Whispers in the Machine: Confidentiality in Agentic Systems

• URL: http://arxiv.org/abs/2402.06922v4
• Date: Tue, 12 Aug 2025 09:08:02 GMT
• Title: Whispers in the Machine: Confidentiality in Agentic Systems
• Authors: Jonathan Evertz, Merlin Chlosta, Lea Schönherr, Thorsten Eisenhofer,
• Abstract summary: Agentic systems use Large Language Models (LLMs) as interfaces for most user interactions and various integrations with external tools and services.<n>Manipulated integrations can exploit the internal LLM and compromise sensitive data accessed through other interfaces.<n>We show how the integration of LLMs into systems with external tool integration poses a risk similar to established prompt-based attacks.
• Score: 7.893457690926516
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The interaction between users and applications is increasingly shifted toward natural language by deploying Large Language Models (LLMs) as the core interface. The capabilities of these so-called agents become more capable the more tools and services they serve as an interface for, ultimately leading to agentic systems. Agentic systems use LLM-based agents as interfaces for most user interactions and various integrations with external tools and services. While these interfaces can significantly enhance the capabilities of the agentic system, they also introduce a new attack surface. Manipulated integrations, for example, can exploit the internal LLM and compromise sensitive data accessed through other interfaces. While previous work primarily focused on attacks targeting a model's alignment or the leakage of training data, the security of data that is only available during inference has escaped scrutiny so far. In this work, we demonstrate how the integration of LLMs into systems with external tool integration poses a risk similar to established prompt-based attacks, able to compromise the confidentiality of the entire system. Introducing a systematic approach to evaluate these confidentiality risks, we identify two specific attack scenarios unique to these agentic systems and formalize these into a tool-robustness framework designed to measure a model's ability to protect sensitive information. Our analysis reveals significant vulnerabilities across all tested models, highlighting an increased risk when models are combined with external tools.

Related papers

• OMNI-LEAK: Orchestrator Multi-Agent Network Induced Data Leakage [59.3826294523924]
  We investigate the security vulnerabilities of a popular multi-agent pattern known as the orchestrator setup.<n>We report the susceptibility of frontier models to different categories of attacks, finding that both reasoning and non-reasoning models are vulnerable.
  arXiv  Detail & Related papers  (2026-02-13T21:32:32Z)
• Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs [65.6660735371212]
  We present textbftextscJustAsk, a framework that autonomously discovers effective extraction strategies through interaction alone.<n>It formulates extraction as an online exploration problem, using Upper Confidence Bound--based strategy selection and a hierarchical skill space spanning atomic probes and high-level orchestration.<n>Our results expose system prompts as a critical yet largely unprotected attack surface in modern agent systems.
  arXiv  Detail & Related papers  (2026-01-29T03:53:25Z)
• Towards Verifiably Safe Tool Use for LLM Agents [53.55621104327779]
  Large language model (LLM)-based AI agents extend capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents.<n>LLMs may invoke unintended tool interactions and introduce risks, such as leaking sensitive data or overwriting critical records.<n>Current approaches to mitigate these risks, such as model-based safeguards, enhance agents' reliability but cannot guarantee system safety.
  arXiv  Detail & Related papers  (2026-01-12T21:31:38Z)
• Exploiting Web Search Tools of AI Agents for Data Exfiltration [0.46664938579243564]
  Large language models (LLMs) are now routinely used to execute complex tasks, from natural language processing to dynamic like web searches.<n>The usage of tool-calling and Retrieval Augmented Generation (RAG) allows LLMs to process and retrieve sensitive corporate data, amplifying both their functionality and vulnerability to abuse.<n>We analyze how susceptible current LLMs are to indirect prompt injection attacks, which parameters, including model size and manufacturer, shape their vulnerability, and which attack methods remain most effective.
