Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 305papers have no tags yet and are not included in filtered results.

Attacker access：Black-box System component：Guardrails and judges Clear all

Another 305papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.12292Oct 9
The paper proposes an option channel attack: changing one option label can make an agent guardrail allow a prohibited operation
Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations
arXiv
2610.12292
Published
Oct 9
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
LAYA-TD, LAYA-EN, LAYA-ML and others5
- AttacksDetection evasion
- ComponentGuardrails and judges
AbstractThe authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.11112Oct 8
EpiReal-Bench：商用图像生成模型虚假声明红队基准
构建 EpiReal-Bench，评测图像生成器将虚假主张渲染为可信证据
arXiv
2610.11112
Published
Oct 8
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
GPT-Image-2, Nano Banana 2, Grok Imagen 2.0 and others4
- AttacksJailbreaks
- ComponentImage generation
Abstract四款商用图像模型能把假主张画成可信证据。
EpiReal-Bench 用来量商用图像生成器会不会把虚假现实主张画成可信视觉证据。
Paper analysisRead analysis
AttacksarXiv 2610.10742Oct 8
BRANCH 方法绕过 6 套多扫描器护栏系统
提出 BRANCH 方法，用分支搜索绕过多扫描器护栏
arXiv
2610.10742
Published
Oct 8
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Meta Llama Guard 3 8B, Meta Llama Guard 7B, Meta Llama Guard 3 1B and others18
- AttacksDetection evasion
- TechniqueAutomated search
- ComponentGuardrails and judges
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 2610.02432Oct 2
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
Oct 2
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
Paper analysisRead analysis
AttacksarXiv 2609.38253Sep 29
CollageAttack：利用跨模态对齐缺陷对 T2I 模型实施空间文本组合越狱
提出 CollageAttack，用空间文本碎片重组越狱文生图模型
arXiv
2609.38253
Published
Sep 29
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
GPT-Image-2, Doubao-Seedream-5.0-Lite, Wan2.7-Image-Pro and others5
- AttacksJailbreaks
- TechniqueEncoding and obfuscation
- ComponentImage generation
Abstract系统揭示 T2I 跨模态空间合成安全漏洞，证实离散无害元素可在图像层面重构有害意图并放大传播强度。
Paper analysisRead analysis
AttacksarXiv 2609.34920Sep 28
RISE：用迭代策略演化对现代文生图模型做红队测试
提出 RISE，迭代演化可复用策略对文生图模型做红队
arXiv
2609.34920
Published
Sep 28
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
DALL·E 3, Nano Banana 2, GPT-Image-2 and others7
- AttacksJailbreaks
- TechniqueAutomated search
- ComponentImage generation
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.09798Sep 9
CS-Guard：首个面向代码生成安全的 LLM 护栏评测基准
提出 CS-Guard 基准，评测代码生成护栏对虚构场景攻击的防御
arXiv
2609.09798
Published
Sep 9
Layer
Prompt layer
Setting
coding agent
Attacker
Black-box
Evaluated models
CodeLlama-13B-Instruct, DeepSeekCoder-V2-Lite-16B, GPT-OSS-20B and others7
- AttacksJailbreaks
- ComponentGuardrails and judges
Abstract论文提出了代码安全护栏基准 CS-Guard，评估发现现有护栏对虚构场景攻击和代码级恶意请求防御较弱。
Paper analysisRead analysis
AttacksarXiv 2609.09553Sep 9
研究：任意密文攻击前沿大模型无需微调即可越狱
提出任意字母置换密码越狱，无需微调即可诱导有害输出
arXiv
2609.09553
Published
Sep 9
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Claude Sonnet 4, Claude Sonnet 4.5, Gemini 3 Flash (preview) and others7
- AttacksJailbreaks
- TechniqueEncoding and obfuscation
- ComponentGuardrails and judges
Abstract前沿大模型无需微调即可通过提示词学会字母置换密码，进而绕过分类器与对齐，作者呼吁关注能力提升带来的安全风险。
Paper analysisRead analysis
AttacksarXiv 2609.08236Sep 8
研究：内容不变的风格包装可翻转 LLM 安全评判器的判定
提出内容不变样式包装，翻转安全评审器的判定
arXiv
2609.08236
Published
Sep 8
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
GPT-4o-mini (gpt4o), GPT-4o-mini (strongreject), DeepSeek-Chat and others7
