Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 232 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.
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
Published Oct 6
Evaluated models Llama-2-7B-chat-hf , Mistral-7B-Instruct-v0.3 , Gemma-7B-it and others4 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。
测量带后门教师经 OPD 向干净学生迁移潜伏后门
Published Oct 6
Evaluated models Qwen2.5-1.5B-Instruct , Qwen2.5-3B-Instruct , Qwen2.5-7B-Instruct Abstract 作者称 OPD 可在压低无触发词有害率时迁入后门。带后门的外部教师经 OPD，可在压低无触发词有害率的同时，把触发条件下的有害行为传给初始干净学生。 。
提出 Bi-QSTO，优化能穿过质量筛选并在微调中削弱安全对齐的投毒样本
Published Oct 1
Evaluated models Llama2-7B-Chat , Llama3-8B-Instruct , Qwen2-7B-Instruct and others5 Abstract 质量筛选挡不住部分高分样本的安全削弱。Bi-QSTO 研究一个实际训练缺口：基于质量的数据选择会先于微调决定样本去留，而以往微调投毒多假设毒样本直接进入训练集。已对齐 LLM 的拒答会被少量有害或看似无害的微调样本削弱。作者用三个问题串起实验：选择能否排除毒样本。
提出 FreqDoor，在频域混合振幅并对生成式 VLM 做训练时视觉后门
Published Sep 7
Evaluated models BLIP-2 (opt-2.7b) , InstructBLIP (flan-t5-xl) , LLaVA (interleave-qwen) Abstract FreqDoor 用频域振幅混合给三款 VLM 植入仅视觉的训练时后门。FreqDoor 是针对生成式 VLM 的仅视觉、训练时后门：在频域混合触发源振幅、保留干净图像相位，使触发在空间上分散。
提出 TrojanMerge，在源模型植入仅在合并后生效的潜伏分量
Published Apr 1
Evaluated models Llama 2 M1 (safety-aligned chat variant) , Tulu-2-7b , Llama 3 M1 (safety-aligned chat variant) and others9 提出 ACL 量化攻击，令模型全精度良性而量化后恶意
Published Jan 6
Evaluated models Qwen2.5-1.5B-Instruct , Qwen2.5-3B-Instruct , Llama-3.2-1B-Instruct and others4 You have reached the end