Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Backdoors and poisoning · Papers
Found 3 papers提出 TrojanWorld,用物理触发器对世界模型智能体植入想象引导后门
- Published
- Evaluated models
- TD-MPC2, DreamerV3, R2-Dreamer
AbstractTrojanWorld 揭示了世界模型智能体的供应链后门风险,通过在世界模型中操纵想象可实现对闭环动作的持续控制。
提出 SYNCHAIN,诱导计算机使用 Agent 自建跨任务持久攻击链
- Published
- Evaluated models
- Qwen3.5-9B, Llama-3.1-8B, Ministral-3-8B
Abstract论文揭示了 CUA 自合成工件带来的内部供应链威胁,验证了潜伏载荷的跨任务传播能力与防御局限。
Propose a structured JSON backdoor that triggers malicious actions in robot control via a poisoned LoRA
- Published
- Evaluated models
- Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4
You have reached the end