A Unified Evaluation Framework of Physical Adversarial Robustness in the Edge VLM Era
Recent advancements in Vision-Language Models (VLMs) enable end-to-end visual grounding via language prompts and generat
今日共收录 814 条安全情报,包含 0 个 CVE,421 篇安全通告,以及 100 篇研究论文。
← 返回归档列表Recent advancements in Vision-Language Models (VLMs) enable end-to-end visual grounding via language prompts and generat
The Regular Syndrome Decoding (RSD) problem is a structured variant of classical Syndrome Decoding and underlies a growi
Local Retrieval-Augmented Generation (RAG) systems are vulnerable to indirect prompt injection and retrieval poisoning,
Deterministic industrial networks often present an operational trade-off between maintaining microsecond timing of prima
The UK, EU and US governments have set timelines for post-quantum cryptography migration of critical systems, with deadl
Language-model attackers consume computational resources as they explore and interact with a target, creating an opportu
Diffusion models have emerged as the foundation of modern generative systems, yet their high memorization capacity raise
CVE-2026-109619 · CVE-2026-109618
CVE-2026-109618 and CVE-2026-109619 are Critical vulnerabilities in PHP, a scripting language used globally for web serv
京ICP证080047号[京ICP备08010314号-6]
京网文〔2020〕6051-1195号
(总)网出证(京)字第281号
京公网安备 11000002002063号
浙公网安备 33010602009975号
Background Security Improvements
Get help with security issues
submit your research
update the software on your iPhone or iPad
update the software on your Mac
Latest security bulletins
Latest Compatibility Definition Document (CDD)