cyberintel.kalymoon.com · 2713 articles · updated every 4 hours · grows forever
arXiv:2604.07775v1 Announce Type: cross Abstract: Collaboration and information sharing empower Multi-Agent Systems (MAS) but also introduce a critical security risk known as Agent Cascading Injection…
arXiv:2604.07552v1 Announce Type: cross Abstract: Trust management in VANETs is critically important for secure communication between vehicles. In event-based trust systems, vehicles broadcast the eve…
arXiv:2604.07539v1 Announce Type: cross Abstract: We present a constructive proof that a single C program, the \emph{Vulnerability Factory}, admits a countably infinite set of distinct, independently …
arXiv:2604.07532v1 Announce Type: cross Abstract: Vehicular Ad Hoc Networks (VANETs) are vulnerable to intelligent attackers who exploit the homogeneous treatment of traffic events in existing trust m…
arXiv:2604.08499v1 Announce Type: new Abstract: Prompt injection attacks pose serious security risks across a wide range of real-world applications. While receiving increasing attention, the community…
arXiv:2604.08480v1 Announce Type: new Abstract: When a user sends a message over a wireless network, the message does not travel as-is. It is encrypted, authenticated, encapsulated, and transformed as…
arXiv:2604.08407v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on third-party API routers to dispatch tool-calling requests across multiple upstream providers. The…
arXiv:2604.08304v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) significantly enhances large language models (LLMs) but introduces novel security risks through external knowledge …
arXiv:2604.08297v1 Announce Type: new Abstract: Ensuring Large Language Model (LLM) safety is crucial, yet the lack of a clear understanding about safety mechanisms hinders the development of precise …
arXiv:2604.08140v1 Announce Type: new Abstract: Network traffic, as a key media format, is crucial for ensuring security and communications in modern internet infrastructure. While existing methods of…
arXiv:2604.08113v1 Announce Type: new Abstract: Ensuring reliability in adversarial settings necessitates treating privacy as a foundational component of data-driven systems. While differential privac…
arXiv:2604.08037v1 Announce Type: new Abstract: Talking-head generation has advanced rapidly with diffusion-based generative models, but training usually depends on centralized face-video and speech d…
arXiv:2604.08019v1 Announce Type: new Abstract: Humanitarian organizations help to ensure people's livelihoods in crisis situations. Typically, multiple organizations operate in the same region. To en…
arXiv:2604.07839v1 Announce Type: new Abstract: The rapid expansion of the Internet of Things (IoT) and smart home ecosystems has led to a fragmented landscape of user data management across consumer …
arXiv:2604.07831v1 Announce Type: new Abstract: Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is unavailabl…
arXiv:2604.07797v1 Announce Type: new Abstract: Searchable Encryption (SE) enables users to query outsourced encrypted data while preserving data confidentiality. However, most efficient schemes still…
arXiv:2604.07771v1 Announce Type: new Abstract: Anamorphic encryption serves as a vital tool for covert communication, maintaining secrecy even during post-compromise scenarios. Particularly in the re…
arXiv:2604.07754v1 Announce Type: new Abstract: The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve mod…
arXiv:2604.07727v1 Announce Type: new Abstract: Existing jailbreak defense paradigms primarily rely on static detection of prompts, outputs, or internal states, often neglecting the dynamic evolution …
arXiv:2604.07695v1 Announce Type: new Abstract: The rapid deployment of AI agents acting autonomously on behalf of human principals has outpaced the development of cryptographic protocols for establis…
arXiv:2604.07581v1 Announce Type: new Abstract: It can be difficult for practitioners to interpret the quality of differentially private (DP) statistics due to the added noise. One method to help anal…
arXiv:2604.07568v1 Announce Type: new Abstract: Maximal Extractable Value, or MEV, remains a structural threat to blockchain fairness because a block producer can often observe pending transactions an…
arXiv:2604.07551v1 Announce Type: new Abstract: The Model Context Protocol (MCP) enables large language models (LLMs) to dynamically discover and invoke third-party tools, significantly expanding agen…
arXiv:2604.07536v1 Announce Type: new Abstract: Large language models (LLMs) increasingly rely on external tools to perform time-sensitive tasks and real-world actions. While tool integration expands …