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

Oct 12 · Monday

All papers

Found 316 papers

Filter4

Attack type

Jailbreaks66 Prompt injection47 Poisoning and backdoors22 Model tampering4 Extraction and theft12 Detection evasion16 Denial of service4 Malicious use10

Attack technique

Gradient and representation optimization32 Automated search15 Multi-turn escalation6 Encoding and obfuscation17 Role-play and persuasion5 Conversation structure manipulation4 Reasoning-chain manipulation13 Cross-modal payloads54 Defense-targeted6 Dormant triggers7

Model risks

Deception and scheming34 Reward hacking18 Misalignment and value divergence7 Dangerous agent actions18 Inappropriate refusal14 Hallucination and fabrication16 Bias and discrimination3

Defense type

Model hardening27 Inference-time intervention18 Detection and filtering17 Instruction–data separation6 Permissions and approval6 Monitoring and auditing60

Impact

Harmful content75 Unauthorized actions38 Data and privacy leaks22 Output manipulation75 Availability and reliability12 Oversight failure46

System component

MCP and skills82 Memory78 RAG51 Guardrails and judges169 Monitors92 Reasoning chains75 Permissions and sandboxing93 Fine-tuning and open weights64 Vision137 Audio38 Video13 Image generation49 Embeddings13 Multimodal224

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.

System component：Monitors System component：Reasoning chains System component：Vision System component：Audio Clear all

