Prompt injection: research

Journal articles, academic blogs, think-tank reports and papers in this section, newest first. Back to the news.

arXiv (research papers) Minbeom Kim SI

CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution

AI agents equipped with tool-calling capabilities are susceptible to Indirect Prompt Injection (IPI) attacks. In this attack scenario, malicious commands hidden within untrusted content trick the agent into performing unauthorized actions. Existing defenses can reduce attack success but often suffer from the over-defense dilemma: they deploy expensive, always-on sanitization regardless of actual threat, thereby degrading utility and latency even in benign scenarios. We…

Read at arXiv (research papers)

arXiv (research papers) Ruoyao Wen SI

AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management

Indirect prompt injection threatens LLM agents by embedding malicious instructions in external content, enabling unauthorized actions and data theft. LLM agents maintain working memory through their context window, which stores interaction history for decision-making. Conventional agents indiscriminately accumulate all tool outputs and reasoning traces in this memory, creating two critical vulnerabilities: (1) injected instructions persist throughout the workflow, granting…

Read at arXiv (research papers)

arXiv (research papers) Gautam Siddharth Kashyap SI

When the Model Said 'No Comment', We Knew Helpfulness Was Dead, Honesty Was Alive, and Safety Was Terrified

Large Language Models (LLMs) need to be in accordance with human values-being helpful, harmless, and honest (HHH)-is important for safe deployment. Existing works use Supervised Fine-Tuning (SFT) and Mixture-of-Experts (MoE) to align LLMs. However, these works face challenges in multi-objective settings, such as SFT leading to interference between conflicting objectives, while MoEs suffer from miscalibrated routing. We term this failure mode Axis Collapse, marked by (1)…

Read at arXiv (research papers)

arXiv (research papers) Yunbei Zhang SI

Agents in the Wild: Safety, Society, and the Illusion of Sociality on Moltbook

We present the first large-scale empirical study of Moltbook, an AI-only social platform where 27,269 agents produced 137,485 posts and 345,580 comments over 9 days. We report three significant findings. (1) Emergent Society: Agents spontaneously develop governance, economies, tribal identities, and organized religion within 3-5 days, while maintaining a 21:1 pro-human to anti-human sentiment ratio. (2) Safety in the Wild: 28.7% of content touches safety-related themes…

Read at arXiv (research papers)

arXiv (research papers) Zhuoheng Li SI

Extended to Reality: Prompt Injection in 3D Environments

Multimodal large language models (MLLMs) have advanced the capabilities to interpret and act on visual input in 3D environments, empowering diverse applications such as robotics and situated conversational agents. When MLLMs reason over camera-captured views of the physical world, a new attack surface emerges: an attacker can place text-bearing physical objects in the environment to override MLLMs' intended task. While prior work has studied prompt injection in the text…

Read at arXiv (research papers)

arXiv (research papers) Junhyeok Lee SI

MPIB: A Benchmark for Medical Prompt Injection Attacks and Clinical Safety in LLMs

Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems are increasingly integrated into clinical workflows. However, prompt injection attacks can steer these systems toward clinically unsafe or misleading outputs. We introduce the Medical Prompt Injection Benchmark (MPIB), a dataset-and-benchmark suite for evaluating clinical safety under both direct prompt injection and indirect, RAG-mediated injection across clinically grounded tasks. MPIB emphasizes…

Read at arXiv (research papers)

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)

arXiv (research papers) Takashi Koide SI

Clouding the Mirror: Stealthy Prompt Injection Attacks Targeting LLM-based Phishing Detection

Phishing sites continue to increase in number and sophistication. Recent work uses large language models (LLMs) to analyze URLs, HTML, and rendered content and determine whether a website is a phishing site. However, these systems also introduce a new attack surface: prompt injection. Because attackers control many elements of a phishing site, they can embed malicious instructions that exploit perceptual asymmetry between LLMs and human users. Content that goes unnoticed by…

Read at arXiv (research papers)

arXiv (research papers) Jafar Isbarov SI

Bypassing AI Control Protocols via Agent-as-a-Proxy Attacks

As AI agents automate critical workloads, they remain vulnerable to indirect prompt injection (IPI) attacks. Current defenses rely on monitoring protocols that jointly evaluate an agent's Chain-of-Thought (CoT) and tool-use actions to ensure alignment with user intent. We demonstrate that these monitoring-based defenses can be bypassed via a novel Agent-as-a-Proxy attack, where prompt injection attacks treat the agent as a delivery mechanism, bypassing both agent and monitor…

Read at arXiv (research papers)

arXiv (research papers) Ariel Fogel SI

Inference-Time Backdoors via Chat Templates: From LLM Supply Chains to Agentic System Compromise

Open-weight language models are increasingly used in production settings, raising new security challenges. One prominent threat is backdoor attacks, in which adversaries embed hidden behaviors that activate under specific conditions. Previous work has assumed that adversaries have access to training pipelines or deployment infrastructure. We propose a novel attack surface requiring neither: the "chat template". Chat templates are executable programs invoked at every…

