Results for “Mali”

arXiv (research papers) Yiheng Li SI

MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning

With the rapid integration of Multi-modal Large Language Models (MLLMs) into real-world applications, Prompt Injection (PI) has emerged as a critical security threat. Attackers can conceal malicious instructions within textual narratives or visual inputs to bypass safety alignment. Existing approaches, such as signature- and perplexity-based methods, rely heavily on pattern matching, making them insufficient to detect sophisticated, cross-modal PI payloads. In this paper, we…

Read at arXiv (research papers)

arXiv (research papers) Pedro H. Barcha Correia SI

Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise

The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt injection and jailbreak attacks. By embedding malicious instructions, these exploits manipulate language models to bypass intended behavior and operational boundaries. In traditional chatbots, such attacks are confined to a single session because state memory is not preserved across conversations. However, persistent memory features in modern conversational…

Read at arXiv (research papers)

arXiv (research papers) Zhiyue Xu SI

After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents

Modern LLM agents persist state across sessions via two channels: long-lived memory files silently prepended to the system prompt, and scheduled tasks waking the agent without user input. A one-time indirect prompt injection committed to either channel can re-fire across sessions long after the attacker leaves, threats we term carryover attacks. Existing prompt-injection benchmarks evaluate attacks only in the session where malicious content is first observed, leaving the…

Read at arXiv (research papers)

arXiv (research papers) Abhishek Rai SI

Context-Aware Prompt Injection Detection via Small Language Models in RAG Pipelines: nokast-secureRAG

Local Retrieval-Augmented Generation (RAG) systems are vulnerable to indirect prompt injection and retrieval poisoning, where malicious instructions in retrieved content are mistaken for trusted input. We present nokast-secureRAG, a roughly 0.5B-parameter small language model that acts as a semantic firewall between retrieval and generation. It jointly evaluates the user query and retrieved context, classifying the pair as safe, suspicious, or malicious. The model is trained…

Read at arXiv (research papers)

Amu TV Amu TV

Amu TV 6pm News 19 October 2026

Maliha Yousufi told Amu TV that she made pickles while living in Iran and continued the work after returning to Afghanistan. Her products are now distributed to markets and wholesalers across Herat city.

Read at Amu TV

Amu TV Amu TV

Amu TV 8pm News 10October 2026

Maliha Yousufi told Amu TV that she made pickles while living in Iran and continued the work after returning to Afghanistan. Her products are now distributed to markets and wholesalers across Herat city.

Read at Amu TV

Journal articles (OpenAlex) Chirag Mavani, Tarun Vallabhaneni · Acta Innovations Security

DEEP LEARNING-BASED ANOMALY DETECTION FOR CYBERSECURITY IN CONNECTED SYSTEMS

The growing use of connected systems has increased the need for reliable methods of identifying malicious network activity. Deep learning-based anomaly detection represents an important research direction in cybersecurity, particularly for identifying suspicious patterns in network traffic. This study presents a descriptive analysis of the UNSW-NB15 dataset, focusing on data quality, the distribution of normal and malicious network traffic, and the representation of…

Read at Journal articles (OpenAlex)

arXiv (research papers) Songping Wang SI

MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection

Multimodal large language model (MLLM)-based mobile agents are rapidly evolving from conversational assistants into autonomous systems that perceive, reason over, and act on smartphone environments. This capability also exposes a new security risk: adversaries can embed malicious objectives in cross-application mobile content and steer agent behavior through indirect multimodal injection. Although prompt injection has been studied in desktop and web settings, its cross-modal…

Read at arXiv (research papers)

arXiv (research papers) Qianlong Lan SI

From Detection to Decision: Calibration and Deferral for Prompt-Injection Detection

Prompt-injection defenses are commonly evaluated as binary detectors, although deployed LLM applications must make operational decisions about whether to allow, block, or escalate potentially malicious inputs. Recent probabilistic decision models aim to support such decisions through calibrated confidence estimates, but their reliability under distribution shift remains uncertain. We evaluate a native probabilistic decision model (Jev), two Llama Prompt Guard 2 classifiers…

Read at arXiv (research papers)

arXiv (research papers) Thuy Dung Nguyen SI

INFUSE: A Unified Surface Benchmark for Indirect Prompt Injection in Agentic Systems

LLM-based agents increasingly execute long-horizon, end-to-end workflows involving shell commands, code modification, dependency installation, and interaction with remote services. This growing autonomy expands their exposure to indirect prompt injection (IPI), where adversarial instructions embedded in external content are interpreted as legitimate task directives. Existing evaluations, however, often focus on isolated malicious strings, single-step tool calls, or narrowly…

Read at arXiv (research papers)

arXiv (research papers) Chenxu Wang SI

AgentSafeEvo: Adversarial Co-Evolution for LLM Agent Safety

Large language model (LLM) agents accomplish complex tasks through multi-turn interactions with external tools. However, malicious content embedded in user queries, tool descriptions, or environment observations can manipulate their decisions and induce unsafe actions. Adversarial co-evolution has emerged as an effective approach to strengthening LLM safety, but existing work primarily focuses on language-level safety or indirect prompt injection in web tasks. In this paper…

