Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.

Attack type：Jailbreaks Attack type：Extraction and theft Defense type：Detection and filtering Defense type：Permissions and approval Clear all

Another 240papers do not have category tags yet and are not included in filtered results.

DefensesarXiv 2610.07532Oct 6
LADE：用暗知识中的模型无关潜在安全信号防御 LLM 越狱
提出 LADE，用首 token 暗知识在生成前过滤越狱查询
arXiv
2610.07532
Published
Oct 6
Layer
Prompt layer
Setting
Models and APIs
Attacker
White-box
Evaluated models
Llama-2-7B-Chat, Llama-3-8B-Instruct, Qwen2-7B-Instruct and others13
- DefensesDetection and filtering
- AttacksJailbreaks
Abstract作者用 LADE 在生成前过滤有害查询，并称八个模型中六个的 Held-out 平均最好。
LADE 是一种只读首 token 输出概率的防御，用来在生成前挡下可能引出有害回复的查询。
Paper analysisRead analysis
DefensesarXiv 2610.03434Oct 2
Persona Guardrail：面向智能体系统的生产级防御框架
提出 Persona Guardrail，强制客服智能体守住功能边界
arXiv
2610.03434
Published
Oct 2
Layer
Application layer
Setting
AI Agent
Attacker
Black-box
Evaluated models
Qwen3-30B-A3B, Qwen3-VL-30B, Qwen3-8B and others5
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
AbstractPersona Guardrail 用功能边界做同步输入输出校验，并在 PAGE 与生产延迟预算下给出评测。
Persona Guardrail 是客服向智能体的同步运行时防御：先写明功能边界，再决定放行或拦截，而不是只检测某一攻击类。
Paper analysisRead analysis
DefensesarXiv 2610.02853Oct 2
研究提出基于收缩约束状态空间模型的有界可达性与越狱检测方法
提出收缩约束 SSM 安全头，认证嵌入扰动并检测越狱
arXiv
2610.02853
Published
Oct 2
Layer
Prompt layer
Setting
Models and APIs
Attacker
White-box, Black-box
Evaluated models
ToySSMClassifier, S4 safety head
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
Abstract收缩给出玩具 LTI 的有界认证。
给 SSM 安全头一个收缩条件，并在越狱检测上使用收缩正则的 S4 头。。
Paper analysisRead analysis
DefensesarXiv 2610.01058Oct 1
MOMAT：面向量化 LLM 低功耗越狱防御的多图集混合框架
提出 MOMAT 多图集检索与轻量判定，防御量化模型越狱
arXiv
2610.01058
Published
Oct 1
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Llama2-13B, Llama2-7B, Mistral-7B
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.36849Sep 29
研究评估 GradSafe 在多轮对话中的越狱检测脆弱性
评测多轮对话中 GradSafe 越狱检测的可分性与脆弱性
arXiv
2609.36849
Published
Sep 29
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Llama 3.1 8B Instruct, Qwen2.5-7B-Instruct
- DefensesDetection and filtering
- AttacksJailbreaks
- TechniqueMulti-turn escalation
- ComponentGuardrails and judges
AbstractCWS 显示不安全梯度在真实多轮流量中变弱，且随攻击族和模型而变。
作者评估梯度越狱检测从单条提示词迁到多轮对话后还剩多少可分性，方法是用 Context Window Scanner 把 GradSafe 原封不动地套到用户轮窗口上。
Paper analysisRead analysis
DefensesarXiv 2609.36562Sep 29
ThinkingGuard：通过逐步风险归因解码多模态大语言模型中的隐式危害
构建 TriggerBench 并训练 ThinkingGuard，检测图文隐式风险
arXiv
2609.36562
Published
Sep 29
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
ThinkingGuard（Qwen3-VL-8B-Instruct）
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
AbstractTriggerBench 隔离触发条件，ThinkingGuard 用分步归因在隐式风险检测上取得作者报告的较高平均分。
这篇工作研究多模态隐式风险检测：图文各自良性，风险只在关键元素与触发元素交互时出现。
Paper analysisRead analysis
DefensesarXiv 2609.38239Sep 29
推理层安全：防御对抗性推理与基础设施滥用
用 SCM 合成会话并训练检测器识别推理层滥用
arXiv
2609.38239
Published
Sep 29
Layer
Infrastructure layer
Setting
Models and APIs
Evaluated models
gradient-boosted detector (GBDT/XGBoost)
- DefensesDetection and filtering
- AttacksJailbreaks
Paper analysisRead analysis
Analysis and theoryarXiv 2609.36477Sep 29
研究发现护栏模型在基座模型不确定处过度自信
诊断护栏相对基座在对抗提示上的置信失校
arXiv
2609.36477
Published
Sep 29
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama-Guard 7B, Llama-Guard-2 8B, Llama-Guard-3 8B and others10
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
Abstract对抗包装使 guard 高置信漏检，而对应 base 在同一输入上常更不确定。
诊断性分析：五个提示词分类 guard 的置信度，在清洁输入上可以较校准，在越狱包装后则变成高置信度的错误判定。
Paper analysisRead analysis
DefensesarXiv 2609.34518Sep 28
SEAD 论文提出工具型 Agent 的状态视角攻击与防御方法 DART 与 SAGE
提出工具型 Agent 的自适应攻击 DART 与预执行防御 SAGE
arXiv
2609.34518
Published
Sep 28
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-5.6 Luna, GPT-5.6 Terra, Gemini 3.8 Flash and others5
- DefensesPermissions and approval
- AttacksJailbreaks
- ComponentPermissions and sandboxing
Abstract论文提出状态控制框架 SEAD、攻击 DART 与防御 SAGE，实验显示执行反馈与环境探测在攻防交互中具有关键作用。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.29429Sep 24
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
Sep 24
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。
Paper analysisRead analysis