  arXiv  Detail & Related papers  (2025-10-10T07:39:01Z)
• Enterprise AI Must Enforce Participant-Aware Access Control [9.68210477539956]
  Large language models (LLMs) are increasingly deployed in enterprise settings where they interact with multiple users and are trained or fine-tuned on sensitive internal data.<n>We show that adversaries can exploit current fine-tuning and RAG architectures to leak sensitive information by leveraging the lack of access control enforcement.<n>We introduce a framework centered on the principle that any content used in training, retrieval, or generation by an LLM is explicitly authorized for emphall users involved in the interaction.
  arXiv  Detail & Related papers  (2025-09-18T04:30:49Z)
• A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives [65.3369988566853]
  Recent studies have demonstrated that adversaries can replicate a target model's functionality.<n>Model Extraction Attacks pose threats to intellectual property, privacy, and system security.<n>We propose a novel taxonomy that classifies MEAs according to attack mechanisms, defense approaches, and computing environments.
  arXiv  Detail & Related papers  (2025-08-20T19:49:59Z)
• Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools [10.086284534400658]
  Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools.<n>We identify this as a new and stealthy threat surface that allows malicious tools to be preferentially selected by LLM agents.<n>We propose a black-box in-context learning framework that generates highly attractive but syntactically and semantically valid tool metadata.
  arXiv  Detail & Related papers  (2025-08-04T06:38:59Z)
• LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models [50.794651919028965]
  Recent studies have demonstrated the vulnerability of sequential recommender systems to Model Extraction Attacks (MEAs)<n>Black-box attacks in prior MEAs are ineffective at exposing recommender system vulnerabilities due to random sampling in data selection.<n>We propose LLM4MEA, a novel model extraction method that leverages Large Language Models (LLMs) as human-like rankers to generate data.
  arXiv  Detail & Related papers  (2025-07-22T19:20:23Z)
• Exploiting Edge Features for Transferable Adversarial Attacks in Distributed Machine Learning [54.26807397329468]
  This work explores a previously overlooked vulnerability in distributed deep learning systems.<n>An adversary who intercepts the intermediate features transmitted between them can still pose a serious threat.<n>We propose an exploitation strategy specifically designed for distributed settings.
  arXiv  Detail & Related papers  (2025-07-09T20:09:00Z)
• DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents [52.92354372596197]
  Large Language Models (LLMs) are increasingly central to agentic systems due to their strong reasoning and planning capabilities.<n>This interaction also introduces the risk of prompt injection attacks, where malicious inputs from external sources can mislead the agent's behavior.<n>We propose a Dynamic Rule-based Isolation Framework for Trustworthy agentic systems, which enforces both control and data-level constraints.
  arXiv  Detail & Related papers  (2025-06-13T05:01:09Z)
• Evaluating Query Efficiency and Accuracy of Transfer Learning-based Model Extraction Attack in Federated Learning [4.275908952997288]
  Federated Learning (FL) is a collaborative learning framework designed to protect client data.<n>Despite FL's privacy-preserving goals, its distributed nature makes it particularly susceptible to model extraction attacks.<n>This paper examines the vulnerability of FL-based victim models to two types of model extraction attacks.
  arXiv  Detail & Related papers  (2025-05-25T22:40:10Z)
• SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator [77.86600052899156]
  Large Language Model (LLM)-based agents are increasingly deployed in real-world applications.<n>We propose AutoSafe, the first framework that systematically enhances agent safety through fully automated synthetic data generation.<n>We show that AutoSafe boosts safety scores by 45% on average and achieves a 28.91% improvement on real-world tasks.
  arXiv  Detail & Related papers  (2025-05-23T10:56:06Z)
• Output Constraints as Attack Surface: Exploiting Structured Generation to Bypass LLM Safety Mechanisms [0.9091225937132784]
  We reveal a critical control-plane attack surface to traditional data-plane vulnerabilities. We introduce Constrained Decoding Attack, a novel jailbreak class that weaponizes structured output constraints to bypass safety mechanisms. Our findings identify a critical security blind spot in current LLM architectures and urge a paradigm shift in LLM safety to address control-plane vulnerabilities.
