今日共收录 832 条安全情报，包含 0 个 CVE，435 篇安全通告，以及 100 篇研究论文。
← 返回归档列表Dynamic Application Security Testing (DAST) scanners achieve high recall but also produce a large number of false positi
Large Language Models have emerged as promising tools for software vulnerability analysis, but their effectiveness depen
Large Language Models (LLMs) are widely used to generate code. Although their functional plausibility keeps improving, t
AI systems create images and videos with image/video generation models or by writing code and graphics descriptions that
Supervised fine-tuning can substantially improve the downstream utility of large language models (LLMs) but may compromi
Language model agents are increasingly deployed to automate everyday digital chores from managing emails and social medi
Safety alignment in Large Language Models (LLMs) remains vulnerable to backdoor attacks. Existing LLM backdoors are almo
LLM-based multi-agent systems (MAS) engage tools, share memory, and delegate tasks, often encountering adversarial conte
Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill a
Coding agent harnesses mediate tool use and authorize actions, yet their security mechanisms and runtime effects remain
Safety auditing of post-trained large language models typically relies on model behavior, requiring model execution and
Developers can build LLM agents by adapting third-party models through benign post-training. We study a supply-chain thr
Increasing connectivity to the outside world and the lack of inbuilt security mechanisms have made legacy intra-vehicula
CVE-2025-45737
[原创]某游戏大厂反作弊驱动分析：从代码去混淆到敏感行为还原，CVE-2025-45737任意内核读写漏洞复现、提权实验，附PoC
CVE-2020-6507
[原创]CVE-2020-6507利用链
CVE-2026-21589
On October 5th, Atlassian published patches&#;x26;#;xc2;&#;x26;#;xa0;for multiple products to fix an "Arbitrary File Acc
CVE-2026-21589
Threat actors have begun to exploit a newly disclosed critical security flaw impacting Atlassian Data Center products th
Federated learning lets a UAV fleet train a shared GPS spoofing detector without raw receiver data leaving any aircraft,
We consider the problem of parameter selection for EIP-1559, a widely used gas pricing mechanism for blockchains. As opp
Intrusion detectors can confidently misclassify attacks that were not seen during training. Human review can correct the