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

Oct 12 · Monday

All papers

Found 91 papers

Filter3

System component

MCP and skills15 Memory17 RAG16 Guardrails and judges80 Monitors22 Reasoning chains26 Permissions and sandboxing16 Fine-tuning and open weights12 Vision39 Audio8 Image generation22 Multimodal68

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.

Attack surface / entry point：User input System component：Guardrails and judges System component：Fine-tuning and open weights Clear all

Another 265papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.12644Oct 9
Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.
Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.
arXiv
2610.12644
Published
Oct 9
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentReasoning chains
AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.
Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.
Paper analysisRead analysis
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 2610.09167Oct 7
Persist-3 用顺序检验识别未见越狱来源，提升 MTK 与 Prompt Guard 2 防御效果
提出 Persist-3 序贯检验，从隐藏表示识别未见越狱源
arXiv
2610.09167
Published
Oct 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama2-7B-chat, Qwen2.5-7B-Instruct, Gemma-2-9B-it and others4
- DefensesMonitoring and auditing
- AttacksJailbreaks
- ComponentMonitors
AbstractPersist-3 用有限窗口检验攻击流是否超出已知越狱源，检出率低于全历史 SR-DKW，但决策只依赖最近观测。
Persist-3 是一个有限记忆的序贯检测器，用来判断攻击表示流是否已经不能由任何一个已知越狱源解释。。
Paper analysisRead analysis
AttacksarXiv 2610.07723Oct 6
Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.
提出回答端后门，让模型自生成触发词以在干净有害请求下绕过拒答
arXiv
2610.07723
Published
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-2-7B-chat-hf, Mistral-7B-Instruct-v0.3, Gemma-7B-it and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract论文提出了多轮对话中回答端自生成触发词绕过安全拒绝的后门攻击，指出输入端防护存在盲区。
Paper analysisRead analysis
DefensesarXiv 2610.07657Oct 6
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
Oct 6
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。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06503Oct 5
研究评测五款开源文生图模型的有害内容生成与审核缺口
评测文生图模型的有害内容生成能力与审核检测缺口
arXiv
2610.06503
Published
Oct 5
Layer
Model layer
Setting
Models and APIs
Evaluated models
SDXL, Stable Diffusion 3.5 Large, FLUX.1-dev and others12
- DefensesDetection and filtering
- AttacksMalicious use
- ComponentImage generation
Paper analysisRead analysis
AttacksarXiv 2610.05943Oct 5
CRIME 框架利用良性 Agent 技能组合诱发恶意行为
提出 CRIME 框架，组合良性 Agent 技能诱发恶意行为
arXiv
2610.05943
Published
Oct 5
Layer
Application layer
Setting
AI Agent
Evaluated models
DeepSeek-V4-Flash, GPT-4o-mini, GPT-4o and others6
- AttacksJailbreaks
- TechniqueAutomated search
- ComponentMCP and skills
Abstract良性技能经 DCA 或 ACA 组合后可产生恶意环境后果，单独审查对不上。
CRIME 把公共技能库中各自通过审查的技能配成两两组合，看联合执行能否实现指定恶意任务。。
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 2610.03434Oct 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
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
DefensesarXiv 2610.00883Oct 1
DeBERTa-ConPara：面向部署的 AI 生成文本检测，推理端 Unicode 归一化提升对抗鲁棒性
提出推理时 Unicode 归一化的检测器，识别遭字符级扰动的 AI 生成文本
arXiv
2610.00883
Published
Oct 1
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
microsoft/deberta-v3-large, deberta-v3-base, bert-large-cased and others4
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
Abstract推理时归一化消除两类 Unicode 攻击，训练时归一化则会删掉对抗监督。
DeBERTa-ConPara 是一个面向部署的 AI 文本检测器：DeBERTa-v3-large 在多数据集原始文本上训练，推理前做确定性 Unicode 归一化，用一个固定阈值面对没有目标域标签的场景。
Paper analysisRead analysis
DefensesarXiv 2609.39548Sep 30
NDDL：用正常扩散动力学为文生图模型做后门防御
提出 NDDL，用良性扩散轨迹检测文生图后门提示并定位触发 token
arXiv
2609.39548
Published
Sep 30
Layer
Model layer
Setting
Models and APIs
Evaluated models
Stable Diffusion v1.5, Stable Diffusion XL, Stable Diffusion v3.5 and others4
- DefensesMonitoring and auditing
- AttacksPoisoning and backdoors
- ComponentImage generation
AbstractNDDL 从良性扩散轨迹学习正常转移，用动态不一致检测后门并定位触发 token。
NDDL 是面向文生图扩散模型的后门防御：防御者只有白盒模型访问和良性提示词，没有后门先验，需要区分后门提示词并找出触发 token。
Paper analysisRead analysis
AttacksarXiv 2609.38253Sep 29
CollageAttack: Exploiting cross-modal alignment defects for spatial text composition jailbreaks against T2I models.
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
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
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

AI Safety Daily

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

All papers

Attack type

Attack technique

Defense type

Impact

System type

Attacker access

Attack surface / entry point

Layer

System component

Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.

The paper proposes an option channel attack: changing one option label can make an agent guardrail allow a prohibited operation

EpiReal-Bench：商用图像生成模型虚假声明红队基准

BRANCH 方法绕过 6 套多扫描器护栏系统

Persist-3 用顺序检验识别未见越狱来源，提升 MTK 与 Prompt Guard 2 防御效果

Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.

DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

研究评测五款开源文生图模型的有害内容生成与审核缺口

CRIME 框架利用良性 Agent 技能组合诱发恶意行为

论文研究 LLM 数字孪生参与增强民主时的提示注入脆弱性

Persona Guardrail：面向智能体系统的生产级防御框架

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

论文提出 LLM 输入扰动鲁棒性度量，并发布 ASA 攻击与 AttestMCP 防护

MOMAT：面向量化 LLM 低功耗越狱防御的多图集混合框架

DeBERTa-ConPara：面向部署的 AI 生成文本检测，推理端 Unicode 归一化提升对抗鲁棒性

NDDL：用正常扩散动力学为文生图模型做后门防御

CollageAttack: Exploiting cross-modal alignment defects for spatial text composition jailbreaks against T2I models.

研究评估 GradSafe 在多轮对话中的越狱检测脆弱性

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

研究发现护栏模型在基座模型不确定处过度自信