Results for “Prompt”

arXiv (research papers) Indranil Halder SI

Jailbreak Scaling Laws for Large Language Models: Polynomial-Exponential Crossover

Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth observed without injection to exponential growth with the number of inference-time samples. We first identify a minimal statistical mechanism for these two regimes by giving a small set of assumptions on the distribution of safe generation across…

Read at arXiv (research papers)

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) Chuan Guo Michael Pokorny SI

IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs

Instruction hierarchy (IH) defines how LLMs prioritize system, developer, user, and tool instructions under conflict, providing a concrete, trust-ordered policy for resolving instruction conflicts. IH is key to defending against jailbreaks, system prompt extractions, and agentic prompt injections. However, robust IH behavior is difficult to train: IH failures can be confounded with instruction-following failures, conflicts can be nuanced, and models can learn shortcuts such…

Read at arXiv (research papers)

Dialogue Earth (formerly Diálogo Chino) Nadia Luna Geopolitics

Salmon farming is coming to the end of the world

The Argentinian province of Tierra del Fuego has U-turned on its pioneering decision to ban salmon aquaculture, prompting conservation fears

Read at Dialogue Earth (formerly Diálogo Chino)

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) Yuxu Ge SI

Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice

Autonomous agents powered by large language models introduce a class of execution-layer vulnerabilities -- prompt injection, retrieval poisoning, and uncontrolled tool invocation -- that existing guardrails fail to address systematically. In this work, we propose the Layered Governance Architecture (LGA), a four-layer framework comprising execution sandboxing (L1), intent verification (L2), zero-trust inter-agent authorization (L3), and immutable audit logging (L4). To…

Read at arXiv (research papers)

Simon Willison SI

Clinejection — Compromising Cline's Production Releases just by Prompting an Issue Triager

Clinejection — Compromising Cline's Production Releases just by Prompting an Issue Triager Adnan Khan describes a devious attack chain against the Cline GitHub repository, which started with a prompt injection attack in the title of an issue opened against the repo. Cline were running AI-powered issue triage using the anthropics/claude-code-action@v1 action, configured to run Claude Code with --allowedTools "Bash,Read,Write,..." any time any user opened an issue in their…

Read at Simon Willison

arXiv (research papers) Junchen Li SI

When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG

Retrieval-Augmented Generation (RAG) systems are vulnerable to blocking attacks, in which poisoned documents cause large language models (LLMs) to refuse benign queries. Existing attacks rely on adversarial suffixes or explicit instructions, which are increasingly ineffective against modern LLMs, susceptible to prompt injection filtering, or require feedback from the target system. We observe overlapping risk categories and refusal criteria across safety-aligned LLMs, a…

Read at arXiv (research papers)

arXiv (research papers) Neha Nagaraja SI

Image-based Prompt Injection: Hijacking Multimodal LLMs through Visually Embedded Adversarial Instructions

Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection (IPI), a black-box attack in which adversarial instructions are embedded into natural images to override model behavior. Our end-to-end IPI pipeline incorporates segmentation-based region selection, adaptive font scaling, and background-aware rendering to conceal prompts from human perception…

Read at arXiv (research papers)

arXiv (research papers) Neha Nagaraja SI

Goal-Driven Risk Assessment for LLM-Powered Systems: A Healthcare Case Study

While incorporating LLMs into systems offers significant benefits in critical application areas such as healthcare, new security challenges emerge due to the potential cyber kill chain cycles that combine adversarial model, prompt injection and conventional cyber attacks. Threat modeling methods enable the system designers to identify potential cyber threats and the relevant mitigations during the early stages of development. Although the cyber security community has…

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) Martin Odersky SI

Tracking Capabilities for Safer Agents

AI agents that interact with the real world through tool calls pose fundamental safety challenges: agents might leak private information, cause unintended side effects, or be manipulated through prompt injection. To address these challenges, we propose to put the agent in a programming-language-based "safety harness": instead of calling tools directly, agents express their intentions as code in a capability-safe language: Scala 3 with capture checking. Capabilities are…

