Marija Ivanovska
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Marija Ivanovska has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Vitomir Štruc
Faculty of Electrical Engineering, University of Ljubljana, Ljubljana, Slovenia
7 shared publications - Janez Perš
Faculty of Electrical Engineering University of Ljubljana
2 shared publications Jakob Kreft
1 shared publication- Leon Todorov1 shared publication
Lindita Ahmeti
Identities: Journal for Politics, Gender and Culture
1 shared publication- Marjan Stoimchev
Department of Knowledge Technologies, Joef Stefan Institute, Ljubljana, Slovenia
1 shared publication
Latest Publications
- Open Access
Emergent Morphing Attack Detection in Open Multi-modal Large Language Models
Face morphing attacks threaten biometric verification, yet most morphing attack detection (MAD) systems require task-specific training and generalize poorly to unseen attack types. Meanwhile, open-source multimodal large language models (MLLMs) have demonstrated strong visual-linguistic reasoning, but their potential in biometric forensics remains underexplored. In this paper, we present the first systematic zero-shot evaluation of open-source MLLMs for single-image MAD, using publicly available weights and a standardized, reproducible protocol. Across diverse morphing techniques, many MLLMs show non-trivial discriminative ability without any fine-tuning or domain adaptation, and LLaVA1.6-Mistral-7B achieves state-of-the-art performance, surpassing highly competitive task-specific MAD baselines by at least 23% in terms of equal error rate (EER). The results indicate that multimodal pretraining can implicitly encode fine-grained facial inconsistencies indicative of morphing artifacts, enabling zero-shot forensic sensitivity. Our findings position open-source MLLMs as reproducible, interpretable, and competitive foundations for biometric security and forensic image analysis. This emergent capability also highlights new opportunities to develop state-of-the-art MAD systems through targeted fine-tuning or lightweight adaptation, further improving accuracy and efficiency while preserving interpretability. To support future research, all code and evaluation protocols will be released upon publication.
Open AccessEmergent Morphing Attack Detection in Open Multi-modal Large Language Models
Face morphing attacks threaten biometric verification, yet most morphing attack detection (MAD) systems require task-specific training and generalize poorly to unseen attack types. Meanwhile, open-source multimodal large language models (MLLMs) have demonstrated strong visual-linguistic reasoning, but their potential in biometric forensics remains underexplored. In this paper, we present the first systematic zero-shot evaluation of open-source MLLMs for single-image MAD, using publicly available weights and a standardized, reproducible protocol. Across diverse morphing techniques, many MLLMs show non-trivial discriminative ability without any fine-tuning or domain adaptation, and LLaVA1.6-Mistral-7B achieves state-of-the-art performance, surpassing highly competitive task-specific MAD baselines by at least 23% in terms of equal error rate (EER). The results indicate that multimodal pretraining can implicitly encode fine-grained facial inconsistencies indicative of morphing artifacts, enabling zero-shot forensic sensitivity. Our findings position open-source MLLMs as reproducible, interpretable, and competitive foundations for biometric security and forensic image analysis. This emergent capability also highlights new opportunities to develop state-of-the-art MAD systems through targeted fine-tuning or lightweight adaptation, further improving accuracy and efficiency while preserving interpretability. To support future research, all code and evaluation protocols will be released upon publication.
- Open Access
- 16 November 2025
- Published by Elsevier in Information Fusion
- Vol. 127
SelfMAD++: Self-supervised foundation model with local feature enhancement for generalized morphing attack detection
- 16 November 2025
- Published by Elsevier in Information Fusion
- Vol. 127
Open AccessSelfMAD++: Self-supervised foundation model with local feature enhancement for generalized morphing attack detection
- Open Access
- 1 October 2025
- Published by Elsevier in Journal of Systems Architecture
- Vol. 169
Privacy-by-design AIoT vision for intelligent urban environments
- 1 October 2025
- Published by Elsevier in Journal of Systems Architecture
- Vol. 169
Open AccessPrivacy-by-design AIoT vision for intelligent urban environments
- Open Access
- 7 February 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 248
Y-GAN: Learning dual data representations for anomaly detection in images
- 7 February 2024
- Published by Elsevier in Expert Systems with Applications
- Vol. 248
Open AccessY-GAN: Learning dual data representations for anomaly detection in images
- Open Access
On the Vulnerability of DeepFake Detectors to Attacks Generated by Denoising Diffusion Models
The detection of malicious deepfakes is a constantly evolving problem that requires continuous monitoring of detectors to ensure they can detect image manipulations generated by the latest emerging models. In this paper, we investigate the vulnerability of single-image deepfake detectors to black-box attacks created by the newest generation of generative methods, namely Denoising Diffusion Models (DDMs). Our experiments are run on FaceForensics++, a widely used deepfake benchmark consisting of manipulated images generated with various techniques for face identity swapping and face reenactment. Attacks are crafted through guided reconstruction of existing deepfakes with a proposed DDM approach for face restoration. Our findings indicate that employing just a single denoising diffusion step in the reconstruction process of a deepfake can significantly reduce the likelihood of detection, all without introducing any perceptible image modifications. While training detectors using attack examples demonstrated some effectiveness, it was observed that discriminators trained on fully diffusion-based deepfakes exhibited limited generalizability when presented with our attacks.
