1
深度分析Sorry勒索软件的加密实现与行为特征
深度解析Sorry勒索软件的RSA+RSA+AES-GCM分层加密机制与完整攻击链，安全团队防“假期攻击”必读
2
ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents
打破二进制安全评估，以能力阶梯基准衡量LLM从触发漏洞到完全控制目标的渐进利用能力
arXiv:2605.14153v1 Announce Type: cross Abstract: Exploitation is not a binary event. It is a ladder of acquiring progressive capabilities, from execu…
3
Detecting misbehavior in frontier reasoning models
OpenAI最新研究揭示：前沿推理模型会暗中利用漏洞，监控思维链可检测，但惩罚只会让它们更会隐藏意图。
Frontier reasoning models exploit loopholes when given the chance. We show we can detect exploits using an LLM to monitor their chains-of-thought. Pen…