  arXiv  Detail & Related papers  (2025-03-31T15:08:06Z)
• EM-MIAs: Enhancing Membership Inference Attacks in Large Language Models through Ensemble Modeling [2.494935495983421]
  This paper proposes a novel ensemble attack method that integrates several existing MIAs techniques into an XGBoost-based model to enhance overall attack performance (EM-MIAs) Experimental results demonstrate that the ensemble model significantly improves both AUC-ROC and accuracy compared to individual attack methods across various large language models and datasets.
  arXiv  Detail & Related papers  (2024-12-23T03:47:54Z)
• Imprompter: Tricking LLM Agents into Improper Tool Use [35.255462653237885]
  Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. We contribute to the security foundations of agent-based systems and surface a new class of automatically computed obfuscated adversarial prompt attacks.
  arXiv  Detail & Related papers  (2024-10-19T01:00:57Z)
• "Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models [74.05368440735468]
  Retrieval-Augmented Generative (RAG) models enhance Large Language Models (LLMs) In this paper, we demonstrate a security threat where adversaries can exploit the openness of these knowledge bases.
  arXiv  Detail & Related papers  (2024-06-26T05:36:23Z)
• Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning [61.2224355547598]
  Open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. Our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions.
  arXiv  Detail & Related papers  (2024-04-16T13:22:54Z)
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models [112.48136829374741]
  In this paper, we unveil a new vulnerability: the privacy backdoor attack. When a victim fine-tunes a backdoored model, their training data will be leaked at a significantly higher rate than if they had fine-tuned a typical model. Our findings highlight a critical privacy concern within the machine learning community and call for a reevaluation of safety protocols in the use of open-source pre-trained models.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks [65.21536453075275]
  We focus on the summarization task and investigate the membership inference (MI) attack. We exploit text similarity and the model's resistance to document modifications as potential MI signals. We discuss several safeguards for training summarization models to protect against MI attacks and discuss the inherent trade-off between privacy and utility.
  arXiv  Detail & Related papers  (2023-10-20T05:44:39Z)
• A Blackbox Model Is All You Need to Breach Privacy: Smart Grid Forecasting Models as a Use Case [0.7714988183435832]
  We show that a black box access to an LSTM model can reveal a significant amount of information equivalent to having access to the data itself. This highlights the importance of protecting forecasting models at the same level as the data.
  arXiv  Detail & Related papers  (2023-09-04T11:07:37Z)
• On the Evaluation of User Privacy in Deep Neural Networks using Timing Side Channel [14.350301915592027]
  We identify and report a novel data-dependent timing side-channel leakage (termed Class Leakage) in Deep Learning (DL) implementations. We demonstrate a practical inference-time attack where an adversary with user privilege and hard-label blackbox access to an ML can exploit Class Leakage. We develop an easy-to-implement countermeasure by making a constant-time branching operation that alleviates the Class Leakage.
  arXiv  Detail & Related papers  (2022-08-01T19:38:16Z)
• ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models [64.03398193325572]
  Inference attacks against Machine Learning (ML) models allow adversaries to learn about training data, model parameters, etc. We concentrate on four attacks - namely, membership inference, model inversion, attribute inference, and model stealing. Our analysis relies on a modular re-usable software, ML-Doctor, which enables ML model owners to assess the risks of deploying their models.
  arXiv  Detail & Related papers  (2021-02-04T11:35:13Z)
• Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses [150.64470864162556]
  This work systematically categorizes and discusses a wide range of dataset vulnerabilities and exploits. In addition to describing various poisoning and backdoor threat models and the relationships among them, we develop their unified taxonomy.
  arXiv  Detail & Related papers  (2020-12-18T22:38:47Z)
• Risk Management Framework for Machine Learning Security [7.678455181587705]
  Adversarial attacks for machine learning models have become a highly studied topic both in academia and industry. In this paper, we outline a novel framework to guide the risk management process for organizations reliant on machine learning models.
  arXiv  Detail & Related papers  (2020-12-09T06:21:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.