Hasso-Plattner-Institut25 Jahre HPI
Hasso-Plattner-Institut25 Jahre HPI

From fairness to cyberbiosecurity: accountability in machine learning for biology and medicine (Wintersemester 2022/2023)

Dozent: Prof. Dr. Bernhard Renard (Data Analytics and Computational Statistics) , Dr. Jakub Maciej Bartoszewicz (Data Analytics and Computational Statistics) , Marta Stefania Lemanczyk (Data Analytics and Computational Statistics) , Melania Maria Nowicka (Data Analytics and Computational Statistics)

Allgemeine Information

  • Semesterwochenstunden: 2
  • ECTS: 3
  • Benotet: Ja
  • Einschreibefrist: 01.10.2022 - 31.10.2022
  • Prüfungszeitpunkt §9 (4) BAMA-O: 14.11.2022
  • Lehrform: Seminar
  • Belegungsart: Wahlpflichtmodul
  • Lehrsprache: Englisch
  • Maximale Teilnehmerzahl: 6

Studiengänge, Modulgruppen & Module

IT-Systems Engineering MA
Data Engineering MA
Digital Health MA
  • SCAD: Scalable Computing and Algorithms for Digital Health
    • HPI-SCAD-C Concepts and Methods
  • SCAD: Scalable Computing and Algorithms for Digital Health
    • HPI-SCAD-T Technologies and Tools
  • SCAD: Scalable Computing and Algorithms for Digital Health
    • HPI-SCAD-S Specialization
  • APAD: Acquisition, Processing and Analysis of Health Data
    • HPI-APAD-C Concepts and Methods
  • APAD: Acquisition, Processing and Analysis of Health Data
    • HPI-APAD-T Technologies and Tools
  • APAD: Acquisition, Processing and Analysis of Health Data
    • HPI-APAD-S Specialization
Cybersecurity MA
Software Systems Engineering MA


Adoption of AI in biology and medicine offers great potential, but is also associated with unique risks and challenges. In this seminar, we will discuss different perspectives on accountability and ethical issues related to deployment of machine learning models for health and biotech. We will cover a wide array of different applications ranging from biomedical research to molecular design, and analyze both their promises and associated risks. First, we will focus on the problems of algorithmic biases, fairness and privacy, stressing both the connections to more general issues in AI ethics and the specific characteristics of health-related data and models. Further, we will touch on AI (bio)safety and cyberbiosecurity, discussing how the convergence of machine learning, biotechnology and computational biology could lead to both scientific breakthroughs and potential emergence of new threats.

Learning objectives:

  • You learn to identify open challenges in accountability of AI for health, AI (bio)safety, and cyberbiosecurity
  • You learn to critically read scientific literature and identify dual-use research, potential risks, and ethical issues
  • You learn about good scientific practice and ethical research
  • You can present a scientific manuscript in this field and lead a discussion


Biological background is not necessary to participate in the seminar, but you will need at least a basic understanding of machine learning. Good English skills are required to understand and discuss current literature.


  1. Cirillo et al., Sex and gender differences and biases in artificial intelligence for biomedicine and healthcare , npj Digital Medicine, 2020 https://www.nature.com/articles/s41746-020-0288-5
  2. Norori et al., Addressing bias in big data and AI for health care: A call for open science, Cell Patterns, 2022 https://doi.org/10.1016/j.patter.2021.100347
  3. Kaissis et al., Secure, privacy-preserving and federated machine learning in medical imaging, Nat Mach Intell, 2020, https://www.nature.com/articles/s42256-020-0186-1
  4. Urbina et al., Dual use of artificial-intelligence-powered drug discovery, Nat Mach Intell, 2022 https://www.nature.com/articles/s42256-022-00465-9
  5. Smith & Sandbrink, Biosecurity in an age of open science, PLoS Biology, 2022, https://journals.plos.org/plosbiology/article?id=10.1371/journal.pbio.3001600
  6. Sandbrink et al., Mitigating Biosecurity Challenges of Wildlife Virus Discovery, Preprint, 2022, https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4035760
  7. O'Brien & Nelson, Assessing the Risks Posed by the Convergence of Artificial Intelligence and Biotechnology, Health Security, 2020, https://www.liebertpub.com/doi/full/10.1089/hs.2019.0122
  8. Esvelt, Pandemic virus prediction and the proliferation of accessible weapons of mass destruction, Congressional testimony, 2021, https://docs.house.gov/meetings/FA/FA05/20211208/114290/HHRG-117-FA05-Wstate-EsveltK-20211208.pdf

Lern- und Lehrformen

  • Seminar for master's students
  • Language of instruction: English
  • Maximum number of participants: 6

Meetings will take place in room K-1.03. Topics will be presented in the first session (24.10.2022). For topic assignments, participants will have to write an e-mail by Oct 31st, 2022, in which they can give preferences for up to three of the presented topics. Then, the topics will be assigned by us. As first talks will be scheduled on Nov 14th, Nov 7th will be the last time point to de-register from the class.

The seminar will be conducted on-site (with a hybrid option if needed). Please register in the moodle of the course for further information.


In the seminar, each participant will give a presentation about a predefined topic within the research area and write a short report. The final grade consists of the following two parts:

  • Presentation and discussion (65%)
  • Written report (35%)


Kick-Off meeting will be on 24.10.2022, from 11:00 - 12:30. As first talks will be scheduled on Nov 14th, Nov 7th will be the last time point to de-register from the class.