arXiv subjects

Bernhard Bauer

Publications and source records attributed to Bernhard Bauer.

5 recordsLinked to original sources

arXiv2025

METRION: A Framework for Accurate Software Energy Measurement

The Information and Communication Technology sector accounted for approximately 1.4% of global greenhouse gas emissions and 4% of the world's electricity consumption in 2020, with both expected to rise. To reduce this environmental impact, optimization strategies are employed to reduce energy consumption at the IT infrastructure and application levels. However, effective optimization requires, firstly, the identification of major energy consumers and, secondly, the ability to quantify whether an optimization has achieved the intended energy savings. Accurate determination of application-level energy consumption is thus essential. Therefore, we introduce an energy attribution model that quantifies the energy consumption of applications on CPU and DRAM at the thread level, considering the influence of Simultaneous Multithreading, frequency scaling, multi-socket architectures, and Non-Uniform Memory Access. To ensure cross-platform applicability, we integrate the proposed model into an extensible framework, METRION, including a platform-independent data model and an initial implementation for Linux systems using Intel CPUs. We evaluate METRION across three different workloads and demonstrate that the energy attribution model can accurately capture the CPU energy consumption of applications targeting solely the CPU with a Mean Absolute Percentage Error of 4.2%, and the DRAM energy consumption of applications targeting DRAM with an 16.1% error.

cs.SE↗

arXiv2025

Exploiting Web Search Tools of AI Agents for Data Exfiltration

Large language models (LLMs) are now routinely used to autonomously execute complex tasks, from natural language processing to dynamic workflows like web searches. 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. As LLMs increasingly interact with external data sources, indirect prompt injection emerges as a critical and evolving attack vector, enabling adversaries to exploit models through manipulated inputs. Through a systematic evaluation of indirect prompt injection attacks across diverse models, we analyze how susceptible current LLMs are to such attacks, which parameters, including model size and manufacturer, specific implementations, shape their vulnerability, and which attack methods remain most effective. Our results reveal that even well-known attack patterns continue to succeed, exposing persistent weaknesses in model defenses. To address these vulnerabilities, we emphasize the need for strengthened training procedures to enhance inherent resilience, a centralized database of known attack vectors to enable proactive defense, and a unified testing framework to ensure continuous security validation. These steps are essential to push developers toward integrating security into the core design of LLMs, as our findings show that current models still fail to mitigate long-standing threats.

cs.CR↗

arXiv2025

MQG4AI Towards Responsible High-risk AI -- Illustrated for Transparency Focusing on Explainability Techniques

As artificial intelligence (AI) systems become increasingly integrated into critical domains, ensuring their responsible design and continuous development is imperative. Effective AI quality management (QM) requires tools and methodologies that address the complexities of the AI lifecycle. In this paper, we propose an approach for AI lifecycle planning that bridges the gap between generic guidelines and use case-specific requirements (MQG4AI). Our work aims to contribute to the development of practical tools for implementing Responsible AI (RAI) by aligning lifecycle planning with technical, ethical and regulatory demands. Central to our approach is the introduction of a flexible and customizable Methodology based on Quality Gates, whose building blocks incorporate RAI knowledge through information linking along the AI lifecycle in a continuous manner, addressing AIs evolutionary character. For our present contribution, we put a particular emphasis on the Explanation stage during model development, and illustrate how to align a guideline to evaluate the quality of explanations with MQG4AI, contributing to overall Transparency.

cs.CY↗

arXiv2023

Towards Democratizing AI: A Comparative Analysis of AI as a Service Platforms and the Open Space for Machine Learning Approach

Recent AI research has significantly reduced the barriers to apply AI, but the process of setting up the necessary tools and frameworks can still be a challenge. While AI-as-a-Service platforms have emerged to simplify the training and deployment of AI models, they still fall short of achieving true democratization of AI. In this paper, we aim to address this gap by comparing several popular AI-as-a-Service platforms and identifying the key requirements for a platform that can achieve true democratization of AI. Our analysis highlights the need for self-hosting options, high scalability, and openness. To address these requirements, we propose our approach: the "Open Space for Machine Learning" platform. Our platform is built on cutting-edge technologies such as Kubernetes, Kubeflow Pipelines, and Ludwig, enabling us to overcome the challenges of democratizing AI. We argue that our approach is more comprehensive and effective in meeting the requirements of democratizing AI than existing AI-as-a-Service platforms.

cs.LG↗

arXiv2023

Towards Automated COVID-19 Presence and Severity Classification

COVID-19 presence classification and severity prediction via (3D) thorax computed tomography scans have become important tasks in recent times. Especially for capacity planning of intensive care units, predicting the future severity of a COVID-19 patient is crucial. The presented approach follows state-of-theart techniques to aid medical professionals in these situations. It comprises an ensemble learning strategy via 5-fold cross-validation that includes transfer learning and combines pre-trained 3D-versions of ResNet34 and DenseNet121 for COVID19 classification and severity prediction respectively. Further, domain-specific preprocessing was applied to optimize model performance. In addition, medical information like the infection-lung-ratio, patient age, and sex were included. The presented model achieves an AUC of 79.0% to predict COVID-19 severity, and 83.7% AUC to classify the presence of an infection, which is comparable with other currently popular methods. This approach is implemented using the AUCMEDI framework and relies on well-known network architectures to ensure robustness and reproducibility.

eess.IV↗