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.
RAG-PIBench：可信 RAG 系统中提示注入检测的泄漏感知基准
提出 RAG-PIBench，评测 RAG 上下文中提示注入检测器
- arXiv
- 2610.08571
- Published
- Layer
- Application layer
- Setting
- LLM applications
- Evaluated models
- DistilBERT-base-uncased, DeBERTa-v3-base, MiniLM
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentRAG
- DefensesarXiv 2610.07657
DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降
实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击
- arXiv
- 2610.07657
- Published
- Layer
- Application layer
- Setting
- Multi-agent systems
- Evaluated models
- Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentGuardrails and judges
AbstractDEFER 把确定性检查放在 judge 之前。
DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。
- 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
AgentSpy: Observing AI agent behavior at the system call layer and detecting skill injection attacks
提出 AgentSpy，在系统调用层观测 Agent 行为并检测技能注入
- arXiv
- 2610.06001
- Published
- Layer
- Application layer
- Setting
- coding agent
- Evaluated models
- gpt-5.6-terra, deepseek-v4-flash, glm-5.3-flash and others4
- DefensesDetection and filtering
- AttacksPoisoning and backdoors
- ComponentMCP and skills
Abstract提出了系统级智能体监控框架 AgentSpy，揭示出通过测试背后的非预期行为与注入风险。
本研究提出了面向 AI 智能体的系统级外部监控与行为分析框架 AgentSpy。
- 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 2610.03073
SecJev：为 System One 决策模型引入安全专业知识
提出 SecJev，用场景加权训练把决策模型适配为安全类型化判断
- arXiv
- 2610.03073
- Published
- Setting
- Models and APIs
- Evaluated models
- SecJev-0.8B, SecJev-2B, SecJev-4B and others4
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
AbstractSecJev 用共享打分器做安全决策，0.8B 的 task-macro 超过 Kev-9B。
SecJev 是 0.8B 到 9B 的安全决策模型族，作者称据其所知是首个面向安全的 Jev-like 家族。
- DefensesarXiv 2610.02432
论文提出 LLM 输入扰动鲁棒性度量，并发布 ASA 攻击与 AttestMCP 防护
提出 ASA 与 AttestMCP，度量并降低 LLM 对输入序列扰动的敏感
- arXiv
- 2610.02432
- Published
- Layer
- Application layer
- Setting
- LLM applications, AI Agent
- Attacker
- Black-box
- Evaluated models
- Gemma-3-27B-Instruct, Gemma-3-4B-Instruct, Llama-3.2-3B-Instruct and others12
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
研究重测 15 个提示注入检测器：基准分数难以预测 Agent 部署表现
重测提示注入检测器在 Agent 工具输出上的检出与任务阻断
- arXiv
- 2610.03448
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Horizon-Labs, Wolf Defender, Prismor-1.5B and others15
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract论文揭示公开基准无法反映智能体检测器表现，检测能力源于输入格式相似而非通用防御，建议基于工具输出与低误报评测。
- 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 2609.33039
TACIT：从 LLM 内部状态检测 Agent 轨迹危害
提出 TACIT，从冻结内部状态检测智能体有害轨迹
- arXiv
- 2609.33039
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Qwen3-4B, Llama-3.1-8B, Qwen3-4B-Instruct and others4
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract提出基于内部表征的智能体轨迹安全检测方法 TACIT，揭示工具风险表征特性并在多项基准上提升检测表现与效率。
- DefensesarXiv 2609.30657
研究者提出面向邮件 Agent 的攻击链建模提示注入检测框架
提出面向邮件 Agent 的攻击链提示注入检测框架
- arXiv
- 2609.30657
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Proposed framework
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract攻击链与动作一致性融合改善了严格检测的平均 F1，但迁移、误报和攻击召回仍需分别看。
这是一项邮件智能体提示注入防御的离线建模与评测研究：作者把攻击文本是否恶意、攻击是否推进到工具操作、最终参数是否达标分开处理。
Jev 被用于零样本检测十类对齐失败，中位 AUROC 达 0.886
提出 RLCDAlignBench，零样本检测多种对齐失败
- arXiv
- 2609.29429
- Published
- Layer
- Prompt layer
- Setting
- Models and APIs
- Evaluated models
- Jev (jev-1.13.0)
- DefensesDetection and filtering
- AttacksJailbreaks
- RiskMisalignment and value divergence
- ComponentGuardrails and judges
Abstract一次通用问题已能给多数对齐失败排序，大的误差来自状态和标签。
RLCDAlignBench 测量用强化学习做校准决策的 Jev，能否当作对齐失败的零样本检测器。
- AttacksarXiv 2609.22510
特拉维夫大学提出爆炸性提示词：条件触发的间接提示注入可绕过九款生产 Agent
提出条件触发的爆炸提示词，并设计摄入期检测器 DeFuse
- arXiv
- 2609.22510
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Llama-3.1-8B-Instruct, Llama-3.1-70B-Instruct, Qwen2.5-32B-Instruct and others15
- DefensesDetection and filtering
- AttacksPrompt injection
- TechniqueDormant triggers
- ComponentGuardrails and judges
Abstract论文揭示了条件触发使提示注入绕过防御并在触发时执行工具，提出轻量检测器并在摄入期有效防范。
论文针对大语言模型智能体面临的间接提示注入威胁，研究了利用条件句式实现时间分离的爆炸提示词。
- DefensesarXiv 2609.21088
Provenance-Aware Transformers：用来源感知架构分离可信边界以防御间接提示注入
提出 Provenance-Aware Transformers，隔离不可信来源防御间接提示注入
- arXiv
- 2609.21088
- Published
- Layer
- Application layer
- Setting
- LLM applications
- Evaluated models
- SmolLM2-360M-Instruct, LLaMA-3-8B-Instruct, Qwen2.5-7B-Instruct and others4
- DefensesInstruction–data separation
- AttacksPrompt injection
- DefensesarXiv 2609.16098
研究者提出面向工具集成 LLM Agent 的通用对抗攻击防御方法
提出 ATF 与 NTR，过滤或恢复工具集以阻止 Agent 调用攻击工具
- arXiv
- 2609.16098
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- Gemma2-9B, Qwen2-7B, LLaMA3-8B and others7
- DefensesPermissions and approval
- AttacksPrompt injection
PIDS-Bench：在过度防御、混淆与分布偏移下评测提示注入检测器
提出 PIDS-Bench，评测提示注入检测器在过度防御与分布偏移下的表现
- arXiv
- 2609.15017
- Published
- Layer
- Application layer
- Setting
- LLM applications
- Evaluated models
- TF-IDF + logistic regression, DistilBERT, DeBERTa-v3-FT and others7
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
AbstractPIDS-Bench 显示高分布内 F1 仍会过度拦截外部来源的安全相关良性输入。
PIDS-Bench 是一个冻结的检测器级基准，用来在固定阈值下同时看提示注入检测和良性误报。
- DefensesarXiv 2609.14987
ActGuard：面向 LLM Agent 间接提示注入的执行前动作审计框架
提出 ActGuard 执行前动作审计，定位并遮盖间接提示注入的恶意片段
- arXiv
- 2609.14987
- Published
- Layer
- Application layer
- Setting
- AI Agent
- Evaluated models
- GPT-4o-mini, Gemini-2.5-Flash, DeepSeek-V4-Flash
- DefensesMonitoring and auditing
- AttacksPrompt injection