, yet the unified natural-language context channel makes them vulnerable to injection attacks: untrusted external data may be dynamically parsed as behavior-guiding instructions during LLM inference, thereby subverting the agent's decision. Existing defenses focus on static detection or isolation of malicious content at the input/output level, remains insufficient for detecting such dynamic…

Read at arXiv (research papers)

arXiv (research papers) Jiahao Chen SI

Beyond Over-Refusal: Defending Indirect Prompt Injection via Latent Instruction Manifolds

Large Language Models (LLMs) have been integrated into complex ecosystems (e.g., Code Agents), while Indirect Prompt Injection (IPI) attacks have emerged as critical barriers to their safe deployment. Attackers exploit LLMs' indistinguishability between "instructions" and "data" to manipulate LLMs via maliciously injected instructions. Existing defenses, however, face an intractable safety-utility trade-off: most guardrails either incur high latency or suffer from severe…

Read at arXiv (research papers)

arXiv (research papers) Minjae Seo SI

MEMORY Wins All: Indirect Bias Injection Attacks via Social Media Content

Personal AI agents consume external content such as web pages and SNS feeds, and retain selected information in persistent memory. As a result, external content has become a new attack vector for memory poisoning, which steers an agent's later actions toward an adversary's bias. However, most existing attacks embed a malicious instruction in external content to make the agent retain the poisoned information, and prompt-injection filters can detect such content. We observe…

Read at arXiv (research papers)

GNET (Global Network on Extremism and Technology) Nathan Heath Geopolitics

Closing the Gap: Consolidating Terrorist Threat Intelligence in Frontier AI Governance

Government and industry leaders alike increasingly employ frameworks to assess and mitigate notable AI risks. These frameworks heavily index on categories of “catastrophic” risk, which the Center for AI Safety defines as “ways in which powerful AIs could bring about catastrophic events with devastating consequences for vast numbers of people.” For example, AI labs focus on risks from malicious use

Read at GNET (Global Network on Extremism and Technology)

arXiv (research papers) Alexandre G. R. Day SI

Workspace Topology as an Attack Vector in Agentic Coding Assistants

Agentic coding assistants are finding widespread use, not just in new code development but in quickly ingesting and leveraging third-party code. This opens up a risk of malicious code being ingested as these coding tools operate with broad filesystem access inside developer workspaces. In this paper, we extensively study the impact of different dimensions of a novel attack surface we term workspace topology -- defined via directory depth, codebase modularity, in-file…

Read at arXiv (research papers)

arXiv (research papers) Sihan Hou SI

Toward Metacognitive One-Shot Indirect Prompt Injection: Strategy Abstraction Via Outcome-Conditioned Reflection

Tool-using large language model (LLM) agents are vulnerable to indirect prompt injection (IPI), in which malicious instructions embedded in external observations manipulate subsequent agent decisions and actions. Most existing adaptive attacks rely on repeatedly querying and refining against the target agent, whereas realistic attackers may have only a single opportunity to interact with an unknown target agent. We propose SAVOR (Strategy Abstraction Via Outcome-Conditioned…

Read at arXiv (research papers)

arXiv (research papers) Xinze Chen SI

SkillsMetric: Mapping the Detection Boundary of Static Analysis for Malicious Agent Skills

Agent Skills---structured packages of instructions and scripts that augment LLM-based agents---are rapidly proliferating, yet their security properties remain under-explored. We present \textsc{SkillsMetric}, a five-stage static analysis framework that scores skill packages along pattern density, statistical anomaly, dataflow taint, import anomaly, and capability mismatch dimensions. We construct an adversarial evaluation dataset of 2{,}266 skills spanning 16~attack types…

Read at arXiv (research papers)

arXiv (research papers) Laiqiao Qin SI

BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes

Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or external data. Existing detection methods only detect the presence of injection and refuse to respond upon detection, overlooking the fact that for many modern aligned models, well-crafted instructions can resist most injection attacks. This means that the injection robustness varies significantly…

Read at arXiv (research papers)

Journal articles (OpenAlex) Collins Uchenna Chimeleze, Norziana Jamil, Zuhaira Muhammad Zain et al. · Scientific Reports Gadgets

Intelligent malware detection on Android smartphones via a hybrid approach using gradient boosting and convolutional neural network

Malware is malicious software that infiltrates systems without user consent. Effective detection involves identifying such software and distinguishing it from benign programs. While machine learning has shown promise in malware detection, many existing techniques demand extensive feature engineering and representation, leading to higher computation times and error rates. To address these limitations, we propose CNN-GBM, a hybrid model combining Convolutional neural networks…

