266 citations · 274 across the 18 of their papers we have counts for
14 papers · 1 filter
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…
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…