cyberintel.kalymoon.com · 4773 articles · updated every 4 hours · grows forever
arXiv:2605.28074v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval,…
arXiv:2605.28071v1 Announce Type: new Abstract: LLM-based agents have recently attracted significant attention due to their ability to autonomously invoke relevant tools to accomplish complex tasks. H…
arXiv:2605.28017v1 Announce Type: new Abstract: Recent generative engine optimisation (GEO) research has shown that prompt-injection attacks can push a target product to the top of an LLM's recommenda…
arXiv:2605.27912v1 Announce Type: new Abstract: We study efficient differentially private algorithms for estimating monotone statistics, i.e., statistics that are monotone under the addition of new ob…
arXiv:2605.27836v1 Announce Type: new Abstract: We demonstrate an attack on Introspection Adapters (Shenoy et al., 2026).
arXiv:2605.27825v1 Announce Type: new Abstract: Membership inference attacks (MIAs) test whether a target data record belongs to a system's private data, and have become a standard tool to measure pri…
arXiv:2605.27823v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting…
arXiv:2605.27804v1 Announce Type: new Abstract: The increasing presence of software in modern automobiles has created a growing need to deliver software updates throughout a vehicle's entire lifespan.…
arXiv:2605.27803v1 Announce Type: new Abstract: Modern architecture research relies on simulators to evaluate system security, yet analyzing emerging hardware vulnerabilities like RowHammer requires f…
arXiv:2605.27743v1 Announce Type: new Abstract: Modern 5G-Advanced and emerging 6G cloud-native telecom architectures encounter unprecedented hyper-complexity, multi-layered threat vectors, and fluid …
arXiv:2605.27729v1 Announce Type: new Abstract: The 2024--2025 Nobel and Turing awards recognised artificial intelligence and quantum science in the same breath -- machine learning as a physical scien…
arXiv:2605.27705v1 Announce Type: new Abstract: Video production workflows offer a rich and demanding arena for evaluating multimodal AI agents: they require composite capabilities across text, image,…
arXiv:2605.27674v1 Announce Type: new Abstract: Cyber-Physical Systems (CPS) integrate sensing, communication, computation, and control to support critical infrastructure, including smart grids, indus…
arXiv:2605.27667v1 Announce Type: new Abstract: Android's permission system is designed to balance usability with informed consent, yet two legacy mechanisms still undermine that balance in Android 16…
arXiv:2605.27647v1 Announce Type: new Abstract: In this note, we consider the setting of uncloneable encryption satisfying uncloneable indistinguishability, a form of symmetric key encryption that pre…
arXiv:2605.27631v1 Announce Type: new Abstract: Code Large Language Models (CLLMs) serve as the core of modern code agents, enabling developers to automate complex software development tasks. In this …
arXiv:2605.27587v1 Announce Type: new Abstract: The Cybersecurity Maturity Model Certification program requires third-party assessments be conducted under a non-consultative model. The model is intend…
arXiv:2605.27565v1 Announce Type: new Abstract: Encrypted cloud storage can hide data contents but still leak sensitive information through access patterns. ORAM addresses this by hiding access patter…
arXiv:2605.27535v1 Announce Type: new Abstract: In AES-like ciphers, diffusion layers are commonly instantiated using MDS matrices, since their optimal branch number yields strong diffusion guarantees…
arXiv:2605.27494v1 Announce Type: new Abstract: Modern retrieval-augmented generation(RAG) deployments increasingly rely on caching to reduce token cost and time-to-first-token(TTFT). Prefix-level KV …
arXiv:2605.27489v1 Announce Type: new Abstract: Multi-agent LLM systems decompose workflows across agents, tools, shared context, memory, and decision gates. This modularity improves interpretability,…
arXiv:2605.27488v1 Announce Type: new Abstract: Agentic systems increasingly run user-authored orchestration code that invokes tools, spawns subtasks, and delegates work across machines and clouds. Al…