cyberintel.kalymoon.com · 2751 articles · updated every 4 hours · grows forever
arXiv:2604.03968v1 Announce Type: new Abstract: AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle at…
arXiv:2604.03912v1 Announce Type: new Abstract: As cloud environments become increasingly complex, cybersecurity and forensic investigations must evolve to meet emerging threats. Large Language Models…
arXiv:2604.03903v1 Announce Type: new Abstract: The Learning with Errors (LWE) problem is a hard math problem in lattice-based cryptography. In the simplest case of binary secrets, it is the subset su…
arXiv:2604.03902v1 Announce Type: new Abstract: Location-based systems that combine encrypted geographic search with zero-knowledge proximity proofs typically treat the two phases as independent. Unde…
arXiv:2604.03900v1 Announce Type: new Abstract: A zero-knowledge proximity proof certifies geometric nearness but carries no commitment to an application context. In stateful geo-content systems, wher…
arXiv:2604.03896v1 Announce Type: new Abstract: IoT location services accept client-reported GPS coordinates at face value, yet spoofing is trivial with consumer-grade tools. Existing spoofing detecto…
arXiv:2604.03886v1 Announce Type: new Abstract: Standard communication protocols for Unmanned Aerial Vehicles (UAVs), such as MAVLink, lack the capability to enforce the contextual validity of message…
arXiv:2604.03862v1 Announce Type: new Abstract: Federated learning (FL) enables multiple clients to collaboratively train a global machine learning model via a server without sharing their private tra…
arXiv:2604.03860v1 Announce Type: new Abstract: Traditional consensus mechanisms, such as Proof of Stake (PoS), increasingly reveal an excessive dependency on large liquidity providers. Although the P…
arXiv:2604.03859v1 Announce Type: new Abstract: WebAssembly is quickly becoming a popular compilation target for a variety of code. However, vulnerabilities in the source languages translate to vulner…
arXiv:2604.03844v1 Announce Type: new Abstract: Formally guaranteeing the safety and liveness of regulatory state transitions in cross-domain state synchronization systems is a problem of growing impo…
arXiv:2604.03843v1 Announce Type: new Abstract: Transformer-based malware detection systems operating on graph modalities such as control flow graphs (CFGs) achieve strong performance by modeling stru…
arXiv:2604.03813v1 Announce Type: new Abstract: Adams Bridge, a hardware accelerator for ML-DSA and ML-KEM designed for the Caliptra root of trust, masks 1 of its Inverse Number Theoretic Transform (I…
arXiv:2604.03790v1 Announce Type: new Abstract: Cyber attacks targeting Industrial Control Systems (ICS) have become increasingly sophisticated and hard to identify. Detecting such attacks requires in…
arXiv:2604.03753v1 Announce Type: new Abstract: Modern advanced driver assistance systems (ADAS) rely on deep neural networks (DNNs) for perception and planning. Since DNNs' parameters reside in DRAM …
arXiv:2604.03750v1 Announce Type: new Abstract: Reverse engineering (RE) is central to software security, particularly for cryptographic programs that handle sensitive data and are highly prone to vul…
arXiv:2604.03665v1 Announce Type: new Abstract: This paper studies how post-quantum cryptographic (PQC) security assumptions can be represented and communicated through a structured, layered framework…
arXiv:2604.03627v1 Announce Type: new Abstract: Authentication is a fundamental security means for protecting system resources. Authenticator-centric authentication techniques (AuthN Techniques) addre…
arXiv:2604.03612v1 Announce Type: new Abstract: As multimodal large language models (LLMs) advance, traditional CAPTCHAs have become obsolete at distinguishing humans from bots. To address this shift,…
arXiv:2604.03608v1 Announce Type: new Abstract: Fault injection attacks deliberately inject faults into a device via physical channels to disturb its regular execution. Adversaries can effectively ded…
arXiv:2604.03598v1 Announce Type: new Abstract: Prompt injection has emerged as a critical vulnerability in large language model (LLM) deployments, yet existing research is heavily weighted toward def…
arXiv:2604.03595v1 Announce Type: new Abstract: Vertical split learning (SL) enables collaborative model training across parties holding complementary features without sharing raw data, but recent wor…
arXiv:2604.03587v1 Announce Type: new Abstract: Reasoning language models (RLMs) are increasingly used in programming. Yet, even state-of-the-art RLMs frequently introduce critical security vulnerabil…
arXiv:2604.03560v1 Announce Type: new Abstract: Hardware intellectual property (IP) in the globalized integrated circuit (IC) supply chain is exposed to a wide range of confidentiality and integrity a…