DefensesarXiv 2609.28693Sep 24
skilder：以角色化技能包为工具型 LLM 智能体做访问控制
提出 Skilder，按角色渐进下发企业工具并确定性拦截越权调用
arXiv
2609.28693
Published
Sep 24
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Haiku 4.5, Qwen 3.5 122B, Gemma 4 31B and others6
- DefensesPermissions and approval
- AttacksJailbreaks
- ComponentMCP and skills
AbstractSkilder 用单 MCP 服务器按角色交付工具并硬拦截。
Skilder 把企业工具型智能体的能力按角色打包，经一个 MCP 服务器做渐进发现，使工具范围由服务器而不是提示词来执行。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.22076Sep 19
APort Vault released: evaluating AI agent payment authorization with 4,371 human-written attacks
构建 APort Vault 基准，对比支付智能体模型拒答与确定性授权
arXiv
2609.22076
Published
Sep 19
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Fable 5.1, Claude Sonnet 5, Claude Haiku 4.5 and others14
- DefensesPermissions and approval
- AttacksJailbreaks
- ComponentPermissions and sandboxing
Paper analysisRead analysis
DefensesarXiv 2609.21484Sep 18
HE-Guardrail：面向加密大模型推理的同态护栏防御越狱攻击
提出 HE-Guardrail，在密文推理中评估越狱护栏并门控回复
arXiv
2609.21484
Published
Sep 18
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Llama-3-8B-Instruct, Llama Guard 3-8B
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
Abstract密文护栏门控 HE-LLM 回复。
把越狱护栏装进同态加密 LLM 推理：服务器不解密，也能按安全决策决定客户端看到目标回复还是拒绝回复。
Paper analysisRead analysis
DefensesarXiv 2609.14003Sep 12
FlowSeal：用信息流控制阻断 LLM Agent 的隐私泄露
提出 FLOWSEAL，用工具级信息流控制阻断智能体隐私泄露
arXiv
2609.14003
Published
Sep 12
Layer
Application layer
Setting
AI Agent
Evaluated models
DeepSeek-V3.2, GPT-4.1-mini, Gemini-Flash-2.5
- DefensesInstruction–data separation
- AttacksJailbreaks
- ComponentPermissions and sandboxing
Abstract作者分析大模型智能体隐私检查与攻击面重合问题，提出外部拦截防御 FLOWSEAL 并验证有效性。
Paper analysisRead analysis
DefensesarXiv 2609.10613Sep 8
后验重加权框架解释并缓解多模态大模型上下文越狱
用后验重加权解释多模态上下文越狱，并提出风险门控的良性示例注入防御
arXiv
2609.10613
Published
Sep 8
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Qwen3-VL-2B, Qwen3-VL-4B, Qwen3-VL-8B and others8
- DefensesInstruction–data separation
- AttacksJailbreaks
- ComponentVision
Abstract后验重加权解释上下文越狱的缩放，并支持风险门控的良性示例防御。
Zhang 等把多模态 ICL 越狱写成对齐模型在安全与有害隐模式之间的推理时后验漂移，并据此做风险门控防御。
Paper analysisRead analysis
DefensesarXiv 2609.06540Sep 6
SRD-GUARD：通过语义改写与多模型联合评分暴露潜在意图的 LLM 防御框架
提出 SRD-GUARD，以语义改写与多模型联合评分拦截包装式越狱
arXiv
2609.06540
Published
Sep 6
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Llama-3-8B-Uncensored, DeepSeek-V4-Flash
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
Paper analysisRead analysis
DefensesarXiv 2609.05903Sep 5
EvoSafeHarness：为 Agent 自动演化模型与领域专属安全护栏
为冻结模型与目标域自动搜索可部署的 Agent 安全 harness
arXiv
2609.05903
Published
Sep 5
Layer
Application layer
Setting
AI Agent
Evaluated models
Sonnet 4.6, GLM-5, Kimi-K2.5 and others11
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Paper analysisRead analysis
DefensesarXiv 2609.01046Sep 1
HiveTraceGuard-Pro：面向提示注入、越狱与对抗混淆的紧凑生成式护栏
提出生成式护栏 HiveTraceGuard-Pro，检测提示注入、越狱与混淆
arXiv
2609.01046
Published
Sep 1
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
HiveTraceGuard-Pro (0.6B)
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
Abstract0.6B 俄英护栏在自建俄语干净集和 PI-RU 上得分最高，聚合 key 居第三，过阻断和回复精度仍是作者标出的短板。
HiveTraceGuard-Pro 是面向请求与回复审核的 0.6B 生成式护栏，由 Qwen3-0.6B 经 LoRA 微调，在俄语和英语上训练，只输出一个 safe/unsafe 裁决。
Paper analysisRead analysis
DefensesarXiv 2609.01677Sep 1
Skill-as-API：面向智能体软件工程的机密多智能体协作协议
提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词
arXiv
2609.01677
Published
Sep 1
Layer
Application layer
Setting
Multi-agent systems, coding agent
- DefensesInstruction–data separation
- AttacksExtraction and theft
- ComponentMCP and skills
Abstract协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。
Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。
Paper analysisRead analysis
DefensesarXiv 2608.17829Aug 18
LeakGauge：用行为探针在解码前检测上下文泄露攻击信号
提出 LeakGauge，用行为后缀的 prefill 对数概率检测上下文泄露
arXiv
2608.17829
Published
Aug 18
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Gemma-4-E4B-it, Gemma-4-31B-it, Qwen2.5-14B-Instruct and others11
- DefensesDetection and filtering
- AttacksExtraction and theft
- ComponentRAG
Paper analysisRead analysis

AI Safety Daily

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