cyberintel.kalymoon.com · 36374 articles · updated every 4 hours · grows forever
arXiv:2605.19233v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) are cyber-physical systems whose attack surface spans networked avionics and on-board sensor fusion: a compromised GPS o…
arXiv:2605.19232v1 Announce Type: new Abstract: Fake Base Station (FBS) detection has been a critical focus of cellular security research for over two decades. However, significant financial and regul…
arXiv:2605.19227v1 Announce Type: new Abstract: Unified autoregressive models (UAMs) are transformer models that generate text as well as image tokens within a single autoregressive pass. Shared param…
arXiv:2605.19159v1 Announce Type: new Abstract: Prompt injection attacks pose significant risks to language model safety, yet existing defenses are typically evaluated using classification performance…
arXiv:2605.19147v1 Announce Type: new Abstract: Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful content…
arXiv:2605.19123v1 Announce Type: new Abstract: Cryptographic primitives such as stream ciphers,Pseudorandom Number Generators (PRNGs), and block cipher modes produce sequences that are designed to be…
arXiv:2605.18991v1 Announce Type: new Abstract: We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted compon…
arXiv:2605.18988v1 Announce Type: new Abstract: The expansion of Multimodal Large Language Models (MLLMs) and their integration into autonomous agentic workflows has introduced a non-stationary attack…
arXiv:2605.18930v1 Announce Type: new Abstract: Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce se…
arXiv:2605.18919v1 Announce Type: new Abstract: Evolutionary algorithms for adversarial attacks leverage population-based search to discover perturbations without gradient information, but suffer from…
arXiv:2605.18918v1 Announce Type: new Abstract: Modern AI assistants are agentic. To answer a single user request, the underlying language model pulls in information from many sources, such as web sea…
arXiv:2605.18915v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are vulnerable to jailbreak attacks, which can elicit harmful responses from MLLMs. Many MLLMs support multi-im…
arXiv:2605.18913v1 Announce Type: new Abstract: The U.S. financial system processes approximately 1.3 million interbank transactions daily, yet no system in the reviewed literature models fraud propag…
arXiv:2605.18908v1 Announce Type: new Abstract: Deep neural networks (DNNs) remain critically vulnerable to backdoor attacks. Existing post-training detectors often require clean or surrogate data, gr…
arXiv:2605.18907v1 Announce Type: new Abstract: Deep neural networks (DNN), despite their remarkable performance, are highly vulnerable to backdoor attacks. Existing defenses mainly rely on activation…
arXiv:2605.18901v1 Announce Type: new Abstract: Small and medium enterprises (SMEs) face growing cyber threats but often lack the resources and expertise needed to adopt Zero Trust Architecture (ZTA).…
arXiv:2605.18873v1 Announce Type: new Abstract: Training and evaluating false data injection attack (FDIA) detectors for power systems is constrained by data scarcity. Operational grid measurements ar…
arXiv:2605.18868v1 Announce Type: new Abstract: While vision and multimodal foundation models underpin critical tasks from perception to complex reasoning, they remain highly vulnerable to adversarial…
arXiv:2605.18773v1 Announce Type: new Abstract: Traditional facility management often relies on centralized decision-making structures that limit stakeholder participation, leading to misalignment wit…
A vulnerability categorized as critical has been discovered in Microsoft Windows 11 24H2/11 25H2/11 26H1/Server 2025 . Affected by this issue is some unknown functionality. Executing a manipulation ca…
A notorious threat actor operating under the alias TeamPCP claims to have breached GitHub’s internal systems, allegedly exfiltrating proprietary organization data and source code. The attackers are of…
A recent cyberattack targeting an online Learning Management System (LMS) has been attributed to the notorious cybercriminal group ShinyHunters. The incident caused widespread service disruptions affe…
Microsoft has disrupted the infrastructure powering the largest malware code-signing service used to help ransomware groups and other cybercriminals make malicious programs harder to detect on Windows…