Adaptive_Greedy_Local_Search

自适应贪心局部搜索 AGLS 语义保持的提示劫持：针对自动提示优化的黑盒对抗攻击 ICME 2026 摘要： 大型语言模型（LLMs）日益配备自动提示优化模块，这些模块会重写用户的输入，并在生成最终响应之前明确展示一个"改进后"的提示。尽管这种可见性旨在增强信任和用户控制，但优化器自主选择单一"最佳"候选的过程仍不受约束。攻击者可以劫持原始提示或由自动提示优化生成的提示，进行替代性重写，从而诱发语义漂移并完成劫持优化过程，进而严重影响 LLM...

ARuleCon: Agentic Security Rule Conversion

Security Information and Event Management SIEM systems make it possible for detecting intrusion anomalies in real-time manner by their applied security rules. However, the heterogeneity of vendor-specific rules e.g., Splunk SPL, Microsoft KQL, IBM AQL, Google YARA-L, and RSA ESA makes...

CVE-2026-32901

Affected software: OpenClaw prior to version 2026.3.2. Vulnerability type: semantic drift in node system.run approval hardening that rewrites wrapper argv, enabling execution of unintended local scripts when an attacker can influence argv and place malicious files in the approved working director...