cyberintel.kalymoon.com · 53594 articles · updated every 4 hours · grows forever
arXiv:2603.18085v1 Announce Type: new Abstract: Recent incidents have highlighted alarming cases where human-AI interactions led to negative psychological outcomes, including mental health crises and …
arXiv:2603.18073v1 Announce Type: new Abstract: Modern language model-based AI systems are remarkably powerful, yet their capabilities remain fundamentally capped by their human creators in three key …
arXiv:2603.18048v1 Announce Type: new Abstract: Recent Audio Multimodal Large Language Models (Audio MLLMs) demonstrate impressive performance on speech benchmarks, yet it remains unclear whether thes…
arXiv:2603.19011v1 Announce Type: new Abstract: NDAI zones let inventor and investor agents negotiate inside a Trusted Execution Environment (TEE) where any disclosed information is deleted if no deal…
arXiv:2603.18939v1 Announce Type: new Abstract: Masking is a countermeasure against Power Side Channel Attacks (PSCAs) in both software and hardware implementations of cryptographic algorithms. Compar…
arXiv:2603.18914v1 Announce Type: new Abstract: The rapid proliferation of artificial intelligence (AI) technologies has led to a dynamic regulatory landscape, where legislative frameworks strive to k…
arXiv:2603.18836v1 Announce Type: new Abstract: Confidential databases (CDBs) are essential for enabling secure queries over sensitive data in untrusted cloud environments using confidential computing…
arXiv:2603.18829v1 Announce Type: new Abstract: Agent Control Protocol (ACP) is a formal technical specification for governance of autonomous agents in B2B institutional environments. ACP is the admis…
arXiv:2603.18793v1 Announce Type: new Abstract: Model watermarking utilizes internal representations to protect the ownership of large language models (LLMs). However, these features inevitably underg…
arXiv:2603.18789v1 Announce Type: new Abstract: The security of modern JavaScript (JS) engines is critical since they provide the primary defense mechanism for executing untrusted code on the web. The…
arXiv:2603.18779v1 Announce Type: new Abstract: Graph data is increasingly prevalent across domains, offering analytical value but raising significant privacy concerns. Edges may encode sensitive rela…
arXiv:2603.18762v1 Announce Type: new Abstract: Autonomous web agents such as \textbf{OpenClaw} are rapidly moving into high-impact real-world workflows, but their security robustness under live netwo…
arXiv:2603.18693v1 Announce Type: new Abstract: Python applications depend on native libraries that may be vendored within package distributions or installed on the host system. When vulnerabilities a…
arXiv:2603.18687v1 Announce Type: new Abstract: Ranging and localisation have become critical for many applications and services. The Wi-Fi (IEEE 802.11) standard is a natural candidate for providing …
arXiv:2603.18647v1 Announce Type: new Abstract: Test Vector Leakage Assessment (TVLA) based on Welch's $t$-test has become a standard tool for detecting side-channel leakage. However, its mean-based n…
arXiv:2603.18637v1 Announce Type: new Abstract: We study how to allocate a fixed supervised fine-tuning budget when three objectives must be balanced at once: multi-turn safety alignment, low over-ref…
arXiv:2603.18613v1 Announce Type: new Abstract: Industrial Cyber-Physical Systems (ICPS) face growing threats from cyber-attacks that exploit sensor and control vulnerabilities. Digital Twin (DT) tech…
arXiv:2603.18608v1 Announce Type: new Abstract: Card-based cryptography uses physical playing cards to construct protocols for secure multi-party computation. Existing card-based protocols employ vari…
arXiv:2603.18549v1 Announce Type: new Abstract: Dynamic Random Access Memory (DRAM) is pervasive in computer systems. Cell vulnerabilities caused by unintended phenomena (forced retention failure, lat…
arXiv:2603.18455v1 Announce Type: new Abstract: SIMON and SPECK were among the first efficient encryption algorithms introduced for resource-constrained applications. SIMON is suitable for Internet of…
arXiv:2603.18449v1 Announce Type: new Abstract: The widespread deployment of large language models (LLMs) calls for post-hoc methods that can flexibly adapt models to evolving safety requirements. Mea…
arXiv:2603.18433v1 Announce Type: new Abstract: Large language models (LLMs) deployed behind APIs and retrieval-augmented generation (RAG) stacks are vulnerable to prompt injection attacks that may ov…
arXiv:2603.18377v1 Announce Type: new Abstract: Cloud-hosted large language models (LLMs) have become the de facto planners in agentic systems, coordinating tools and guiding execution over local envi…
arXiv:2603.18355v1 Announce Type: new Abstract: In the ever-evolving battle against malware, binary obfuscation techniques are a formidable barrier to effective analysis by both human security analyst…