- AttacksDetection evasion
- TechniqueRole-play and persuasion
- ComponentGuardrails and judges
Abstract论文揭示特定安全评审器易受保持内容不变的外层包装诱导改变判定，并指出安全评估应将判定稳定性作为重要考量指标。
这是一项关于大语言模型自动化安全评审系统表面样式脆弱性的评估研究。
Paper analysisRead analysis
AttacksarXiv 2609.07216Sep 7
DIVA：利用视觉锚点对视频生成模型实施多模态越狱
提出 DIVA，将有害意图拆成视觉锚点与运动文本以越狱视频生成模型
arXiv
2609.07216
Published
Sep 7
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Wan, CogVideoX, LTX-Video and others9
- AttacksJailbreaks
- TechniqueCross-modal payloads
- ComponentImage generation
AbstractDIVA 用视觉锚点抑制语义漂移做视频越狱，并给出多条件安全基准 TI2VSafetyBench。
DIVA 是针对带参考图的视频生成模型的免训练 black-box 越狱：用一致性机制本身堵住语义漂移这条安全逃逸路径。。
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
AttacksarXiv 2609.01168Sep 1
CRACK：用多智能体辩论越狱多层安全过滤的 T2I 模型
提出 CRACK，用多智能体辩论在黑盒下越狱文生图多层安全过滤
arXiv
2609.01168
Published
Sep 1
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Stable Diffusion v1.4, SDXL, DALL·E 3 and others4
- AttacksJailbreaks
- TechniqueAutomated search
- ComponentImage generation
AbstractCRACK 以分层诊断的多智能体辩论搜索多层 T2I 过滤器的联合规避区域。
CRACK 是面向文本生成图像模型多层安全栈的黑盒越狱框架，用几何上的 Detection Surface 解释为何粗粒度反馈不够。
Paper analysisRead analysis
DefensesarXiv 2608.12876Aug 13
SPARED：用对抗编辑数据训练基于推理的 AI 生成图像检测器
提出 SPARED，用对抗编辑数据训练基于推理的 AI 生成图像检测器
arXiv
2608.12876
Published
Aug 13
Layer
Training and data layer
Setting
Models and APIs
Attacker
Black-box, White-box
Evaluated models
Qwen3.5-9B
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
AbstractSPARED 用防捷径的编辑对抗环训练 9B 推理检测器。
SPARED 是一套用于可解释 AI 生成图像检测的攻防强化学习流程，报告模型是 Qwen3.5-9B 上的第三轮防御器。
Paper analysisRead analysis
AttacksarXiv 2608.09732Aug 10
ColluSkill 用跨技能组合绕过 Agent 技能扫描器
提出 ColluSkill，用跨技能组合绕过 Agent 技能扫描器
arXiv
2608.09732
Published
Aug 10
Layer
Application layer
Setting
coding agent
Attacker
Black-box, Gray-box
Evaluated models
GPT-5.5, DeepSeek-V4-Pro, GLM-5.2
- DefensesDetection and filtering
- AttacksDetection evasion
- TechniqueDefense-targeted
- ComponentMCP and skills
Abstract论文揭示了单技能孤立扫描的盲区，提出多技能链攻击 ColluSkill 与上下文防御 ChainGuard 并验证了有效性。
Paper analysisRead analysis
DefensesarXiv 2608.06422Aug 6
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
Aug 6
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。
Paper analysisRead analysis
AttacksarXiv 2607.27373Jul 30
RoguePrompt 用双层编码绕过 LLM 审核
提出 RoguePrompt 双层编码自重构越狱，绕过 LLM 审核
arXiv
2607.27373
Published
Jul 30
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
OpenAI GPT-4o (gpt-4o-2024-11-20), Anthropic Claude 3 Opus (claude-3-opus-20240229), Google Gemini 1.5 Pro (gemini-1.5-pro-002)
- AttacksJailbreaks
- TechniqueEncoding and obfuscation
- ComponentGuardrails and judges
Paper analysisRead analysis
AttacksarXiv 2606.21077Jun 19
OTTER：仅替换五个 token 即可绕过 GPT 系列毒性审核
提出 OTTER 词元替换越狱，绕过表面毒性审核诱导有害回答
arXiv
2606.21077
Published
Jun 19
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
gpt-4-turbo, gpt-4o, gpt-4o-mini and others4
- AttacksJailbreaks
- TechniqueEncoding and obfuscation
- ComponentGuardrails and judges
Abstract论文展示了表面毒性与恶意意图的解耦现象，通过标准 API 实现黑盒越狱测试，并提出闭环分类器加固建议。
Paper analysisRead analysis
AttacksarXiv 2606.16751Jun 15
UNIATTACK：面向多层防御的自动化越狱攻击框架
提出 UniAttack 单轮黑盒越狱框架，融合攻击特征绕过多层防御
arXiv
2606.16751
Published
Jun 15
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
DeepSeek-Chat, DeepSeek-Reasoner, GPT-4.1-Nano and others9
- AttacksJailbreaks
- TechniqueAutomated search
- ComponentGuardrails and judges
Paper analysisRead analysis

AI Safety Daily

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