Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 13 papers Another 233 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
Auditing training labels for label-only backdoors, comparing spaces and statistics, and judging by retraining
Published Oct 9
Evaluated models ResNet-32 Abstract Label inspection must be done in a space that has not been fitted to these labels, and judged by retrained models rather than detection scores.The authors ask: can a defender without trusted data decide which training labels to keep, and how much clean data this destroys, and what the final model accuracy is.
Analyzing why optimizing teaching adaptation metrics collapses tutoring choices and diverges from expert judgment
Published Oct 8
Evaluated models Gemini 3.1 Pro Preview , Qwen3-32B Abstract Metrics rise while expert scores fall: the optimum of the separable average is repetition, and the correction mainly rewrites the output projection.After turning teaching adaptation metrics into a fine-tuning objective, the metrics rise while scores from trained educators decline.
分析记忆与泛化如何决定机器遗忘的 retain 损伤
Published Oct 6
Evaluated models one-layer ReLU transformer , one-layer transformer (BMA, width doubled) , Hubble-8B-100B perturbed and others6 Abstract 作者称共享规则占比越高，遗忘带来的 retain damage 越大。作者考察学习方式如何左右 unlearning 的 retain damage：训练越依赖跨样本共享的解法，在匹配的遗忘程度上，retain 上的损失越大。
提出 SAGE，定位代码修复 Agent 最早偏离安全意图的轮次
Published Oct 5
Evaluated models GPT-5.5 , Claude Opus 4.8 , Gemini 3.1 Pro and others6 Abstract SAGE 在已通过检查的修复轨迹上定位静默失败的最早偏离，类型比轮次更稳定。SAGE 在已通过语法和功能检查、但仍含确认安全缺陷的智能体修复轨迹上，定位最早可归因的安全意图偏离。 。
揭示工具型智能体判定无用后仍不停止检索，并检验强制整合纠正效果
Published Oct 5
Evaluated models Qwen2.5-7B , Llama-3.1-8B , Qwen3-8B and others7 Abstract 论文揭示智能体判定工具失效却无法转化为停止行动，证实通过框架规则强制整合判定可提升表现。本文针对智能体在工具静默失效时过度检索的问题，系统分析了判定、信念与停止行动之间的解耦现象，并提出了外部规则整合方案。
因果分解自生成反馈如何破坏测试时训练的长时程适应
Published Oct 4
Evaluated models 125M TTT-E2E , 760M TTT-E2E , 3B TTT-E2E and others5 Abstract 自写闭环损害真实文本预测。持久测试时更新若来自模型自己生成的文本，会同时改变模型和后续训练文本。作者在 PG-19 长流上分解这条闭环，并用独立文本决定是否提交更新。
揭示无触发虚假训练下事实回答与下游决策的审计差距
Published Oct 2
Evaluated models Qwen2.5-0.5B , Qwen2.5-1.5B , Qwen2.5-3B and others9 Abstract 作者发现无触发词虚假训练下事实回答与下游决策存在脱节，直接审计与事实纠错均无法保证决策正确。论文是一项针对语言模型在无触发词虚假信息训练下行为表现的实证分析研究。
提出预训练缩放律，估计野生 AI 网页文本相当于多少人类 token
Published Oct 1
Evaluated models nanochat 19.9M , 35.8M , 86.2M and others7 Abstract wild AI 文本对数据不足的模型先降损失，对高人类预算几乎立刻升损失。作者测量未标注的 wild AI 网页文本对预训练的影响，并提出一个能让 AI token 价值变号的缩放律。
分析投毒诱发的特征学习如何改变后门预算缩放
Published Sep 29
Evaluated models quadratic neuron , network Abstract 作者给出特征学习改变后门预算指数的可解机制，并以高斯采样实验检验。这是一项后门预算的理论分析，核心对象是最小二乘训练的二次神经元。 作者关注：只依据冻结表示估算投毒成本，是否会误判具有特征学习能力的模型。
分析近重复族如何让精确记录成员推断误判为入训
Published Sep 28
Evaluated models Pythia-2.8B , GPT-2 , Qwen3.5-2B and others5 Abstract 近重复使干净参照 MI 把族级暴露当成精确记录。作者研究成员推断能否作为精确记录的数据来源证据。版权和来源审计需要的是该记录本身是否入训，而网页语料中的转载、镜像和轻改会让非同一近重复产生成员样分数。四世界审计 用 E 表示精确记录是否入训、用 F 表示其近重复族是否在场，从而分开 H00 到 H10 的标准 MI、H00 到 H01 的族偏移，以及 H01 到 H11 的 exact-given-family。
证明预训练投毒的清洁超额风险指数随极限顺序变化
Published Sep 26
Evaluated models OLMo-style models Abstract 投毒清洁超额风险的幂指数取决于先固定宽高比还是先取充足数据极限。可解的预训练数据投毒理论：清洁超额风险的缩放指数随极限顺序改变。 。
提出 CellAudit，审计智能体发现的细胞模型是否使用所声明输入
Published Sep 23
Evaluated models CellScientist , AIDE , CellForge and others4 Abstract CellAudit 把输入使用声明从源码追到拟合贡献，并说明高分不必等于使用了扰动。CellAudit 为智能体发现的细胞响应模型增加一层输入使用证伪：源码是否消费注册输入、拟合预测是否依赖它、该依赖是否改善对观测响应的预测。
用 Tamarin 形式化分析智能体支付协议的跨阶段安全关系
Published Aug 30
Evaluated models x402 , MPP , ACP and others4 You have reached the end