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

Oct 13 · Tuesday

All papers

Found 138 papers

Filter6

System type

Models and APIs118 LLM applications9 AI Agent44 coding agent9 science agent5 Multi-agent systems12 Embodied systems and robotics4

Attack surface / entry point

User input17

Layer

Prompt layer7 Model layer83 Application layer17 Training and data layer31

System component

Guardrails and judges4 Monitors9 Reasoning chains6 Fine-tuning and open weights6 Vision14 Audio3 Multimodal16

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.

Model risks：Misalignment and value divergence Model risks：Inappropriate refusal Model risks：Hallucination and fabrication System type：Models and APIs System type：coding agent System type：Multi-agent systems Clear all

Another 227papers do not have category tags yet and are not included in filtered results.

InterpretabilityarXiv 2610.13078Oct 9
Attention sees, MLP refuses: tracing the safety pathway from attention to MLP in LLMs
Trace attention to identify harmfulness to the MLP refusal write pathway and propose Sentinel
arXiv
2610.13078
Published
Oct 9
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Qwen3-8B-Instruct and others18
- DefensesInstruction–data separation
- AttacksJailbreaks
- RiskInappropriate refusal
AbstractAttention updates are more readable for harmfulness, MLP updates write refusal, and Sentinel routes alerts using two-path signals.
The authors reframe jailbreaking and excessive refusal of aligned models as a pathway problem on the residual stream from recognition to writing, and accordingly provide conditional reminders before decoding.
Paper analysisRead analysis
Analysis and theoryarXiv 2610.12436Oct 9
The study proposes an ecological theory of AI agent populations: collaboration brings a critical scale for takeoff.
An ecological model is established for a population of mismatched agents, showing that collaboration produces a critical takeoff scale.
arXiv
2610.12436
Published
Oct 9
Layer
Application layer
Setting
Multi-agent systems
- RiskMisalignment and value divergence
AbstractThe authors say that collaboration changes takeoff from an individual capability threshold to a population threshold, so small-population evaluations are insufficient.
The authors use the ecological strong Allee effect to discuss whether a mismatched agent population can take off when individual capabilities remain unchanged..
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.11305Oct 8
BeliefScope：区分证据与用户压力对模型信念影响的受控框架
用 BeliefScope 分离固定命题上证据与压力对模型信念的影响
arXiv
2610.11305
Published
Oct 8
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3-8B, Llama3.1-8B, Gemma3-12B and others4
- RiskMisalignment and value divergence
AbstractBeliefScope 把证据修正与压力偏移拆成绑定评测条件的行为画像。
BeliefScope 是一个黑盒行为诊断框架，用来把固定命题上的回答变化拆成证据驱动的修正，和不加新事实的方向性压力。信念修正评测能看到信息基础变化后的更新，谄媚评测能看到用户影响下的顺从或漂移。作者认为，当两种输入都偏向同一结论时，表面偏移本身不能区分来源。
Paper analysisRead analysis
DefensesarXiv 2610.09600Oct 7
SafeEvo：从拒答回路视角解释大模型安全对齐机制与演化
用 SafeEvo 提取拒绝电路，并提出 SCA 仅微调该电路
arXiv
2610.09600
Published
Oct 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-3-8B, Qwen-2.5-7B, Mistral-7B-v0.1 and others4
- DefensesModel hardening
- RiskInappropriate refusal
AbstractSafeEvo 识别出基座模型中存在的弱安全电路及其演化动态，据此提出的 SCA 算法实现了安全对齐、能力保留与低过度拒绝的平衡。
Paper analysisRead analysis
InterpretabilityarXiv 2610.09000Oct 7
研究定位 LLaMA-2-7B-Chat 安全敏感参数
定位安全敏感参数并稀疏改动权重以削弱安全对齐
arXiv
2610.09000
Published
Oct 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
LLaMA-2-7B-Chat
- AttacksModel tampering
- RiskInappropriate refusal
Paper analysisRead analysis
Risky behaviorarXiv 2610.08670Oct 7
Study: post-training recipes determine whether large models act against their own moral judgments
提出知行差距面板，测量压力下模型是否违背自身判断
arXiv
2610.08670
Published
Oct 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
OLMo-3-7B-Instruct, Llama-3.1-8B-Instruct, Tulu 3 and others7
- RiskMisalignment and value divergence
Abstract评估发现后训练配方决定知行差距是否存在，行动前审思可有效缓解。
本文评估了开源语言模型作为智能体行动时违背自身道德判断的知行差距及其决定因素。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.08540Oct 6
The paper proposes a scaling law framework for alignment measured by risk category.
提出分风险对齐标度律框架，测量各类风险的对齐负担如何随规模变化
arXiv
2610.08540
Published
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Pythia (14m–2.8b), Qwen2.5 (0.5B–72B), Qwen2.5-Instruct (0.5B–14B) and others4
- RiskMisalignment and value divergence
Abstract论文提出了分风险对齐标度律框架，测得真实性与倾向纠错呈标度有益，但盲后门仍存活，揭示隐藏风险的长期挑战。
本文提出了一个将大语言模型对齐难度形式化为可测量标度关系的理论框架与预注册评测协议。
Paper analysisRead analysis
DefensesarXiv 2610.08061Oct 6
ASCENT：通过一阶最优校准实现安全与效用协同的微调框架
提出 ASCENT，在效用微调中做一阶安全校准并只压制负贡献更新
arXiv
2610.08061
Published
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Gemma-3-12B-it and others4
