News

We cordially invite you to a public lecture held as part of the habilitation procedure of Mgr. Kamil Malinka, Ph.D., Protection mechanisms against deepfake-based attacks. The lecture will take place on June 12, 2025, at 2 p.m. in room G108.

The habilitation thesis follows up on Kamil Malinka's long-term research activities, which he also develops within the Security@FIT research group. The author focuses on the broader context of cybersecurity in the field of artificial intelligence. His professional interest is not limited to technical solutions themselves – he is also interested in user behavior when using selected security tools, the education of future IT professionals, and the impact of deepfakes on voice and facial biometrics. As he himself points out, an essential and somewhat neglected aspect of the problem is understanding how users work with security tools. A key part of his habilitation thesis is the design of a detection mechanism for voice deepfakes based on spectrogram analysis. Finally, the thesis focuses on the problem of comparing detectors, proposing a detailed framework for evaluating and comparing voice deepfake detectors by evaluating 40 state-of-the-art.

Abstract of the lecture: 

First, we will briefly introduce the issue of deepfakes and its security implications. To better understand the problem, we will present the deepfake use lifecycle and illustrate applications of protection mechanisms on top of it. Most of the discussion that has been devoted to protection mechanisms has focused on deepfake detection. The disadvantage of this approach is that if detection fails, no other protection is standing in the way of a successful attack. Detection is thus an important part of building protection, but it is not the only option. First, we will discuss various protection methods such as watermarking, legal regulations, methods for obstructing deepfake creation, forensics analysis, and methods ensuring proof. In the area of deepfake face and voice detection methods, we will summarize current approaches: detection based on artifact detection, deep learning, or based on physiological features such as eye blinking. Next, we will present and evaluate the design of our detection mechanism for voice deepfakes based on spectrogram analysis. Finally, we will focus on the problem of a detector comparison. We will propose a detailed framework for evaluating and comparing deepfake speech detectors. To showcase our framework's usage and its benefits, we then used this framework to evaluate 40 state-of-the-art deepfake speech detectors. We will demonstrate the results of extensive experiments, where we extended common approaches by testing for previously unobserved forms of manipulated speech.

You can join the lecture via MS Teams, link to the meeting HERE.

Thinking about pursuing a Ph.D. at FIT and need more information? Join us on April 8 in lecture hall D 206 where a presentation about the Ph.D. by Professor Sekanina will be given at 3 pm. This will be followed by a discussion with academics, whom you can ask about anything you are interested in regarding PhD studies.

Information about doctoral studies can also be found on the website. An overview of the dissertation topics is available here. And a reminder, the deadline for applications (Round 1) is 30 May.

The 10th anniversary edition of HiVisComp brought together an informal and inspiring gathering of computer graphics, image processing and computer vision experts. The conference was founded in 2014 by Martin Čadík (FIT BUT) and Jaroslav Křivánek (MFF UK). Since then, the event has come a long way and grown significantly. Over the years, it has featured 30 invited speakers from 13 countries, presented 121 technical papers and received almost 1000 abstracts. Today, Martin Čadík organizes it with the help of colleagues from CTU.

HiVisComp was held this year in the Krkonoše Mountains from 29 January to 1 February and once again combined scientific lectures, exchange of experiences and sporting activities. In the current edition, participants discussed the latest developments in data visualisation, lighting simulation or innovative image processing methods. Among the highlights of the programme were the invited lectures, featuring, for example, Gabriela Csurka from NAVER LABS Europe, who presented the evolution from the CroCo model to the DUSt3R and MASt3R, which have brought a major shift in the field of 3D computer vision. She showed how these methods unify and simplify the processing of 3D visual data and open up new possibilities for tasks such as visual localization without a map or robotic navigation.

Torsten Sattler from CTU presented the 3D Gaussian Splatting method, which enables faster and higher quality 3D scene reconstruction compared to traditional approaches. He focused on artifact resolution, working with different lighting conditions and extracting accurate 3D models.

Marc Alexa from TU Berlin presented a new approach to fitting lines to planes and related problems. His method is computationally efficient, easy to implement and preserves important geometric properties.

As part of the research team presentation, Adam Herout from FIT BUT presented The Malleable Glyph Challenge.

Outdoor and social activities are an integral part of this conference. This year, they were in the spirit of cross-country skiing and skiing. The full conference programme can be viewed on hiviscomp.cz.