Read at arXiv (research papers)

arXiv (research papers) Haritz Puerto SI

From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves

Large reasoning models (LRMs) produce reasoning traces (RTs) that often contain sensitive information. These leaky thoughts are difficult to control and frequently violate explicit privacy directives. Because RTs can be exposed through prompt injection attacks, this becomes a direct privacy risk to the user. We approach this as a controllability problem: since privacy directives are themselves instructions, improving instruction-following (IF) within the RT provides a direct…

Read at arXiv (research papers)

arXiv (research papers) Qianxun Xu SI

SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls

Recent advances in text-to-video diffusion models have enabled high-fidelity and temporally coherent videos synthesis. However, current models are predominantly optimized for single-event generation. When handling multi-event prompts, without explicit temporal grounding, such models often produce blended or collapsed scenes that break the intended narrative. To address this limitation, we present SwitchCraft, a training-free framework for multi-event video generation. Our…

Read at arXiv (research papers)

arXiv (research papers) Tian Zhang SI

AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification

Tool-augmented large language model (LLM) agents aggregate dialogue history, tool outputs, and retrieved content into an accumulated runtime state to complete multi-step tasks. This execution model exposes agents to indirect prompt injection (IPI) attacks, in which attacker-controlled instructions embedded in external artifacts enter the agent state and later influence tool use. Multi-turn IPI is especially challenging because injected content can persist across steps and…

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) Piyush Jaiswal SI

Analysis of LLMs Against Prompt Injection and Jailbreak Attacks

Large Language Models (LLMs) are widely deployed in real-world systems. Given their broader applicability, prompt engineering has become an efficient tool for resource-scarce organizations to adopt LLMs for their own purposes. At the same time, LLMs are vulnerable to prompt-based attacks. Thus, analyzing this risk has become a critical security requirement. This work evaluates prompt-injection and jailbreak vulnerability using a large, manually curated dataset across…

Read at arXiv (research papers)

arXiv (research papers) Che Wang SI

AdapTools: Adaptive Tool-based Indirect Prompt Injection Attacks on Agentic LLMs

The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security vulnerabilities, particularly indirect prompt injection (IPI) attacks. Existing attack methods are limited by their reliance on static patterns and evaluation on simple language models, failing to address the fast-evolving nature of modern AI agents. We…

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)

arXiv (research papers) David Schmotz SI

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this can extend agent capabilities to new domains, it creates an increasingly complex agent supply chain, offering new surfaces for prompt injection attacks. We identify skill-based prompt injection as a significant threat and introduce…

Read at arXiv (research papers)

arXiv (research papers) Zac Garby SI

The LLMbda Calculus: AI Agents, Conversations, and Information Flow

Large language models are increasingly deployed as agents: they plan, call tools, read untrusted data, and act on the results. This exposes them to prompt injection: data meant only to be read is obeyed as an instruction. The most principled defences replace content inspection with provenance: classifying data by source and keeping trusted and untrusted apart through a separation of duty (the dual-LLM pattern) and information-flow control. Yet the leading systems are hard to…

Read at arXiv (research papers)

arXiv (research papers) Charles Ye SI

Prompt Injection as Role Confusion

LLMs see the world as a single stream of text, partitioned into roles like or . We trace prompt injection to role confusion: models perceive the source of text from how it sounds, not its labeled role. A command hidden in a webpage hijacks an agent simply because it sounds like text, despite its label. We design role probes to measure how LLMs internally perceive "who is speaking," and find that injected text occupies the same representational space as the trusted role it…

Read at arXiv (research papers)

Journal articles (OpenAlex) Samuel Finnerty · PLOS Climate Geopolitics

Scientists as activists: An ethnography of the ‘critical moments’ in scientists’ transition to climate activism