- DefensesModel hardening
- RiskInappropriate refusal
Paper analysisRead analysis
DefensesarXiv 2610.07774Oct 6
研究者提出读取路由 logits 的 MoE 视觉语言模型多模态安全检测器
AI summary研究者提出一种轻量级路由 logits 安全检测器，在提示词预填充阶段读取 MoE 视觉语言模型的专家路由信号，在生成前判断多模态请求是否安全，且不修改模型参数或专家路由。
arXiv
2610.07774
Published
Oct 6
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3-VL-30B-A3B-Instruct, Kimi-VL-A3B-Instruct
- DefensesMonitoring and auditing
- RiskInappropriate refusal
- ComponentMonitors
Abstract读出而非操纵 router logits，可在不改模型的情况下降低两模型的组合式安全错误。
作者在两个指令微调 MoE VLM 上比较改模型与读路由。组合式风险按 HoliSafe 分成五类：图文各自可安全，合在一起才不安全，或不安全内容只在图像里。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06522Oct 5
SycoLens study: a single sycophancy flip rate masks the distinction between correction and capitulation
构建 SycoLens 重放评测，区分谄媚翻转中的纠错与屈从
arXiv
2610.06522
Published
Oct 5
Layer
Model layer
Setting
Models and APIs
Evaluated models
opus-5, sonnet-5, sonnet-4.6 and others11
- RiskMisalignment and value divergence
Abstract论文揭示施压句式、边界距离与格式偏置主导翻转率，提出系统解构纠错与顺从的综合评测方案。
本文系统解构了大语言模型在用户质疑下的阿谀奉承行为与评测机制。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06366Oct 5
VERA：结构化审计发现约 60% 正确漏洞判定伴随虚构推理
提出 VERA，审计 LLM 漏洞解释里的虚构推理
arXiv
2610.06366
Published
Oct 5
Layer
Model layer
Setting
coding agent
Evaluated models
sonnet-5, gemma-4-26b, llama-4-maverick and others8
- RiskHallucination and fabrication
- ComponentReasoning chains
Paper analysisRead analysis
DefensesarXiv 2610.05898Oct 5
数据稀缺下 LLM 的协作式个性化偏好对齐：APO 方法
提出 APO，协同学习少样本个性化偏好对齐的 aligner 初始化
arXiv
2610.05898
Published
Oct 5
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct
- DefensesModel hardening
- RiskMisalignment and value divergence
Paper analysisRead analysis
DefensesarXiv 2610.05637Oct 5
Study shows VLM visual grounding refusal rates are on average 31 to 59 percentage points lower by harm domain
提出融合定位拒答与能力保留的安全微调，补齐视觉定位输出的拒答缺口
arXiv
2610.05637
Published
Oct 5
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Claude Sonnet 4.6, Gemini 3.5 Flash, Molmo2-8B and others5
- DefensesModel hardening
- RiskInappropriate refusal
- ComponentVision
Abstract论文揭示了 VLM 定位安全落后于 VQA 的对齐断层，提出三成分微调方案有效弥合差距并保留定位能力，表征分析揭示了对齐机制。
Paper analysisRead analysis
InterpretabilityarXiv 2610.05541Oct 5
研究者提出 CAP 指标与 CSFD 算法，发现越狱通过压制安全特征绕过拒答
提出 CAP 指标与 CSFD 算法，发现被抑制的安全特征
arXiv
2610.05541
Published
Oct 5
Layer
Model layer
Setting
Models and APIs
Evaluated models
Gemma-2-2B, Qwen3-8B, Gemma-3-4B-IT and others5
- RiskInappropriate refusal
Abstract论文指出越狱通过抑制安全特征运作，提出 CAP 与 CSFD 补充了针对激活特征的解释性方法。
Paper analysisRead analysis
DefensesarXiv 2610.05219Oct 4
AURA：用正交适配缓解 LLM 推理与安全对齐的子空间干扰
提出 AURA，用正交惩罚分开顺序适配中的推理与安全子空间
arXiv
2610.05219
Published
Oct 4
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen-3-14B, Qwen-2.5-14B-Instruct, Llama-3-8B-Instruct and others4
- DefensesModel hardening
- RiskMisalignment and value divergence
AbstractAURA 用子空间正交分开顺序任务。
AURA 是面向共享骨干智能体的顺序 LoRA 正则，用来分开前后任务的残差子空间。
Paper analysisRead analysis
DefensesarXiv 2610.04998Oct 4
EmoRSS：缓解大语言模型由情绪引发的过度拒答
提出 EmoRSS，推理时在拒绝子空间反向抵消情绪激活偏移以缓解过度拒答
arXiv
2610.04998
Published
Oct 4
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama-3.1-8B-it, Qwen3-8B
- DefensesInference-time intervention
- RiskInappropriate refusal
Paper analysisRead analysis
DefensesarXiv 2610.04967Oct 4
One Token Can Be Enough：用 Prefix Steering 连接提示与激活引导
提出 Prefix Steering，以短前缀激活引导控制行为并保住能力
arXiv
2610.04967
Published
Oct 4
Layer
Model layer
Setting
Models and APIs
Evaluated models
OLMo 3 7B, OLMo 3 32B, Qwen3 1.7B and others4
- DefensesInference-time intervention
- RiskInappropriate refusal
Abstract短前缀 steering 用已有方向做短暂干预。
本文用注意力层匹配连接提示词与激活干预，并把干预改成从末提示词 token 开始的短前缀。
Paper analysisRead analysis
InterpretabilityarXiv 2610.04245Oct 3
研究揭示语言模型拒答行为的转向维度差异
测量安全拒绝与一般语境拒绝的转向维数
arXiv
2610.04245
Published
Oct 3
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama-3.1-8B-Instruct, Qwen2.5-3B-Instruct
- RiskInappropriate refusal
Paper analysisRead analysis
DefensesarXiv 2610.02999Oct 2
OmniConfess：用 Token 级「忏悔」缓解全模态幻觉
提出 OmniConfess，冻结候选并按通道重打分以缓解全模态幻觉
arXiv
2610.02999
Published
Oct 2
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen2.5-Omni-7B, Qwen3-Omni-30B-A3B, Nemotron-3-Nano-Omni-30B
- DefensesInference-time intervention
- RiskHallucination and fabrication
- ComponentVision
Paper analysisRead analysis
InterpretabilityarXiv 2610.02910Oct 2
论文提出用路由梯度敏感度定位稀疏 MoE 模型中的安全敏感专家
用路由梯度敏感度定位稀疏 MoE 的安全敏感专家
arXiv
2610.02910
Published
Oct 2
Layer
Model layer
Setting
Models and APIs
Evaluated models
Mixtral-8x7B, Qwen1.5-MoE, DeepSeek-MoE and others5
- RiskInappropriate refusal
Abstract频率不是敏感度。
在五个稀疏 MoE 上，用 router 梯度而不是激活频率挑选要抑制的专家，留出恶意提示词上的拒答降得更多。。推理时让少数路由专家不被选中，就可以不重训练地改变拒答，但频率只记录使用次数。
Paper analysisRead analysis

