Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 29 papers 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.
Proposes digital lock compilation, encrypting executable networks into host weights to hide arbitrary capabilities
Published Oct 10
Evaluated models Gemma 3 270M Abstract The authors use a digital lock to hide an executable capability and state that elicitation on the chemistry and parity tasks did not recover the capability.The authors construct a class of backdoors that encrypt an executable network into the weights, used to discuss the limits of white-box elicitation audits under supply chain attacks.
Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.
Published Oct 9
Evaluated models Llama-3.1-8B-Instruct , Qwen2.5-7B-Instruct , Mistral-7B-Instruct-v0.3 Abstract Hidden 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.
提出 FAB 攻击，向声学基础模型植入可由环境声触发的后门
Published Oct 7
Evaluated models HuBERT-base , WavLM-base 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。
提出持久视觉记忆注入，使对抗图像经缓存在触发时操控输出
Published Oct 7
Evaluated models Qwen3-8B , Qwen3-VL-8B-Instruct , Gemma-4-12B Abstract 论文提出 P-VMI，证实对抗输入被掩蔽后仍可经 KV 缓存持久控制模型，强调了保留状态的安全风险。
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。 。
提出只改 SAE 解码器的后门，在冻结语言模型上植入代码插入
Published Oct 5
Evaluated models Gemma 3 4B Instruct , Qwen3 1.7B , Llama 3.1 8B Instruct Abstract 只改解码器的 SAE 可带上代码插入后门，且若干常规质量指标变化不大。只改 SAE 解码器、冻结编码器与语言模型，即可把代码插入行为放进推理时的辅助组件。作者把这视为 SAE 供应链问题：checkpoint 一旦替换某一层激活，就参与后续计算，而不只是解释工具。
提出 PLW，用微调把先前对话敏感触发编码进后续生成图像
Published Oct 5
Evaluated models OmniGen2 , BAGEL-7B Abstract PLW 把先前对话线索写成后续图像中的隐水印，检出随触发、模型和间隔变化。
提出 BadAction，通过动作触发器给交互式视频生成植入后门
Published Sep 30
Evaluated models Astra (Wan2.1-T2V-1.3B) 提出主题锚点投毒，放大众包微调后的专有指令提取
Published Sep 28
Evaluated models Qwen2.5-7B-Instruct , Qwen2.5-14B-Instruct , Llama-3.1-8B-Instruct and others4 Abstract 论文提出基于主题锚点的数据中毒攻击，证明低比例的中毒样本可在黑盒条件下隐蔽放大微调指令泄漏。
提出 Information Blackhole 与 AGM，控制点云自编码器后门重建到指定形状
Published Sep 27
Evaluated models FoldingNet , PointDiffusion Abstract AGM 用自适应高斯匹配压制 PCAE 投毒潜码中的源几何，九组设置的 CD-ASD 均下降。这篇工作研究点云自编码器的训练时后门 ：干净输入仍自重建，带触发的输入应重建成攻击者指定形状。分类后门只需把预测推向离散标签。PCAE 把源几何与目标信息编进同一个连续潜空间，残留源几何会把重建拉回源形状。
提出推理通道预填与输出前缀组合攻击以越狱推理模型
Published Sep 24
Evaluated models Gemini 3 Flash Preview , DeepSeek V4 Flash , Claude Haiku 4.5 提出 RAMP，逆转对抗扰动加强恶意软件检测器的干净标签后门
Published Sep 23
Evaluated models MalConv , MalConvGCG Abstract RAMP 用反转扰动做 clean-label 投毒。RAMP 是 score-based black-box 下的 clean-label 后门增强，对象是会微调的 Windows PE 原始字节恶意软件检测器。
提出 plan injection 攻击，植入良性伪装计划以绕过思维链监视器
Published Sep 15
Evaluated models Qwen2.5-Coder-7B-Instruct , Qwen3-8B , DeepSeek-R1-0528 and others6 Abstract 论文指出模型会将外部上下文中的伪装计划改写为自身推理，使思维链监视器失效甚至反向合理化恶意行为。
提出任意字母置换密码越狱，无需微调即可诱导有害输出
Published Sep 9
Evaluated models Claude Sonnet 4 , Claude Sonnet 4.5 , Gemini 3 Flash (preview) and others7 Abstract 前沿大模型无需微调即可通过提示词学会字母置换密码，进而绕过分类器与对齐，作者呼吁关注能力提升带来的安全风险。
揭示推理加深引发的对齐坍塌，用 Reasoning Trap 放大越狱
Published Sep 8
Evaluated models Qwen3-8B , Qwen3-14B , Llama2-7B and others8 Abstract 更深推理提升题目准确率，同时提高扰动下的相对损失。作者研究扩展推理是否以对齐稳健性为代价，提出 ALR、RT 与 RRA。 。
提出联邦学习细粒度分布式后门框架 FDBA，用动态触发与对比嵌入降低投毒比例
Published Sep 7
Evaluated models ResNet-18 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 GhostWord 词级触发后门，对自动语音识别做数据投毒
Published Sep 2
Evaluated models Whisper-Small , Whisper-Medium , MMS and others4 利用加密思维块的跨模型重放，诱导弱模型逐字转写专有推理链
Published Aug 11
Evaluated models Claude Opus 4.8 , Claude Sonnet 4.6 , Claude Haiku 4.5 and others13 Abstract 论文揭示了客户端加密思维块跨模型互换漏洞，提出了低成本提取方法并给出防御方案。