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
System type
Attack surface / entry point
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Another 261papers do not have category tags yet and are not included in filtered results.
- AttacksarXiv 2609.02774
CodePoisonRAG：针对检索增强代码生成的知识投毒攻击
提出 CodePoisonRAG，对检索增强代码生成的知识库投毒以植入漏洞
- arXiv
- 2609.02774
- Published
- Layer
- Application layer
- Setting
- LLM applications
- Evaluated models
- Qwen 3.5 9B, Code Llama 13B, DeepSeek-Coder-V2 16B
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentRAG
AbstractCodePoisonRAG 展示了 RACG 外部知识库的新攻击面，在较低投毒率下可定向诱发指定漏洞并部分抵御防御。
- DefensesarXiv 2608.06422
CMU 研究：分片判断可避免 LLM 监督失效并抵御对抗利用
提出分片监督，将评判标准分配给独立调用以抵御展示攻击
- arXiv
- 2608.06422
- Published
- Layer
- Application layer
- Setting
- LLM applications
- Attacker
- Black-box
- Evaluated models
- Claude Opus 4.8, Claude Sonnet 4.6, Claude Opus 4.6 and others4
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
Abstract论文揭示决策负载是大模型监督的独立瓶颈，提出分片与辩论机制有效分离注意力与平衡证据，在多项高难度基准上实现稳健评判。
本文系统研究了大语言模型在执行多标准监督与评判时的决策负载瓶颈及其安全风险。
- AttacksarXiv 2604.03890
从提示到物理动作：针对 LLM 中介机器人控制系统的结构化后门攻击
提出结构化 JSON 后门，经投毒 LoRA 在机器人控制中触发恶意动作
- 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