Open AccessOn the Vulnerability of DeepFake Detectors to Attacks Generated by Denoising Diffusion Models
The detection of malicious deepfakes is a constantly evolving problem that requires continuous monitoring of detectors to ensure they can detect image manipulations generated by the latest emerging models. In this paper, we investigate the vulnerability of single-image deepfake detectors to black-box attacks created by the newest generation of generative methods, namely Denoising Diffusion Models (DDMs). Our experiments are run on FaceForensics++, a widely used deepfake benchmark consisting of manipulated images generated with various techniques for face identity swapping and face reenactment. Attacks are crafted through guided reconstruction of existing deepfakes with a proposed DDM approach for face restoration. Our findings indicate that employing just a single denoising diffusion step in the reconstruction process of a deepfake can significantly reduce the likelihood of detection, all without introducing any perceptible image modifications. While training detectors using attack examples demonstrated some effectiveness, it was observed that discriminators trained on fully diffusion-based deepfakes exhibited limited generalizability when presented with our attacks.
- Open Access
TomatoDIFF: On-plant Tomato Segmentation with Denoising Diffusion Models
Artificial intelligence applications enable farmers to optimize crop growth and production while reducing costs and environmental impact. Computer vision-based algorithms in particular, are commonly used for fruit segmentation, enabling in-depth analysis of the harvest quality and accurate yield estimation. In this paper, we propose TomatoDIFF, a novel diffusion-based model for semantic segmentation of on-plant tomatoes. When evaluated against other competitive methods, our model demonstrates state-of-the-art (SOTA) performance, even in challenging environments with highly occluded fruits. Additionally, we introduce Tomatopia, a new, large and challenging dataset of greenhouse tomatoes. The dataset comprises high-resolution RGB-D images and pixel-level annotations of the fruits.
Open AccessTomatoDIFF: On-plant Tomato Segmentation with Denoising Diffusion Models
Artificial intelligence applications enable farmers to optimize crop growth and production while reducing costs and environmental impact. Computer vision-based algorithms in particular, are commonly used for fruit segmentation, enabling in-depth analysis of the harvest quality and accurate yield estimation. In this paper, we propose TomatoDIFF, a novel diffusion-based model for semantic segmentation of on-plant tomatoes. When evaluated against other competitive methods, our model demonstrates state-of-the-art (SOTA) performance, even in challenging environments with highly occluded fruits. Additionally, we introduce Tomatopia, a new, large and challenging dataset of greenhouse tomatoes. The dataset comprises high-resolution RGB-D images and pixel-level annotations of the fruits.
- Open Access
Learning to Combine Local and Global Image Information for Contactless Palmprint Recognition
In the past few years, there has been a leap from traditional palmprint recognition methodologies, which use handcrafted features, to deep-learning approaches that are able to automatically learn feature representations from the input data. However, the information that is extracted from such deep-learning models typically corresponds to the global image appearance, where only the most discriminative cues from the input image are considered. This characteristic is especially problematic when data is acquired in unconstrained settings, as in the case of contactless palmprint recognition systems, where visual artifacts caused by elastic deformations of the palmar surface are typically present in spatially local parts of the captured images. In this study we address the problem of elastic deformations by introducing a new approach to contactless palmprint recognition based on a novel CNN model, designed as a two-path architecture, where one path processes the input in a holistic manner, while the second path extracts local information from smaller image patches sampled from the input image. As elastic deformations can be assumed to most significantly affect the global appearance, while having a lesser impact on spatially local image areas, the local processing path addresses the issues related to elastic deformations thereby supplementing the information from the global processing path. The model is trained with a learning objective that combines the Additive Angular Margin (ArcFace) Loss and the well-known center loss. By using the proposed model design, the discriminative power of the learned image representation is significantly enhanced compared to standard holistic models, which, as we show in the experimental section, leads to state-of-the-art performance for contactless palmprint recognition. Our approach is tested on two publicly available contactless palmprint datasets—namely, IITD and CASIA—and is demonstrated to perform favorably against state-of-the-art methods from the literature. The source code for the proposed model is made publicly available.