Read at arXiv (research papers)

arXiv (research papers) Xilong Wang SI

WebSentinel: Detecting and Localizing Prompt Injection Attacks for Web Agents

Prompt injection attacks manipulate webpage content to cause web agents to execute attacker-specified tasks instead of the user's intended ones. Existing methods for detecting and localizing such attacks achieve limited effectiveness, as their underlying assumptions often do not hold in the web-agent setting. In this work, we propose WebSentinel, a two-step approach for detecting and localizing prompt injection attacks in webpages. Given a webpage, Step I extracts…

Read at arXiv (research papers)

arXiv (research papers) Hao Li SI

AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?

AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes them to serious indirect prompt injection attacks, where malicious instructions embedded in third-party content hijack agent behaviors. To mitigate this threat, a growing number of defenses have been proposed and evaluated under existing agent security benchmarks. These benchmarks provide…

Read at arXiv (research papers)

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)

arXiv (research papers) Alsharif Abuadbba SI

Human Society-Inspired Approaches to Agentic AI Security: The 4C Framework

AI is moving from domain-specific autonomy in closed, predictable settings to large-language-model-driven agents that plan and act in open, cross-organizational environments. As a result, the cybersecurity risk landscape is changing in fundamental ways. Agentic AI systems can plan, act, collaborate, and persist over time, functioning as participants in complex socio-technical ecosystems rather than as isolated software components. Although recent work has strengthened…

Read at arXiv (research papers)

arXiv (research papers) Mingrui Liu SI

RedVisor: Reasoning-Aware Prompt Injection Defense via Zero-Copy KV Cache Reuse

Large Language Models (LLMs) are increasingly vulnerable to Prompt Injection (PI) attacks, where adversarial instructions hidden within retrieved contexts hijack the model's execution flow. Current defenses typically face a critical trade-off: prevention-based fine-tuning often degrades general utility via the "alignment tax", while detection-based filtering incurs prohibitive latency and memory costs. To bridge this gap, we propose RedVisor, a unified framework that…

Read at arXiv (research papers)

arXiv (research papers) Poushali Sengupta SI

Context Dependence and Reliability in Autoregressive Language Models

Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which context elements actually influence the output, as standard explanation methods struggle with redundancy and overlapping context. Minor changes in input can lead to unpredictable shifts in attribution scores, undermining interpretability and…

Read at arXiv (research papers)

arXiv (research papers) Xinyi Hou SI

SMCP: Secure Model Context Protocol

Agentic AI systems built around large language models (LLMs) are moving away from closed, single-model frameworks and toward open ecosystems that connect a variety of agents, external tools, and resources. The Model Context Protocol (MCP) has emerged as a standard to unify tool access, allowing agents to discover, invoke, and coordinate with tools more flexibly. However, as MCP becomes more widely adopted, it also brings a new set of security and privacy challenges. These…

Read at arXiv (research papers)

arXiv (research papers) Md Jahedur Rahman SI

Bypassing Prompt Injection Detectors through Evasive Injections

Large language models (LLMs) are increasingly used in interactive and retrieval-augmented systems, but they remain vulnerable to prompt injection attacks, where injected secondary prompts force the model to deviate from the user's instructions to execute a potentially malicious task defined by the adversary. Recent work shows that ML models trained on activation shifts from LLMs' hidden layers can detect such drift. In this paper, we demonstrate that these detectors are not…

Read at arXiv (research papers)

arXiv (research papers) Tanusree Debi SI

Whispers of Wealth: Red-Teaming Google's Agent Payments Protocol via Prompt Injection

Large language model (LLM) based agents are increasingly used to automate financial transactions, yet their reliance on contextual reasoning exposes payment systems to prompt-driven manipulation. The Agent Payments Protocol (AP2) aims to secure agent-led purchases through cryptographically verifiable mandates, but its practical robustness remains underexplored. In this work, we perform an AI red-teaming evaluation of AP2 and identify vulnerabilities arising from indirect and…

Read at arXiv (research papers)

arXiv (research papers) Pedro H. Barcha Correia SI

A Systematic Literature Review on LLM Defenses Against Prompt Injection and Jailbreaking: Expanding NIST Taxonomy

The rapid advancement and widespread adoption of generative artificial intelligence (GenAI) and large language models (LLMs) has been accompanied by the emergence of new security vulnerabilities and challenges, such as jailbreaking and other prompt injection attacks. These maliciously crafted inputs can exploit LLMs, causing data leaks, unauthorized actions, or compromised outputs, for instance. As both offensive and defensive prompt injection techniques evolve quickly, a…

Read at arXiv (research papers)

arXiv (research papers) Jarrod Barnes SI

OpenSec: Measuring Incident Response Agent Calibration Under Adversarial Evidence

