266 citations · 278 across the 19 of their papers we have counts for
21 papers
Not All Challenges Are Equal: Evaluating Interactive Liveness Detection Against Real-Time Face Swaps
Anton Firc, David Drtil, Martin Perešíni +3
Remote identity verification assumes that a camera stream shows a live person, yet public real-time face-swap tools can replace that person before the stream reaches the verifier.…
QBFF: Deep Quantum Bottleneck for Automatic Speaker Verification Anti-Spoofing
Anton Firc, Nouhaila Innan, Vojtěch Staněk +6
A central goal of quantum machine learning is to identify applications in which small quantum circuits can improve task performance while remaining executable on real hardware. We…
AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks
Jakub Reš, Petr Kaška, Martin Perešíni +2
Large language models (LLMs) are vulnerable to jailbreak attacks that bypass safety alignment through carefully crafted prompts. Many existing defenses require access to model weig…
Tracking the Trend in How Speech Synthesizers Deceive People
Milan Šalko, Anton Firc, Kamil Malinka +4
Advances in speech synthesis have made deepfake audio highly realistic. Earlier studies reported 70-80% human detection accuracy, but relied primarily on older synthesizers. We com…
SpAArSIST: Sparsified AASIST for Efficient and Reliable Anti-Spoofing
Anton Firc, Vojtěch Staněk, Zbyněk Lička +2
We present SpAArSIST, a deployment-oriented refinement of the widely used AASIST graph pooling backend for self-supervised learning (SSL) based anti-spoofing. Motivated by redundan…
What Do Deepfake Speech Detectors Actually Hear?
Vojtěch Staněk, Veronika Jirmusová, Anton Firc +3
Deepfake speech detectors often output a single score without explaining why an audio sample is flagged, where in the signal the evidence lies, or what cues drive the decision. We…
Evolutionary Multi-Objective Fusion of Deepfake Speech Detectors
Vojtěch Staněk, Martin Perešíni, Lukáš Sekanina +2
While deepfake speech detectors built on large self-supervised learning (SSL) models achieve high accuracy, employing standard ensemble fusion to further enhance robustness often r…
Selfish Mining in Multi-Attacker Scenarios: An Empirical Evaluation of Nakamoto, Fruitchain, and Strongchain
Martin Perešíni, Tomáš Hladký, Jakub Kubík +1
The aim of this work is to enhance blockchain security by deepening the understanding of selfish mining attacks in various consensus protocols, especially the ones that have the po…
PoS-CoPOR: Proof-of-Stake Consensus Protocol with Native Onion Routing Providing Scalability and DoS-Resistance
Ivan Homoliak, Martin Perešíni, Marek Tamaškovič +3
Proof-of-Stake (PoS) consensus protocols often face a trade-off between performance and security. Protocols that pre-elect leaders for subsequent rounds are vulnerable to Denial-of…
SNARKChain: Proof-of-Useful-Work Blockchain Consensus with General-Purpose SNARK Marketplace
Samuel Oleksak, Richard Gazdik, Martin Peresini +1
Proof of Work (PoW) is widely regarded as the most secure permissionless blockchain consensus protocol. However, its reliance on computationally intensive yet externally useless pu…
Secret Leader Election in Ethereum PoS: An Empirical Security Analysis of Whisk and Homomorphic Sortition under DoS on the Leader and Censorship Attacks
Tereza Burianová, Martin Perešíni, Ivan Homoliak
Proposer anonymity in Proof-of-Stake (PoS) blockchains is a critical concern due to the risk of targeted attacks such as malicious denial-of-service (DoS) and censorship attacks. W…
FeatherWallet: A Lightweight Mobile Cryptocurrency Wallet Using zk-SNARKs
Martin Perešíni, Ivan Homoliak, Samuel Olekšák +1
Traditionally, mobile wallets rely on a trusted server that provides them with a current view of the blockchain, and thus, these wallets do not need to validate the header chain or…
Enhancing Security of AI-Based Code Synthesis with GitHub Copilot via Cheap and Efficient Prompt-Engineering
Jakub Res, Ivan Homoliak, Martin Perešíni +3
AI assistants for coding are on the rise. However one of the reasons developers and companies avoid harnessing their full potential is the questionable security of the generated co…
SoK: Cryptocurrency Wallets -- A Security Review and Classification based on Authentication Factors
Ivan Homoliak, Martin Perešíni
In this work, we review existing cryptocurrency wallet solutions with regard to authentication methods and factors from the user's point of view. In particular, we distinguish betw…
DAG-Sword: A Simulator of Large-Scale Network Topologies for DAG-Oriented Proof-of-Work Blockchains
Martin Perešíni, Tomáš Hladký, Kamil Malinka +1
The blockchain brought interesting properties for many practical applications. However, some properties, such as the transaction processing throughput remained limited, especially…
CBDC-AquaSphere: Interoperable Central Bank Digital Currency Built on Trusted Computing and Blockchain
Ivan Homoliak, Martin Perešíni, Patrik Holop +2
The adoption of decentralized, tamper-proof ledger systems is paving the way for new applications and opportunities in different contexts. While most research aims to improve their…
Incentive Attacks on DAG-Based Blockchains with Random Transaction Selection
Martin Perešíni, Ivan Homoliak, Federico Matteo Benčić +2
Several blockchain consensus protocols proposed to use of Directed Acyclic Graphs (DAGs) to solve the limited processing throughput of traditional single-chain Proof-of-Work (PoW)…
On the Educational Impact of ChatGPT: Is Artificial Intelligence Ready to Obtain a University Degree?
Kamil Malinka, Martin Perešíni, Anton Firc +2
In late 2022, OpenAI released a new version of ChatGPT, a sophisticated natural language processing system capable of holding natural conversations while preserving and responding…
Detecting and Preventing Credential Misuse in OTP-Based Two and Half Factor Authentication Toward Centralized Services Utilizing Blockchain-Based Identity Management
Jozef Drga, Ivan Homoliak, Juraj Vančo +2
This work focuses on the problem of detection and prevention of stolen and misused secrets (such as private keys) for authentication toward centralized services. We propose a solut…
DAG-Oriented Protocols PHANTOM and GHOSTDAG under Incentive Attack via Transaction Selection Strategy
Martin Perešíni, Federico Matteo Benčić, Kamil Malinka +1
In response to the bottleneck of processing throughput inherent to single chain PoW blockchains, several proposals have substituted a single chain for Directed Acyclic Graphs (DAGs…
AQUAREUM: Non-Equivocating Censorship-Evident Centralized Ledger with EVM-Based Verifiable Execution using Trusted Computing and Blockchain
Ivan Homoliak, Mario Larangeira, Martin Peresini +1
Distributed ledger systems (i.e., blockchains) have received a lot of attention. They promise to enable mutually untrusted participants to execute transactions while providing the…