Policy responses to the climate crisis have lagged behind the scientific consensus on its seriousness, prompting a growing number of scientists to engage in activism, including civil disobedience. This shift challenges traditional norms of neutrality and objectivity, raising questions about how scientists reconcile their professional identity with activism and sustain engagement. Drawing on two years of immersive ethnography (participant observation and autoethnography) with…

Read at Journal articles (OpenAlex)

arXiv (research papers) Manuel Wirth SI

Trojan Horses in Recruiting: A Red-Teaming Case Study on Indirect Prompt Injection in Standard vs. Reasoning Models

As Large Language Models (LLMs) are increasingly integrated into automated decision-making pipelines, specifically within Human Resources (HR), the security implications of Indirect Prompt Injection (IPI) become critical. While a prevailing hypothesis posits that "Reasoning" or "Chain-of-Thought" Models possess safety advantages due to their ability to self-correct, emerging research suggests these capabilities may enable more sophisticated alignment failures. This…

Read at arXiv (research papers)

arXiv (research papers) Yu Yin SI

The Vulnerability of LLM Rankers to Prompt Injection Attacks

Large Language Models (LLMs) have emerged as powerful re-rankers. Recent research has however showed that simple prompt injections embedded within a candidate document (i.e., jailbreak prompt attacks) can significantly alter an LLM's ranking decisions. While this poses serious security risks to LLM-based ranking pipelines, the extent to which this vulnerability persists across diverse LLM families, architectures, and settings remains largely under-explored. In this paper, we…

Read at arXiv (research papers)

arXiv (research papers) Xiaojun Jia SI

SkillJect: Effectively Automating Skill-Based Prompt Injection for Skill-Enabled Agents

Agent skills extend LLM agents with task-specific instructions, executable scripts, and auxiliary resources, improving reusability but creating a new supply-chain attack surface. A malicious or compromised skill can be repeatedly loaded as trusted guidance and steer downstream tool use. Existing skill-based prompt-injection attacks are often manual and brittle, because explicit malicious instructions are rejected or ignored when they are not aligned with the original…

Read at arXiv (research papers)

arXiv (research papers) Max Fomin SI

When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift

Detecting prompt injection, jailbreak attacks, and harmful requests is critical for deploying LLM-based agents safely, yet current evaluation practices in this literature overestimate generalization. We train activation-based classifiers (linear probes on LLM hidden states) on a benchmark of 18 datasets (prompt attacks plus benign sources) and propose Leave-One-Dataset-Out (LODO) evaluation, where the held-out dataset is never seen during training. Across four LLMs from…

Read at arXiv (research papers)

arXiv (research papers) Yuqi Jia SI

AlignSentinel: Alignment-Aware Detection of Prompt Injection Attacks

Prompt injection attacks insert malicious instructions into an LLM's input to steer it toward an attacker-chosen task instead of the intended one. Existing detection defenses typically classify any input with instruction as malicious, leading to misclassification of benign inputs containing instructions that align with the intended task. In this work, we account for the instruction hierarchy and distinguish among three categories: inputs with misaligned instructions, inputs…

Read at arXiv (research papers)

arXiv (research papers) Aashish Kolluri SI

Optimizing Agent Planning for Security and Autonomy

Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe actions by enforcing confidentiality and integrity policies, but currently appear costly: they reduce task completion rates and increase token usage compared to probabilistic defenses. We argue that existing evaluations miss a key benefit of system-level defenses: reduced reliance on human oversight…

Read at arXiv (research papers)

arXiv (research papers) J Alex Corll SI

Peak + Accumulation: A Proxy-Level Scoring Formula for Multi-Turn LLM Attack Detection

Multi-turn prompt injection attacks distribute malicious intent across multiple conversation turns, exploiting the assumption that each turn is evaluated independently. While single-turn detection has been extensively studied, no published formula exists for aggregating per-turn pattern scores into a conversation-level risk score at the proxy layer -- without invoking an LLM. We identify a fundamental flaw in the intuitive weighted-average approach: it converges to the…

Read at arXiv (research papers)

Older stories