cyberintel.kalymoon.com · 42810 articles · updated every 4 hours · grows forever
arXiv:2604.19753v1 Announce Type: new Abstract: We propose a feature-free approach to algorithm selection that replaces hand-crafted instance features with pretrained text embeddings. Our method, Zero…
arXiv:2604.19751v1 Announce Type: new Abstract: Generative AI is entering research, education, and professional work faster than current governance frameworks can specify how AI-assisted outputs shoul…
arXiv:2604.19749v1 Announce Type: new Abstract: Equipping LLMs with external tools effectively addresses internal reasoning limitations. However, it introduces a critical yet under-explored phenomenon…
arXiv:2409.07609v2 Announce Type: replace Abstract: Deploying adversarially robust machine learning systems requires continuous trade-offs between robustness, cost, and latency. We present an autonomi…
arXiv:2405.12042v3 Announce Type: replace Abstract: The Messaging Layer security (MLS) and its underlying Continuous Group Key Agreement (CGKA) protocol allows a group of users to share a cryptographi…
arXiv:2604.20596v1 Announce Type: cross Abstract: Federated learning (FL) enables training of a global model while keeping raw data on end-devices. Despite this, FL has shown to leak private user info…
arXiv:2604.20245v1 Announce Type: cross Abstract: Fundamental rate-distortion-perception (RDP) trade-offs arise in applications requiring maintained perceptual quality of reconstructed data, such as n…
arXiv:2604.20211v1 Announce Type: cross Abstract: Logging code plays an important role in software systems by recording key events and behaviors, which are essential for debugging and monitoring. Howe…
arXiv:2604.20062v1 Announce Type: cross Abstract: The rise of IoT devices and the uptake of cloud computing have informed a new era of data-driven intelligence. Traditional centralized machine learnin…
arXiv:2604.20047v1 Announce Type: cross Abstract: Vision Transformers (ViTs) have achieved remarkable success across vision tasks, yet recent studies show they remain vulnerable to backdoor attacks. E…
arXiv:2604.19785v1 Announce Type: cross Abstract: Sensitive information, such as knowledge about an individual's personality, can be can be misused to influence behavior (e.g., via personalized messag…
arXiv:2604.20833v1 Announce Type: new Abstract: As artificial intelligence (AI) systems are increasingly deployed across critical domains, their security vulnerabilities pose growing risks of high-pro…
arXiv:2604.20826v1 Announce Type: new Abstract: Phishing attacks remain one of the most prevalent threats to online security, with the Anti-Phishing Working Group reporting over 890,000 attacks in Q3 …
arXiv:2604.20801v1 Announce Type: new Abstract: LLM agents have begun to find real security vulnerabilities that human auditors and automated fuzzers missed for decades, in source-available targets wh…
arXiv:2604.20793v1 Announce Type: new Abstract: Post-quantum cryptographic (PQC) accelerators for ML-KEM (FIPS 203) and ML-DSA (FIPS 204) rely on pipelined Number Theoretic Transform (NTT) stages over…
arXiv:2604.20771v1 Announce Type: new Abstract: The Internet of Vehicles (IoV) is advancing modern transportation by improving safety, efficiency, and intelligence. However, the reliance on the Contro…
arXiv:2604.20765v1 Announce Type: new Abstract: Critical vulnerabilities with Common Vulnerability Scoring System scores of 9.0 or higher pose severe risks to organisations' information systems. Timel…
arXiv:2604.20704v1 Announce Type: new Abstract: Adversarial robustness evaluation underpins every claim of trustworthy ML deployment, yet the field suffers from fragmented protocols and undetected gra…
arXiv:2604.20621v1 Announce Type: new Abstract: Autonomous vehicles (AVs) increasingly rely on multi-sensor perception pipelines that combine data from cameras, lidar, radar, and other modalities to i…
arXiv:2604.20576v1 Announce Type: new Abstract: As DRAM scaling exacerbates RowHammer, DDR5 introduces per-row activation counting (PRAC) to track aggressor activity. However, PRAC indiscriminately in…
arXiv:2604.20496v1 Announce Type: new Abstract: The April 2026 Claude Mythos sandbox escape exposed a critical weakness in frontier AI containment: the infrastructure surrounding advanced models remai…
arXiv:2604.20495v1 Announce Type: new Abstract: Machine learning-based static malware detectors remain vulnerable to adversarial evasion techniques, such as metamorphic engine mutations. To address th…
arXiv:2604.20401v1 Announce Type: new Abstract: Approximate nearest neighbor (ANN) search in AI systems increasingly handles sensitive data on third-party infrastructure. Trusted execution environment…
arXiv:2604.20389v1 Announce Type: new Abstract: The rapid evolution and use of Large Language Models (LLMs) in professional workflows require an evaluation of their domain-specific knowledge against i…