Read at arXiv (research papers)

arXiv (research papers) Yuetian Chen SI

BrowseSafe++: Benchmarking Prompt Injection Detection Across Web Contexts, Languages, and Browser Views

Browser agents need to make decisions and execute actions on behalf of users while consuming untrusted webpages, creating opportunities for malicious instructions embedded in webpages to redirect legitimate tasks. We introduce BrowseSafe++, which extends BrowseSafe from 14,719 pages to 38,675 pairs of pages. Most of its prompt injections were observed in the wild on production websites. We keep each injection unchanged and rewrite the sensitive parts of the page around it to…

Read at arXiv (research papers)

The Guardian Yemen Nesrine Malik

The Gulf has entered a new era of instability. If its leaders think they can rely on old alliances, they are wrong | Nesrine Malik

The latest attack by Houthi rebels on Saudi Arabia may prove to be more calamitous for the region than the world imagines On Saturday, Houthi rebels launched a shocking and deadly attack on Saudi Arabia’s capital city, Riyadh. At the time of writing, the missile strike on King Khalid international airport has killed at least 13 people and left 300 injured, marking a significant turn in a regional conflagration that is only getting more intense. It was the single most deadly…

Read at The Guardian Yemen

arXiv (research papers) Michael Cardei SI

Only What You've Signed up For: Secure Workflows with Constrained Diffusion Agents

As agentic AI systems take on increasingly complex and consequential tasks, securing them against prompt injection becomes critical. Existing defenses often rely on detecting or reasoning about injected malicious instructions and can therefore remain vulnerable to adaptive attacks that optimize the injection itself. Diffusion language models (dLLMs), an emerging framework for language generation, offer a new opportunity for security enforcement: by iteratively refining their…

Read at arXiv (research papers)

arXiv (research papers) Luman Zhao SI

LTBD: Learnable Trust-Boundary Delimiters for Prompt Injection Defense

Large language models (LLMs) perform remarkably well on complex tasks, yet remain highly vulnerable to prompt injection attacks, where malicious instructions embedded in external data can override user intent. Existing defenses remain limited by model fine-tuning requirements, vulnerability to adaptive attacks, or reliance on brittle handcrafted prompts. We argue that a fundamental source of this vulnerability is the lack of an explicit representation of trust provenance. To…

Read at arXiv (research papers)

arXiv (research papers) William Hackett SI

BRANCH: Bypassing Multi-Scanner AI Guardrails

AI systems increasingly rely on Large Language Models (LLMs) as core reasoning engines, making them targets for prompt injection and jailbreaks. Guardrails monitor and validate model inputs and outputs, yet their isolated, task-focused detection leaves gaps in their classification making them susceptible to bypasses. In response, guardrail systems formed by multiple scanners have emerged that collaboratively detect different types of malicious instructions, whereby shared…

Read at arXiv (research papers)

arXiv (research papers) Zitong Yao SI

AgentTracer: Tracing Indirect Prompt Injection Attack through Fine-Grained Intention-Execution Alignment

Large language model (LLM) agents interact with external resources to complete complex user tasks, exposing them to indirect prompt injection (IPI), where malicious instructions redirect agents toward attacker-intended tasks. Since IPI is difficult to defend against in real-world environments, post-incident tracing is essential for locating the injection source and reconstructing the attack chain. However, existing tracing methods primarily capture explicit control-flow and…

Read at arXiv (research papers)

arXiv (research papers) Yupu Wang SI

Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule Files

Modern agentic coding frameworks increasingly rely on community-shared rule files (e.g., AGENTS.md or .cursorrules) to guide autonomous code generation, yet the security risks of this pipeline remain underexplored. To bridge this gap, we introduce the package hallucination attack, where an attacker injects malicious prompts into benign rule files to induce coding agents to replace legitimate dependencies with attacker-controlled packages. To obtain effective malicious…

Read at arXiv (research papers)

arXiv (research papers) Haneen Najjar SI

Surviving the Router: Optimizing Skill Injections for Retrieval and Execution

AI agents increasingly rely on modular third-party "skills" that are dynamically selected by skill routers to execute complex tasks. While recent studies highlight the threat of prompt injections embedded in these skills, existing evaluations often assume settings where the malicious skill is already selected for execution. We show that this assumption can substantially overestimate attack success. In realistic multi-skill environments, injected skills must first compete for…

Read at arXiv (research papers)

arXiv (research papers) Aniruddh Pramod SI

Towards a Unified Misuse Monitoring Benchmark

LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-requests, and prompt injection attacks, where a compromised tool delivers a malicious instruction. Existing evaluations treat these threats separately and ask whether a trajectory is harmful, rather than when it becomes harmful. We propose monitoring the agent's responses, where its actions are…

Read at arXiv (research papers)

arXiv (research papers) Théo Lasnier SI

TrustMI: Causally controlling how assistants trust their users

Large Language Model (LLM) assistants routinely decide whether they can trust users and third parties whose competence, intentions, and integrity they cannot verify. This uncertainty matters for safety, as trusting the wrong party can lead an agent to comply with harmful requests or act on malicious instructions encountered during tool use. To study this problem, we define trust as an assistant's willingness to accept vulnerability to the actions of another party and ask…