AI Safety Daily

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

All papers

Attack type

Model risks

Defense type

Impact

System type

Attack surface / entry point

Layer

System component

Attention sees, MLP refuses: tracing the safety pathway from attention to MLP in LLMs

The study proposes an ecological theory of AI agent populations: collaboration brings a critical scale for takeoff.

BeliefScope：区分证据与用户压力对模型信念影响的受控框架

SafeEvo：从拒答回路视角解释大模型安全对齐机制与演化

研究定位 LLaMA-2-7B-Chat 安全敏感参数

Study: post-training recipes determine whether large models act against their own moral judgments

The paper proposes a scaling law framework for alignment measured by risk category.

ASCENT：通过一阶最优校准实现安全与效用协同的微调框架

研究者提出读取路由 logits 的 MoE 视觉语言模型多模态安全检测器

SycoLens study: a single sycophancy flip rate masks the distinction between correction and capitulation

VERA：结构化审计发现约 60% 正确漏洞判定伴随虚构推理

数据稀缺下 LLM 的协作式个性化偏好对齐：APO 方法

Study shows VLM visual grounding refusal rates are on average 31 to 59 percentage points lower by harm domain

研究者提出 CAP 指标与 CSFD 算法，发现越狱通过压制安全特征绕过拒答

AURA：用正交适配缓解 LLM 推理与安全对齐的子空间干扰

EmoRSS：缓解大语言模型由情绪引发的过度拒答

One Token Can Be Enough：用 Prefix Steering 连接提示与激活引导

研究揭示语言模型拒答行为的转向维度差异

OmniConfess：用 Token 级「忏悔」缓解全模态幻觉

论文提出用路由梯度敏感度定位稀疏 MoE 模型中的安全敏感专家