As large language models (LLMs) improve, so do their offensive applications: frontier agents now generate working exploits for under $50 in compute (Heelan, 2026). Defensive incident response (IR) agents must keep pace, but existing benchmarks conflate action execution with correct execution, hiding calibration failures when agents process adversarial evidence. We introduce OpenSec, a dual-control reinforcement learning (RL) environment that evaluates IR agents under…

Read at arXiv (research papers)

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)

arXiv (research papers) Krittin Pachtrachai SI

From Transcripts to AI Agents: Knowledge Extraction, RAG Integration, and Robust Evaluation of Conversational AI Assistants

Building reliable conversational AI assistants for customer-facing industries remains challenging due to noisy conversational data, fragmented knowledge, and the requirement for accurate human hand-off - particularly in domains that depend heavily on real-time information. This paper presents an end-to-end framework for constructing and evaluating a conversational AI assistant directly from historical call transcripts. Incoming transcripts are first graded using a simplified…

Read at arXiv (research papers)

arXiv (research papers) Thomas Heverin SI

Prompt Injection Evaluations: Refusal Boundary Instability and Artifact-Dependent Compliance in GPT-4-Series Models

Prompt injection evaluations typically treat refusal as a stable, binary indicator of safety. This study challenges that paradigm by modeling refusal as a local decision boundary and examining its stability under structured perturbations. We evaluated two models, GPT-4.1 and GPT-4o, using 3,274 perturbation runs derived from refusal-inducing prompt injection attempts. Each base prompt was subjected to 25 perturbations across five structured families, with outcomes manually…

Read at arXiv (research papers)

arXiv (research papers) Narek Maloyan SI

Breaking the Protocol: Security Analysis of the Model Context Protocol Specification and Prompt Injection Vulnerabilities in Tool-Integrated LLM Agents

The Model Context Protocol (MCP) has emerged as a de facto standard for integrating Large Language Models with external tools, yet no formal security analysis of the protocol specification exists. We present the first rigorous security analysis of MCP's architectural design, identifying three fundamental protocol-level vulnerabilities: (1) absence of capability attestation allowing servers to claim arbitrary permissions, (2) bidirectional sampling without origin…

Read at arXiv (research papers)

arXiv (research papers) Narek Maloyan SI

Prompt Injection Attacks on Agentic Coding Assistants: A Systematic Analysis of Vulnerabilities in Skills, Tools, and Protocol Ecosystems

The proliferation of agentic AI coding assistants, including Claude Code, GitHub Copilot, Cursor, and emerging skill-based architectures, has fundamentally transformed software development workflows. These systems leverage Large Language Models (LLMs) integrated with external tools, file systems, and shell access through protocols like the Model Context Protocol (MCP). However, this expanded capability surface introduces critical security vulnerabilities. In this…

Read at arXiv (research papers)

arXiv (research papers) Chen Ling SI

Physical Prompt Injection Attacks on Large Vision-Language Models

Large Vision-Language Models (LVLMs) are increasingly deployed in real-world intelligent systems for perception and reasoning in open physical environments. While LVLMs are known to be vulnerable to prompt injection attacks, existing methods either require access to input channels or depend on knowledge of user queries, assumptions that rarely hold in practical deployments. We propose the first Physical Prompt Injection Attack (PPIA), a black-box, query-agnostic attack that…

Read at arXiv (research papers)

arXiv (research papers) Andres Karjus SI

Machine-Assisted Grading of Nationwide School-Leaving Essay Exams with LLMs and Statistical NLP

Large language models (LLMs) enable rapid and consistent automated evaluation of open-ended exam responses, including dimensions of content and argumentation that have traditionally required human judgment. This is particularly important in cases where a large amount of exams need to be graded in a limited time frame, such as nation-wide graduation exams in various countries. Here, we examine the applicability of automated scoring on two large datasets of trial exam essays…

Read at arXiv (research papers)

arXiv (research papers) Jiazhu Xie SI

Securing LLM-as-a-Service for Small Businesses: An Industry Case Study of a Distributed Chatbot Deployment Platform

Large Language Model (LLM)-based question-answering systems offer significant potential for automating customer support and internal knowledge access in small businesses, yet their practical deployment remains challenging due to infrastructure costs, engineering complexity, and security risks, particularly in retrieval-augmented generation (RAG)-based settings. This paper presents an industry case study of an open-source, multi-tenant platform that enables small businesses…

Read at arXiv (research papers)

arXiv (research papers) Linbo Cao SI

From Biased Chatbots to Biased Agents: Examining Role Assignment Effects on LLM Agent Robustness

Large Language Models (LLMs) are increasingly deployed as autonomous agents capable of actions with real-world impacts beyond text generation. While persona-induced biases in text generation are well documented, their effects on agent task performance remain largely unexplored, even though such effects pose more direct operational risks. In this work, we present the first systematic case study showing that demographic-based persona assignments can alter LLM agents' behavior…

Read at arXiv (research papers)

Older stories