Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 13 papers

Filter4

Attack type

Defense type

Model hardening13 Inference-time intervention5 Detection and filtering39 Instruction–data separation49 Permissions and approval69 Monitoring and auditing41 Watermarking and provenance5

Impact

Unauthorized actions6 Availability and reliability3

System type

LLM applications3 AI Agent13 coding agent0

Attack surface / entry point

Web pages and interfaces5 Tool responses6

Layer

Application layer13 Training and data layer10

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.

Defense type：Model hardening System type：AI Agent System type：coding agent Layer：Application layer Clear all

Another 255papers do not have category tags yet and are not included in filtered results.

DefensesarXiv 2610.10833Oct 8
研究：Agent 准时停机不等于有效使用时间预算
用时钟 harness 和预算塑形 GRPO 改善 Agent 的按时返回
arXiv
2610.10833
Published
Oct 8
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen3.6-27B, Qwen3-4B, Qwen3.5-9B and others4
- DefensesModel hardening
Abstract作者比较提示词、harness 与 GRPO：按时性可改善，但额外时间仍未变成更好解。
作者研究小规模 LLM 智能体在显式 wall-clock 预算下能否按时返回，并把更多时间换成更好的解。
Paper analysisRead analysis
DefensesarXiv 2610.08773Oct 7
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
Oct 7
Layer
Application layer
Setting
web agent
Evaluated models
Qwen3.5-4B
- DefensesModel hardening
- AttacksPrompt injection
Paper analysisRead analysis
DefensesarXiv 2610.06401Oct 5
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
Oct 5
Layer
Application layer
Setting
AI Agent
Evaluated models
Gemma-4-12B-it, Nemotron-3-Nano-30B-A3B, Qwen3.8-27B
- DefensesModel hardening
- AttacksPrompt injection
Paper analysisRead analysis
DefensesarXiv 2610.04412Oct 3
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
Oct 3
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。
Paper analysisRead analysis
DefensesarXiv 2610.04269Oct 3
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
Oct 3
Layer
Application layer
Setting
AI Agent
Evaluated models
SR-Agent-Llama, SR-Agent-Qwen3-8B, SR-Agent-Qwen3-4B
- DefensesModel hardening
- AttacksPrompt injection
Paper analysisRead analysis
Risky behaviorarXiv 2609.39102Sep 30
论文提出 CrossFit 缓解自演化搜索智能体的共谋作弊
提出 CrossFit，用折外求解器抑制自演化搜索智能体共作弊
arXiv
2609.39102
Published
Sep 30
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen3.5-4B, Qwen3.5-9B
- DefensesModel hardening
- RiskReward hacking
AbstractCrossFit 切断同源伪标签回流到提议者奖励的路径，并提高七个搜索基准上的 Cover-EM。
False Frontiers 诊断自进化搜索智能体中的 co-cheating，并用按来源交叉拟合的反馈来缓解它。
Paper analysisRead analysis
DefensesarXiv 2609.36820Sep 29
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
Sep 29
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。
Paper analysisRead analysis
DefensesarXiv 2609.34463Sep 28
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
Sep 28
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct
- DefensesModel hardening
- AttacksPrompt injection
Paper analysisRead analysis
DefensesarXiv 2609.07529Sep 7
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
Sep 7
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen3.5-9B
- DefensesModel hardening
- AttacksPrompt injection
Paper analysisRead analysis
DefensesarXiv 2609.02786Sep 3
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
Sep 3
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。
Paper analysisRead analysis
DefensesarXiv 2609.22178Aug 27
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
Aug 27
Layer
Application layer
Setting
Browser and computer use
Evaluated models
SCOPE-mid-checkpoint, SCOPE-Capability-Safety, SCOPE-RL
- DefensesModel hardening
- AttacksPrompt injection
Paper analysisRead analysis
DefensesarXiv 2608.21500Aug 22
SecOPD uses on-policy distillation to reduce adaptive prompt injection attack success rate to 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
Aug 22
Layer
Application layer
Setting
AI Agent
Evaluated models
SecOPD
- DefensesModel hardening
- AttacksPrompt injection
Paper analysisRead analysis
DefensesarXiv 2608.02110Aug 3
IACM-RL：面向动态意图波动下复杂工具调用的意图感知上下文管理与强化学习
提出 IACM-RL，用信念状态与强化学习改进动态意图下的复杂工具调用
arXiv
2608.02110
Published
Aug 3
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen3-8B, 1.7B Qwen
- DefensesModel hardening
Paper analysisRead analysis

You have reached the end

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop