Dr. Nora Hofer
Research Assistant

E-mailnora.hofer@uibk.ac.at
Phone+43 512 507-53217
AddressTechnikerstraße 21A, 6020 Innsbruck, Austria
OfficeICT 3N03
Dr. Nora Hofer

Note

I am currently reaching out to law enforcement agencies in order to find experts for a study on developments in digital imaging technologies. If you have received such a request and would like to verify whether it is authentic, please contact me via the channels on this website.

Research Interests

  • Digital forensics
  • Steganography and steganalysis
  • Machine learning in adversarial environments

Positions

since 07/2021 Research Assistant, Department of Computer Science, University of Innsbruck, Austria
04/2021 – 06/2021 Student Assistant, Department of Computer Science, University of Innsbruck, Austria
2019 – 2021 Software Developer, Otera Intelligent NLU GmbH (previously DeepOpinion), Innsbruck, Austria
2015 – 2019 Technical Staff, SPEED-U-UP GmbH, Innsbruck, Austria

Education

2024 – 2026 Ph.D. studies in Computer Science, University of Innsbruck, Austria
2020 – 2024 Supplementary studies in Computer Science, University of Innsbruck, Austria
2018 – 2020 M.A. studies in Management, Communication & IT, Management Center Innsbruck, Austria
2017 – 2018 ERASMUS+ exchange, University of Ljubljana, Slovenia
2015 – 2018 B.A. studies in Management, Communication & IT, Management Center Innsbruck, Austria

Publications

  • Hofer, N. The Role of Lossy Compression in Digital Image Forensics. 2026. [PDF]
  • Hofer, N. and Böhme, R. When the Codec Hallucinates: User Perceptions of Miscompressed Images. In Conference on Human Factors in Computing Systems (ACM CHI). ACM, Barcelona, Spain, 2026. [PDF] [Publisher] [Data]
  • Hofer, N. and Böhme, R. Challenging Cases of Neural Image Compression: A Dataset of Visually Compelling Yet Semantically Incorrect Reconstructions. In ACM International Conference on Multimedia (MM). ACM, Dublin, Ireland, 2025, pp. 13318–13324. [PDF] [Publisher] [Data] [Video]
  • Hofer, N. and Böhme, R. A Taxonomy of Miscompressions: Preparing Image Forensics for Neural Compression. In IEEE International Workshop on Information Forensics and Security (WIFS). IEEE, Rome, Italy, 2024, pp. 1–6. [PDF] [Publisher]
  • Hofer, N. Increasing Trust in Image Analysis by Detecting Trellis Quantization in JPEG Images. In IEEE International Conference on Image Processing (ICIP). IEEE, Abu Dhabi, UAE, 2024, pp. 3834–3840. [PDF] [Publisher]
  • Schlögl, A., Hofer, N., and Böhme, R. Causes and Effects of Unanticipated Numerical Deviations in Neural Network Inference Frameworks. In Conference on Neural Information Processing Systems (NeurIPS). New Orleans, LA, 2023. [PDF] [Publisher] [Video]
  • Hofer, N. and Böhme, R. Progressive JPEGs in the Wild: Implications for Information Hiding and Forensics. In Proceedings of the 11th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSEC). ACM, Chicago, IL, 2023, pp. 47–58. [PDF] [Publisher] [Video]
  • Beneš, M., Hofer, N., and Böhme, R. The Effect of the JPEG Implementation on the Cover–Source Mismatch Error in Image Steganalysis. In Proceedings of the 30th European Signal Processing Conference (EUSIPCO). EURASIP, Belgrade, Serbia, 2022, pp. 1057–1061. [PDF] [Publisher] [Video]
  • Beneš, M., Hofer, N., and Böhme, R. Know Your Library: How the libjpeg Version Influences Compression and Decompression Results. In Proceedings of the 10th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSEC). ACM, 2022, pp. 19–25. [PDF] [Publisher]
  • Hofer, N., Schöttle, P., Rietzler, A., and Stabinger, S. Adversarial Examples Against a BERT ABSA Model – Fooling Bert With L33T, Misspellign, and Punctuation, In International Conference on Availability, Reliability and Security (ARES). 2021. [Publisher] [Video]

Awards

Grants

Talks

  • Guest lecture on Neural Forensics – Reproducibility and Trustworthiness of ML in Forensic Settings at the University of Florence in April 2026, Florence, Italy.
  • Guest lecture on When the Codec Hallucinates – Pitfalls for Modern Image Compression for Multimedia Data Security at the University of Trento in December 2025, Trento, Italy.
  • Poster presentation on Current Research: Semantic Changes in Learning Based Image Compression at the IEEE EURASIP Summer School on Signal Processing (S3P-2025) in September 2025, San Vincenzo, Italy.
  • Poster presentation on Unanticipated Numerical Deviations in Neural Network Inference Frameworks at the Austrian Computer Science Day in June 2025, Innsbruck, Austria.
  • Invited talk on Progressive JPEGs in the Wild: Implications for Information Hiding and Forensics at the SPS-IFS (Information Forensics and Security Technical Committee) Webinar in November 2023, online.
  • Invited talk Social Network Identification Using Progressive JPEG Scan Scripts at the ENFSI Digital Imaging Working Group Meeting in October 2023, Prague Czech Republic.

Projects