AttacksarXiv 2610.10000
超越奖励压制：有界奖励热启动 Bandit 的近最优离线攻击
提出热启动 Bandit 的部署前有界离线注入攻击
- arXiv
- 2610.10000
- Published
- Setting
- LLM applications
- Evaluated models
- UCB, Thompson Sampling, ϵ-greedy
- AttacksPoisoning and backdoors
All papers
Filter3
Attack type
Impact
System type
Attack surface / entry point
Layer
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Another 254papers do not have category tags yet and are not included in filtered results.
- AttacksarXiv 2610.05793
研究者训练出按多智能体拓扑触发的代码后门模型
提出拓扑条件后门，使代码模型在推断多智能体部署时植入漏洞
- arXiv
- 2610.05793
- Published
- Setting
- coding agent
- Evaluated models
- Qwen2.5-7B-Instruct, Qwen2.5-Coder-7B-Instruct
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract论文证实了拓扑条件后门的可训练性与泛化性，展示了常规评测盲区，并提出差异化拓扑审计作为检测防御方向。
- AttacksarXiv 2609.17817
论文：用投毒基准污染自改进编码 Agent，令其后续版本写出漏洞代码
提出基准投毒攻击，使自修改编码 Agent 跨代写出含漏洞代码
- arXiv
- 2609.17817
- Published
- Layer
- Application layer
- Setting
- coding agent
- Evaluated models
- Claude Sonnet 4.5, Qwen3.5-397B, gpt-oss-120b and others5
- AttacksPoisoning and backdoors
Abstract论文报告了恶意基准能污染自修改代码智能体的进化过程并持续输出漏洞，警示系统设计需纳入安全约束。
- AttacksarXiv 2604.03890
From prompts to physical actions: structured backdoor attacks against LLM-mediated robot control systems
Propose a structured JSON backdoor that triggers malicious actions in robot control via a poisoned LoRA
- arXiv
- 2604.03890
- Published
- Evaluated models
- Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract推理层后门传不到执行。
You have reached the end