Another 255papers 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
DefensesarXiv 2610.12463Oct 9
Paper reviews OpenAI, Anthropic, and Google agent safety incidents and proposes the PASAC framework
Proposes PASAC and a five-layer boundary guarantee stack, turning agent evaluation overstepping into verifiable whole-system guarantees.
arXiv
2610.12463
Published
Oct 9
Layer
Application layer
Setting
AI Agent
- DefensesPermissions and approval
- RiskDangerous agent actions
- ComponentPermissions and sandboxing
Paper analysisRead analysis
DefensesarXiv 2610.12445Oct 9
FAR.AI paper: white-box probes surpass Opus 5.5 text monitoring on SHADE-Arena with 98.8% AUC
Using FIBS to train white-box probes to monitor agent sabotage behavior and undisclosed deception
arXiv
2610.12445
Published
Oct 9
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen3.5-397B-A17B, Qwen3.5-122B-A10B, Qwen3.5-27B and others10
- DefensesMonitoring and auditing
- RiskDeception and scheming
- ComponentMonitors
Paper analysisRead analysis
InterpretabilityarXiv 2610.12361Oct 9
Study: legal reasoning models citing legal provisions does not equal relying on legal provisions.
Uses premise permutation and hidden-layer tracing to audit whether legal chain-of-thought truly relies on the cited legal provisions.
arXiv
2610.12361
Published
Oct 9
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3-8B, Qwen3-14B, Llama-3.1-8B and others7
- AttacksPrompt injection
- ComponentReasoning chains
AbstractUsing counterfactual substitution of authorities and internal commitment tracing, the authors find that legal CoT rulings depend on authorities only to a limited extent and are vulnerable to prompt injection manipulation.
This study conducts an empirical audit of the causal truthfulness of legal citations in chain-of-thought reasoning of large language models in the legal domain.
Paper analysisRead analysis
InterpretabilityarXiv 2610.11986Oct 8
FearCaut-Qwen: Activation steering changes the risk judgment criteria of vision-language models
Using fear activation steering to test the hazard judgment criteria of vision-language models
arXiv
2610.11986
Published
Oct 8
Layer
Model layer
Setting
LLM applications
Evaluated models
Qwen/Qwen2.5-VL-7B-Instruct
- ComponentVision
Paper analysisRead analysis
DefensesarXiv 2610.11942Oct 8
LGWM: Verifying GUI agent screen transitions with action-conditioned world models
Proposes LGWM, using an action-conditioned world model to verify GUI agent screen transitions.
arXiv
2610.11942
Published
Oct 8
Layer
Application layer
Setting
Browser and computer use
Evaluated models
LGWM
- DefensesMonitoring and auditing
- AttacksPrompt injection
- ComponentMonitors
Paper analysisRead analysis
Analysis and theoryarXiv 2610.11765Oct 8
研究提出三项指标衡量 LLM 不思考行为，发现被要求停止思考时仍持续显式推理
度量关闭思考指令下终答前是否仍有可见显式推理
arXiv
2610.11765
Published
Oct 8
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3-4B, Qwen3-32B, Qwen3-235B-A22B and others6
- ComponentReasoning chains
Abstract作者用三级指标测 no-thinking，并称模型有随答案空间加重的思考惯性。
作者把 no-thinking 定义为可测量的回答行为，而不是从思考开关、特殊标记或输出长度推断。
Paper analysisRead analysis
DefensesarXiv 2610.11352Oct 8
RL-ARC：用推理引导的不确定性校准大型推理模型
提出 RL-ARC，用推理置信度在强化学习中校准推理模型
arXiv
2610.11352
Published
Oct 8
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen2.5-7B, Qwen3-8B, Llama-8B distilled from DeepSeek-R1
- DefensesModel hardening
- ComponentReasoning chains
AbstractRL-ARC 用推理置信度调节答案置信度，作者称可少牺牲精度并改善 ID 与 OOD 校准。
RL-ARC 是校准感知的强化学习框架，用推理过程的口头置信度调节答案置信度。
Paper analysisRead analysis
InterpretabilityarXiv 2610.10865Oct 8
用路由稀疏自编码器解耦语音编码器中的语言学与副语言学信息
提出路由 TopK SAE，把语音编码器稀疏码拆成语言与副语言通路
arXiv
2610.10865
Published
Oct 8
Layer
Model layer
Setting
Models and APIs
Evaluated models
SPEAR XLarge, WavLM Large
- ComponentAudio
Abstract路由 SAE 在冻结 SPEAR 与 WavLM 上分开语言和副语言因子，探针与交换支持通路分工。
TopK SAE 的稀疏码被分成语言通路与副语言通路，用来分开冻结语音编码器里同时存在的音素信息和说话人、情感、韵律。只重构不能得到作者选定的这一分解。语言通路由音素识别监督，副语言通路由说话人识别、情感分类和韵律预测监督，作用在对方通路上的梯度反转对抗用来压低交叉因子。
Paper analysisRead analysis
Analysis and theoryarXiv 2610.10405Oct 8
研究发现大语言模型被要求不诚实作答时推理 token 数上升
检验推理 token 数能否区分被提示的诚实与不诚实作答
arXiv
2610.10405
Published
Oct 8
Layer
Model layer
Setting
Models and APIs
Evaluated models
Gemma-4-e4b, Qwen-3.5-9b, GPT-OSS-120B
- RiskDeception and scheming
- ComponentReasoning chains
Abstract被提示不诚实时推理 token 组水平更高。
三个推理模型在被提示的回答政策下出现组水平推理 token 差异。作者把它当作不读思维链内容的 black-box 候选信号，而不是自发欺骗检测器。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.10358Oct 8
Open-MMUnlearning 发布：统一多模态大模型遗忘方法与评测框架
提出统一框架评测多模态大模型的遗忘方法
arXiv
2610.10358
Published
Oct 8
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
LLaVA-1.5-7B
- DefensesModel hardening
- ComponentVision
Paper analysisRead analysis
DefensesarXiv 2610.09941Oct 7
OrthoPurify 用一步正交投影净化被后门污染的视觉语言模型
提出 OrthoPurify，用正交投影清除视觉语言模型适配器中的劫持方向
arXiv
2610.09941
Published
Oct 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
LLaVA-1.5-7B, Qwen3-VL-8B, LLaVA-1.5-13B and others5
- DefensesModel hardening
- AttacksPoisoning and backdoors
- ComponentFine-tuning and open weights
Abstract一次投影去掉劫持方向。
OrthoPurify 是部署前的 LVLM 后门净化方法，用一次正交投影去掉被劫持的权重更新方向。
Paper analysisRead analysis
AttacksarXiv 2610.09920Oct 7
研究：多向量视觉文档索引可被反演还原页面内容
提出流匹配逆向框架，从多向量视觉文档索引重构页面
arXiv
2610.09920
Published
Oct 7
Layer
Application layer
Setting
LLM applications
Evaluated models
Tomoro-ColQwen3-8B, ColQwen3.5-4.5B, Tomoro-colqwen3-embed-4b and others13
- AttacksExtraction and theft
- ComponentEmbeddings
Paper analysisRead analysis
AttacksarXiv 2610.09819Oct 7
FAB 攻击：给 HuBERT/WavLM 植入后门，背景警笛声即可让下游语音任务失灵
提出 FAB 攻击，向声学基础模型植入可由环境声触发的后门
arXiv
2610.09819
Published
Oct 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
HuBERT-base, WavLM-base
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentAudio
Abstract论文提出了针对声学基模的 FAB 后门攻击，在弱威胁模型下实现了任务无关、物理可触发的后门植入。
Paper analysisRead analysis
DefensesarXiv 2610.09793Oct 7
用时序逻辑监控工具 Agent
提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链
arXiv
2610.09793
Published
Oct 7
Layer
Application layer
Setting
AI Agent
Attacker
Black-box
- DefensesMonitoring and auditing
- AttacksPrompt injection
- ComponentMonitors
Abstract形式化验证可有效识别多步攻击，但其有效性高度依赖轨迹的可信历史记录。
这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。
Paper analysisRead analysis
AttacksarXiv 2610.09708Oct 7
研究者提出利用祖先 VLM 的黑盒对抗补丁攻击，可降低 VLA 任务成功率
提出利用祖先 VLM 优化对抗补丁，使已部署 VLA 任务失败
arXiv
2610.09708
Published
Oct 7
Layer
Prompt layer
Setting
Embodied systems and robotics
Evaluated models
OpenVLA, UniVLA, π0.5
- TechniqueGradient and representation optimization
- ComponentVision
Paper analysisRead analysis
DefensesarXiv 2610.09703Oct 7
研究揭示 Token-Pruning 对 VLM 安全性的影响并提出 SAP 缓解机制
提出 Safety-Aware Pruning，缓解视觉 token 剪枝放大的多模态越狱
arXiv
2610.09703
Published
Oct 7
Layer
Model layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
LLaVA-1.5-7B
- DefensesInference-time intervention
- AttacksJailbreaks
- ComponentVision
Abstract剪枝去掉背景 token 后注意力塌向恶意前景。
这篇工作评估视觉 token 剪枝如何改变 VLM 在多模态越狱下的行为，并给出推理时防御 SAP。
Paper analysisRead analysis
Analysis and theoryarXiv 2610.09667Oct 7
东京大学研究：推理模型按 UUID 阈值或整除规则挑选审计样本，控制标识符即可躲开复核
揭示推理模型用标识符规则替代随机抽样，使审计可被预测
arXiv
2610.09667
Published
Oct 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
GPT-6 Sol, GPT-6 Luna, GPT-5.4 mini and others6
- ComponentReasoning chains
Abstract研究揭示推理智能体将标识符转化为确定性规则，破坏群体独立性并导致审计预测漏洞，建议显式提供随机输入。
Paper analysisRead analysis
Analysis and theoryarXiv 2610.09517Oct 7
审计发现 CLIP 安全分数主要反映画面与提示词场景的相似度
开环审计冻结视觉语言安全分，发现其反映场景模板而非危险感知
arXiv
2610.09517
Published
Oct 7
Layer
Model layer
Setting
Embodied systems and robotics
Evaluated models
CLIP ViT-B/32, CLIP ViT-L/14, Qwen2-VL-7B
- ComponentVision
Abstract论文审计了冻结 VLM 安全评分机制，指出其反映场景模板而非危险感知，为安全强化学习评估提供了严谨基准。
本文是一项针对安全强化学习中冻结视觉语言模型（VLM）安全评分机制的实证审计研究。
Paper analysisRead analysis
DefensesarXiv 2610.09469Oct 7
Secure-CUA: Constraining the Impact of Untrusted Content in Computer-Use Agents
提出 Secure-CUA，用动作事务约束计算机使用智能体的不可信影响
arXiv
2610.09469
Published
Oct 7
Layer
Application layer
Setting
web agent
Evaluated models
Claude Opus 5, Gemini 3.8 Flash, GPT-5.6-Sol
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentVision
AbstractSecure-CUA 用每步事务约束不可信影响，良性 TSR 接近 Vanilla-CUA。
Secure-CUA 要限制图形界面里不可信内容对 CUA 决策和 GUI 执行的影响，同时保留合法任务所需的不可信信息。
Paper analysisRead analysis

