DefensesarXiv 2610.08773
AdvSim2Real 用任务与注入对手共同演化训练网页智能体
提出 AdvSim2Real，协同训练网页智能体抵御页面注入
- arXiv
- 2610.08773
- Published
- Layer
- Application layer
- Setting
- web agent
- Evaluated models
- Qwen3.5-4B
- DefensesModel hardening
- AttacksPrompt injection
All papers
Filter3
Attack type
Defense 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 265papers have no tags yet and are not included in filtered results.
Another 265papers do not have category tags yet and are not included in filtered results.
- DefensesarXiv 2610.06401
RAISED：用自蒸馏抵御工具调用中的提示注入
提出 RAISED 自蒸馏，训练工具智能体抵御间接提示注入
- arXiv
- 2610.06401
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Gemma-4-12B-it, Nemotron-3-Nano-30B-A3B, Qwen3.8-27B
- DefensesModel hardening
- AttacksPrompt injection
- DefensesarXiv 2610.04412
论文研究 LLM 数字孪生参与增强民主时的提示注入脆弱性
提出检测、结构化与 GSPO 流程，降低共识生成的提示注入错位
- arXiv
- 2610.04412
- Published
- Layer
- Application layer
- Setting
- LLM applications, Multi-agent systems
- Evaluated models
- LLaMA-2 7B, LLaMA-3 8B, GPT 3.5 Turbo and others14
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract三章依次做个体偏好预测、政党知识图谱审议，以及共识生成对提示注入的脆弱性与一条防御流程。
这是一篇把 LLM 数字孪生放进增强民主的博士论文，分个体表示、政党聚合和共识生成的提示注入三章。
- DefensesarXiv 2610.04269
SRFT：让 Agent 从失败经验中自我反思以抵御提示注入
提出 SRFT，让 Agent 从失败经验中学习拒绝提示注入
- arXiv
- 2610.04269
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- SR-Agent-Llama, SR-Agent-Qwen3-8B, SR-Agent-Qwen3-4B
- DefensesModel hardening
- AttacksPrompt injection
- DefensesarXiv 2609.36820
CorrGRPO：面向多奖励学习的相关性归一化 GRPO
提出 CorrGRPO，用 Pearson 相关归一化多奖励优势
- arXiv
- 2609.36820
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Qwen2.5-Coder-0.5B-Instruct, Qwen2.5-Coder-1.5B-Instruct, Qwen2.5-Coder-3B-Instruct and others8
- DefensesModel hardening
- AttacksPrompt injection
AbstractCorrGRPO 用 Pearson 相关归一化多奖励 GRPO 优势，并在三个域报告改进。
CorrGRPO 是 GRPO 的多奖励变体：组内优势的分子仍是中心化总奖励，分母改为 Pearson 相关之和，避免大尺度奖励主导归一化。
- DefensesarXiv 2609.34463
CoDeL：用协同演化防御抵御 LLM 智能体的间接提示注入
提出协同演化防御 CoDeL，抵御智能体的间接提示注入
- arXiv
- 2609.34463
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct
- DefensesModel hardening
- AttacksPrompt injection
- DefensesarXiv 2609.07529
CoER：用对抗协同演化与精炼防御自适应间接提示注入
提出 CoER，用对抗共进化与精炼训练工具智能体抵御自适应间接提示注入
- arXiv
- 2609.07529
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Qwen3.5-9B
- DefensesModel hardening
- AttacksPrompt injection
- DefensesarXiv 2609.02786
SafeEvolve：基于智能体经验的 Harness-Policy 协同演化安全对齐框架
提出 SafeEvolve，用轨迹证据协同演化安全 harness 与策略
- arXiv
- 2609.02786
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Qwen3.5-4B, Qwen3-4B-Instruct-2507, Qwen3.5-1.7B and others4
- DefensesModel hardening
- AttacksPrompt injection
AbstractSafeEvolve 用轨迹证据协同更新安全 harness 和策略，在两个 4B 模型的智能体安全基准上改变安全与效用。
SafeEvolve 把已完成的 on-policy 轨迹变成安全 harness 的有界更新，并用两阶段 SFT-RL 把这些更新内化进工具使用策略。
- DefensesarXiv 2609.22178
SCOPE：训练有能力且安全的计算机使用智能体
提出 SCOPE，联合后训练计算机使用智能体的任务能力与安全决策
- arXiv
- 2609.22178
- Published
- Layer
- Application layer
- Setting
- Browser and computer use
- Evaluated models
- SCOPE-mid-checkpoint, SCOPE-Capability-Safety, SCOPE-RL
- DefensesModel hardening
- AttacksPrompt injection
- DefensesarXiv 2608.21500
SecOPD 用同策略蒸馏把自适应提示注入攻击成功率降至 9.0%
提出同策略蒸馏防御微调方法 SecOPD，抵御自适应提示注入
- arXiv
- 2608.21500
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- SecOPD
- DefensesModel hardening
- AttacksPrompt injection
You have reached the end