Open AccessLearning to Combine Local and Global Image Information for Contactless Palmprint Recognition
In the past few years, there has been a leap from traditional palmprint recognition methodologies, which use handcrafted features, to deep-learning approaches that are able to automatically learn feature representations from the input data. However, the information that is extracted from such deep-learning models typically corresponds to the global image appearance, where only the most discriminative cues from the input image are considered. This characteristic is especially problematic when data is acquired in unconstrained settings, as in the case of contactless palmprint recognition systems, where visual artifacts caused by elastic deformations of the palmar surface are typically present in spatially local parts of the captured images. In this study we address the problem of elastic deformations by introducing a new approach to contactless palmprint recognition based on a novel CNN model, designed as a two-path architecture, where one path processes the input in a holistic manner, while the second path extracts local information from smaller image patches sampled from the input image. As elastic deformations can be assumed to most significantly affect the global appearance, while having a lesser impact on spatially local image areas, the local processing path addresses the issues related to elastic deformations thereby supplementing the information from the global processing path. The model is trained with a learning objective that combines the Additive Angular Margin (ArcFace) Loss and the well-known center loss. By using the proposed model design, the discriminative power of the learned image representation is significantly enhanced compared to standard holistic models, which, as we show in the experimental section, leads to state-of-the-art performance for contactless palmprint recognition. Our approach is tested on two publicly available contactless palmprint datasets—namely, IITD and CASIA—and is demonstrated to perform favorably against state-of-the-art methods from the literature. The source code for the proposed model is made publicly available.
- Open Access
- 1 June 2002
- Published by Institute of Social Sciences and Humanities, Skopje in Identities: Journal for Politics, Gender and Culture
- Vol. 1 (3) , 199-200
Кон Nancy Tuana et al. (Ed.), Revealing Male Bodies
Author(s): Marija Ivanovska | Марија Ивановска Title (Macedonian): Кон Nancy Tuana et al. (Ed.), Revealing Male Bodies Title (Albanian): Për Nancy Tuana et al. (Ed.), Revealing Male Bodies Translated by (Macedonian to Albanian): Lindita Ahmeti Journal Reference: Identities: Journal for Politics, Gender and Culture, Vol. 1, No. 3 (Summer 2002) Publisher: Research Center in Gender Studies - Skopje and Euro-Balkan Institute Page Range: 199-200 Page Count: 2 Citation (Macedonian): Марија Ивановска, „Кон Nancy Tuana et al. (Ed.), Revealing Male Bodies“, Идентитети: списание за политика, род и култура, т. 1, бр. 3 (лето 2002): 199-200. Citation (Albanian): Marija Ivanovska, „Për Nancy Tuana et al. (Ed.), Revealing Male Bodies“, përkthim nga Maqedonishtja Lindita Ahmeti, Identities: Journal for Politics, Gender and Culture, Vol. 1, No. 3 (Summer 2002): 199-200.
- 1 June 2002
- Published by Institute of Social Sciences and Humanities, Skopje in Identities: Journal for Politics, Gender and Culture
- Vol. 1 (3) , 199-200
Open AccessКон Nancy Tuana et al. (Ed.), Revealing Male Bodies
Author(s): Marija Ivanovska | Марија Ивановска Title (Macedonian): Кон Nancy Tuana et al. (Ed.), Revealing Male Bodies Title (Albanian): Për Nancy Tuana et al. (Ed.), Revealing Male Bodies Translated by (Macedonian to Albanian): Lindita Ahmeti Journal Reference: Identities: Journal for Politics, Gender and Culture, Vol. 1, No. 3 (Summer 2002) Publisher: Research Center in Gender Studies - Skopje and Euro-Balkan Institute Page Range: 199-200 Page Count: 2 Citation (Macedonian): Марија Ивановска, „Кон Nancy Tuana et al. (Ed.), Revealing Male Bodies“, Идентитети: списание за политика, род и култура, т. 1, бр. 3 (лето 2002): 199-200. Citation (Albanian): Marija Ivanovska, „Për Nancy Tuana et al. (Ed.), Revealing Male Bodies“, përkthim nga Maqedonishtja Lindita Ahmeti, Identities: Journal for Politics, Gender and Culture, Vol. 1, No. 3 (Summer 2002): 199-200.