AI Safety Daily

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

All papers

Attack type

Attack technique

Model risks

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.

Paper reviews OpenAI, Anthropic, and Google agent safety incidents and proposes the PASAC framework

FAR.AI paper: white-box probes surpass Opus 5.5 text monitoring on SHADE-Arena with 98.8% AUC

Study: legal reasoning models citing legal provisions does not equal relying on legal provisions.

FearCaut-Qwen: Activation steering changes the risk judgment criteria of vision-language models

LGWM: Verifying GUI agent screen transitions with action-conditioned world models

研究提出三项指标衡量 LLM 不思考行为，发现被要求停止思考时仍持续显式推理

RL-ARC：用推理引导的不确定性校准大型推理模型

用路由稀疏自编码器解耦语音编码器中的语言学与副语言学信息

研究发现大语言模型被要求不诚实作答时推理 token 数上升

Open-MMUnlearning 发布：统一多模态大模型遗忘方法与评测框架

OrthoPurify 用一步正交投影净化被后门污染的视觉语言模型

研究：多向量视觉文档索引可被反演还原页面内容

FAB 攻击：给 HuBERT/WavLM 植入后门，背景警笛声即可让下游语音任务失灵

用时序逻辑监控工具 Agent

研究者提出利用祖先 VLM 的黑盒对抗补丁攻击，可降低 VLA 任务成功率

研究揭示 Token-Pruning 对 VLM 安全性的影响并提出 SAP 缓解机制

东京大学研究：推理模型按 UUID 阈值或整除规则挑选审计样本，控制标识符即可躲开复核

审计发现 CLIP 安全分数主要反映画面与提示词场景的相似度

Secure-CUA: Constraining the Impact of Untrusted Content in Computer-Use Agents