cyberintel.kalymoon.com · 2889 articles · updated every 4 hours · grows forever
arXiv:2510.03565v4 Announce Type: replace Abstract: Privacy-preserving machine learning has become an important long-term pursuit in this era of artificial intelligence (AI). Fully Homomorphic Encrypt…
arXiv:2507.02281v4 Announce Type: replace Abstract: Construct the first provably secure linear homomorphic ring signature scheme. Ring signatures allow a signer to anonymously sign a message on behalf…
arXiv:2503.23866v3 Announce Type: replace Abstract: This paper investigates backdoor attacks in image-oriented semantic communications. The threat of backdoor attacks on symbol reconstruction in seman…
arXiv:2603.26573v1 Announce Type: cross Abstract: Existing literature on timed opacity uses specific definitions for restricted subclasses of timed automata or limited observation models. This lack of…
arXiv:2603.26167v1 Announce Type: cross Abstract: Diffusion models generate high-quality images but pose serious risks like copyright violation and disinformation. Watermarking is a key defense for tr…
arXiv:2603.25997v1 Announce Type: cross Abstract: Open-source software supply chain security relies heavily on assessing affected versions of library vulnerabilities. While prior studies have leverage…
arXiv:2603.25994v1 Announce Type: cross Abstract: Concept erasure in text-to-image diffusion models seeks to remove undesired concepts while preserving overall generative capability. Localized erasure…
arXiv:2603.25861v1 Announce Type: cross Abstract: Activation-based probes have emerged as a promising approach for detecting deceptively aligned AI systems by identifying internal conflict between tru…
arXiv:2603.26632v1 Announce Type: new Abstract: Malware continues to be a predominant operational risk for organizations, especially when obfuscation techniques are used to evade detection. Despite th…
arXiv:2603.26497v1 Announce Type: new Abstract: Reentrancy remains one of the most critical classes of vulnerabilities in Ethereum smart contracts, yet widely used detection tools and datasets continu…
arXiv:2603.26417v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative training while keeping sensitive data on clients' devices, but local model updates can still leak private …
arXiv:2603.26409v1 Announce Type: new Abstract: In this paper we present an attack on a recently proposed code-based Private Information Retrieval (PIR) scheme. Indeed, the server can retrieve the ind…
arXiv:2603.26407v1 Announce Type: new Abstract: Matchmaking has become a prevalent part in contemporary applications, being used in dating apps, social media, online games, contact tracing and in vari…
arXiv:2603.26361v1 Announce Type: new Abstract: Blockchain technology introduces asset types and custody mechanisms that fundamentally break traditional financial auditing paradigms. This paper presen…
arXiv:2603.26343v1 Announce Type: new Abstract: The application of zero-knowledge proofs (ZKPs) in autonomous systems is an emerging area of research, motivated by the growing need for regulatory comp…
arXiv:2603.26293v1 Announce Type: new Abstract: Bitcoin's limited programmability and transaction throughput have historically prevented native Bitcoin from participating in decentralized finance (DeF…
arXiv:2603.26290v1 Announce Type: new Abstract: Transfer-based anti-money laundering (AML) systems monitor token flows through transaction-graph abstractions, implicitly assuming that economically mea…
arXiv:2603.26270v1 Announce Type: new Abstract: Smart contracts govern billions of dollars in decentralized finance (DeFi), yet automated vulnerability detection remains challenging because many vulne…
arXiv:2603.26224v1 Announce Type: new Abstract: The vigorous development of the Internet has spurred exponential data growth, yet data is predominantly stored in isolated user entities, hampering its …
arXiv:2603.26221v1 Announce Type: new Abstract: Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assista…
arXiv:2603.26219v1 Announce Type: new Abstract: With the explosive growth of graph-structured data, graph databases have become a critical infrastructure for supporting large-scale and complex data an…
arXiv:2603.26093v1 Announce Type: new Abstract: Safety-critical domains like healthcare rely on deep neural networks (DNNs) for prediction, yet DNNs remain vulnerable to evasion attacks. Anomaly detec…
arXiv:2603.26074v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances the utility of Large Language Models (LLMs) by retrieving external documents. Since the knowledge database…
arXiv:2603.26032v1 Announce Type: new Abstract: Large Language Models (LLMs) generate responses based on user prompts. Often, these prompts may contain highly sensitive information, including personal…