1
Attacking the Trusted Imagination: Oracle-Level Integrity Attacks on Imagine-then-Act World Models
揭示“想象-行动”世界模型的致命漏洞，用预言机级攻击篡改AI对未来的信任，安全研究者必读。
arXiv:2606.22966v1 Announce Type: cross Abstract: Many recent vision-language-action (VLA) policies adopt an imagine-then-act design. A world-action m…