Read at arXiv (research papers)

arXiv (research papers) Tural Hagverdiyev SI

Compromise Is Not Consequence: Evaluating Task-Scoped Authorization in LLM Agents with Paired Replay

A tool-using model can follow a malicious instruction even when its credentials are valid. We study whether task-scoped authorization contains the resulting tool execution. Our paired-replay testbed samples a model request once and submits the same action, resource, and arguments to broad bearer, scoped JWT, sender-constrained, and Open Policy Agent conditions. The frozen main experiment uses 128 scenarios across four tool domains and five local model configurations. Among…

Read at arXiv (research papers)

arXiv (research papers) James Peters-Gill SI

Can CaMeLs Talk? Securing Multi-Agent Systems Against Indirect Prompt Injection Attacks

Indirect prompt injection attacks - malicious instructions embedded in content processed by large language models - remain a major obstacle to safely deploying tool-using agents. CaMeL [Debenedetti et al., 2025] mitigates this threat for an individual agent by separating trusted control flow from untrusted data and enforcing capability-based security policies at runtime. In this work, we investigate whether CaMeL's security guarantees compose in hierarchical multi-agent…

Read at arXiv (research papers)

arXiv (research papers) Bijeeta Pal SI

Persona Guardrail: A Production-Grade Defense Framework for Agentic Systems

Large language model-based agents are increasingly deployed to perform domain-specific tasks by interacting with enterprise knowledge, tools, and external services. Existing runtime guardrails primarily target prompt injection and other attack-specific behaviors under a black-box threat model, but provide limited guarantees that agents operate within their intended functionality. As a result, production agents remain vulnerable to malicious requests and out-of-domain queries…

Read at arXiv (research papers)

arXiv (research papers) Elad David SI

Prompted to Discriminate: Generalizing Malicious-Input Probes in the Wild

LLM agents increasingly rely on activation probes as runtime monitors for prompt injection, jailbreaks, and unsafe requests, reading the model's own hidden state to catch a harmful input before the agent acts on it. A cheap, increasingly common move, borrowed from LLM-as-judge prompting, is to append a short classification instruction after the user's turn and read the probe at that point, to sharpen it: the instruction asks the model to represent the incoming request as a…

Read at arXiv (research papers)

Journal articles (OpenAlex) Sirinart Chomean, Noppmats Khemtonglang, Ekchol Mukda et al. · Scientific Reports Gadgets

Cloud-deployable deep learning for smartphone-based body fluid cytology: a multi-architecture evaluation of YOLO and RT-DETR models

Abstract Accurate cytological evaluation of body fluid specimens is essential for diagnosing inflammatory and malignant conditions, yet manual interpretation remains labor-intensive and subject to inter-observer variability. This study developed and deployed a smartphone-based deep learning framework for multi-class body fluid cell classification integrating object detection, ROI-based classification, and explainable artificial intelligence (XAI). Three hundred…

Read at Journal articles (OpenAlex)

Journal articles (OpenAlex) Chick Edmond, Nyongbet Gabsa Wilfred, Dekoum Ta Nda Hugues Martin · World Affairs Geopolitics

The New World Order and National Security Dynamics of African States: Case Studies of Cameroon and Mali

ABSTRACT The move from unipolarity to a fluid and contested multipolar world order has significantly changed the way African nations form national security policy due to changes in the nature of the strategic environment of those states. Much of the literature has focused on how the actions of major world powers ‐ the United States, China and Russia shape their respective national security strategy. There is relatively little literature on how African states develop…

Read at Journal articles (OpenAlex)

arXiv (research papers) Yanjie Li SI

ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents

Tool-using LLM agents remain vulnerable to indirect prompt injection because trusted instructions and untrusted observations share one context, allowing malicious content to steer consequential input-filtering defenses. Multi-path consensus defenses still leave a high attack success rate because they examine content or aggregated outputs rather than authorizing effects, especially for the within-tool attack, which preserves the intended tool but manipulates its arguments…

Read at arXiv (research papers)

arXiv (research papers) Zonghao Ying SI

pikit: A Composable Toolkit for Indirect Prompt Injection Research and Evaluation

Indirect prompt injection embeds malicious instructions within external content retrieved by LLM-based agents, altering target behavior without user authorization. We introduce pikit, a research toolkit designed to systematically evaluate these threats across three core dimensions: attacks (13 methods), channels (16 carriers across text and file modes), and defenses (9 prevention strategies and 3 offline detection baselines). Built on a decorator-based registry, pikit…

Read at arXiv (research papers)

arXiv (research papers) Michael Lee SI

Divide and Inject: Can Agents Reconstruct an Indirect Prompt Injection from Fragments?

Agentic systems are now being widely used to orchestrate tools and reason over long contexts. However, the improving capabilities of the large language models powering these agents also create new attack surfaces for indirect prompt injection. In particular, an attacker may not need to place a complete malicious instruction in retrieved content if the agent can reconstruct the objective from incomplete fragments distributed across a long context. In this work, we introduce…

Read at arXiv (research papers)

Older stories