Read at Journal articles (OpenAlex)

arXiv (research papers) Buzhao Liu SI

Robust Context-Aware Detection of Malicious Instructions in Text

The remarkable instruction-following ability of modern LLMs has enabled their practical use in orchestrating workflows of tool-using agents. This, however, also exposes such agents to attacks which embed malicious instructions in text, such as indirect prompt injection (IPI). One class of approaches to defend against such attacks aims to detect malicious sentences within otherwise benign text. While a number of approaches for this have been proposed, all tend to be brittle…

Read at arXiv (research papers)

arXiv (research papers) Longtao Guo SI

LoginTrap: Uncovering Task-Agnostic Phishing-Style Indirect Prompt Injection Attacks against LLM-based Web Agents

LLM-based web agents automate user tasks by observing webpages and executing browser actions on behalf of users. As these agents operate on real web services, login becomes a sensitive authentication boundary because it involves credentials and sensitive information. Existing work shows that malicious webpage content can manipulate web agent actions, but it has not fully examined whether such content can induce login and cause end-to-end private data leakage. We study this…

Read at arXiv (research papers)

arXiv (research papers) Jianshuo Dong SI

Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States

Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.g., malicious side-tasks hidden in external tool results. While many efforts have sought to address this threat, little is known about the internals of agentic LLMs when they are exposed to IPI attacks. For simplicity, we refer to this condition as IPI exposure. In this paper, we study IPI exposure from three perspectives. (1) Probing: Across eight models, including the 753B-parameter GLM-5.2 and the…

Read at arXiv (research papers)

Journal articles (OpenAlex) Yuxin Hu, Youli Jiang, Jinxiu Jiang · Asian Social Science Geopolitics

Multilingual Practices of Vietnamese Wives at a Chinese Border Town

Against the backdrop of cross-border regional integration between China and Southeast Asian neighbors, growing numbers of Vietnamese women migrate across the border to marry local Chinese men in pursuit of improved livelihoods, yet pervasive linguistic barriers severely restrict their access to local social resources. Focusing on nine Vietnamese cross-border migrant wives in Malipo, Yunnan Province, this study explores their Mandarin communication difficulties and the…

Read at Journal articles (OpenAlex)

arXiv (research papers) Haowen Dai SI

SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems

Multi-agent systems improve capability through task decomposition and role specialization, but these same mechanisms introduce an important safety blind spot: a harmful objective can be fragmented into locally plausible subtasks, allowing malicious intent to evade detection by any single agent. This is a growing social-impact challenge: systems handling sensitive information or consequential tools can turn routine delegation into unauthorized disclosure or unsafe action. We…

Read at arXiv (research papers)

arXiv (research papers) Max Landauer SI

Just Testing, Move Along: Evasion of LLM-based System Log Interpretation by Prompt Injection

Large Language Models (LLMs) are increasingly integrated into Security Operations Center (SOC) workflows, where they support analysts in tasks such as the interpretation of system logs. However, the ability of LLMs to directly process untrusted textual input also introduces new attack surfaces. In particular, attackers can inject contextual information or explicit instructions into log entries in order to influence how malicious activity is interpreted by the model. Despite…

Read at arXiv (research papers)

arXiv (research papers) Vincent Siu SI

Agent Security Needs Redefinition through a Holistic Framework

Agent security is widely treated as a question about action content. Defenses ask whether an instruction looks malicious. Benchmarks ask whether an agent performs a harmful sounding action. \textbf{We argue that agent security is fundamentally a contextual problem, and that the current content based framing systematically misdefines it.} A command to ``delete user data'' might be a routine administrative request or a prompt injection attacking production systems, and the…

Read at arXiv (research papers)

Journal articles (OpenAlex) Anna Osypchuk, Maksym Yakovlye, Anton Suslov et al. · European Foreign Affairs Review Geopolitics

Contesting Influence and Geopolitics of Enlargement: Perceptions from the Western Balkans and the Eastern Neighbourhood

There has been a shift in the EU’s stance on enlargement towards geopolitical logic and actorness. This article examines how local perceptions and expectations in Candidate Countries (CCs) are shaped by malign foreign influences and the ‘geopolitization’ of EU enlargement, including the interplay between control and protean powers in addressing challenges. Building on data from public opinion polls in these countries in 2021–2025 as well as focus groups with experts and…

Read at Journal articles (OpenAlex)

arXiv (research papers) Xinting Liao SI

CPInj: Uncovering Prompt Injection Risks in Textual Collaborative Prompt Optimization

Textual Collaborative Prompt Optimization (TCPO) extends TextGrad (Yuksekgonul et al., 2025) to a decentralized setting by allowing multiple clients to jointly improve prompts for large language models (LLMs) while keeping their data locally. Its reliance on free-form textual updating and aggregation introduces a new and largely unexplored attack surface, i.e., malicious instructions can be injected into local prompts and propagated through server-side prompt aggregation…

Read at arXiv (research papers)

Older stories