Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 13 papers Another 262 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.
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 NDDL，用良性扩散轨迹检测文生图后门提示并定位触发 token
Published Sep 30
Evaluated models Stable Diffusion v1.5 , Stable Diffusion XL , Stable Diffusion v3.5 and others4 Abstract NDDL 从良性扩散轨迹学习正常转移，用动态不一致检测后门并定位触发 token。NDDL 是面向文生图扩散模型的后门防御：防御者只有白盒模型访问和良性提示词，没有后门先验，需要区分后门提示词并找出触发 token。
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 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 AttestChain，将供应链安全智能体报告签名上链并据此控制发布
Published Sep 25
Evaluated models GPT-class LLM Abstract AttestChain 将智能体报告与链上发布门控结合，现有证据来自受控合成构建的总体结果。AttestChain 是一个把 LLM 安全检查、智能体身份验证和许可链发布策略连接起来的软件供应链防御框架。 。
梳理去护栏开源模型的生产、再分发与部署供应链
Published Sep 4 Abstract 这是一份去护栏模型供应链调查，作者将再分发层视为持续供给和下游部署的连接点。10a Labs 调查的是去护栏模型的公开供应链，而非去护栏技术的效果排行榜。 作者关注安全行为被移除后，模型如何继续被复制、转换并接入应用。
提出 RACER，用区域感知一致性对抗微调去除多模态大模型后门
Published Aug 25
Evaluated models LLaVA-1.5-7B , Qwen2-VL-7B , Qwen2.5-VL-7B 提出 AMS，用激活分离与方向相似度检测安全训练改动
Published Aug 6
Evaluated models Llama-3.1-8B-Instruct , Llama-3.2-3B-Instruct , Llama-3.2-1B-Instruct and others14 Abstract AMS 按激活签名把安全改动分四类，前三类可由两级扫描覆盖，行为微调会漏。AMS 是面向开放权重模型、部署前使用的激活扫描器，用来看安全训练被拿掉或改写之后，激活空间里还留着什么几何痕迹。
提出 Z-PEFT，用逐头谱特征零样本检测 PEFT 后门
Published Aug 3
Evaluated models Z-PEFT , Llama-2-7B , Llama-2-13B and others6 提出 SeedHijack，劫持采样 PRNG 以强制选定 token
Published May 8
Evaluated models GPT-2 (124M) , Qwen2-1.5B-Instruct , DeepSeek-R1-1.5B and others5 Abstract 采样层 PRNG 被替换以强制选 token。SeedHijack 把 LLM 采样用的 PRNG 输出换成攻击者选定的数，从而指定下一个 token。权重、输入和 logits 都不改。防御是用硬件 QRNG 替换该随机源。
You have reached the end