Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 12 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.
提出 ZoneClaw，用记忆分区防御计算机使用 Agent 的持久记忆攻击
Published Oct 1
Evaluated models Claude Sonnet 4.6 , GPT-5.5 , GLM-5.2 and others4 提出 IDUnlearn-Bench，评测 VLM 个体级遗忘后的身份残留
Published Sep 27
Evaluated models Qwen3-VL-2B , Qwen3-VL-4B , Qwen3-VL-8B and others6 Abstract IDUnlearn-Bench 用四族探针显示：压低直接属性访问后，身份仍常能被反向查出、绑定或重构。IDUnlearn-Bench 评测 VLM 是否忘掉一个可跨模态识别的人，而不只是答不出某条监督事实。
提出 AEGIS，用中层内部信号选择性激活后层适配器拦截音频越狱
Published Sep 24
Evaluated models Qwen2-Audio-7B , VITA-1.5 , Ultravox v0.5 and others6 提出 PALS，用潜空间平滑防御全双工语音对话的对抗扰动
Published Sep 23
Evaluated models Moshi-style agent 提出 BoundStyle 与 StyleAT，对抗训练防御人脸识别语义攻击
Published Sep 20
Evaluated models MobileFaceNet (MobileFace) , ResNet (ResNet-152, IR-SE) , RepVGG and others7 Abstract BoundStyle 用 StyleGAN3 有界潜编辑快速攻击 FR。StyleAT 用可调的 StyleGAN3 潜空间攻击 BoundStyle 对人脸识别做对抗训练，以抵抗一般语义编辑，并在评测中面对训练时未见的 DiffPrivate。
用后验重加权解释多模态上下文越狱，并提出风险门控的良性示例注入防御
Published Sep 8
Evaluated models Qwen3-VL-2B , Qwen3-VL-4B , Qwen3-VL-8B and others8 Abstract 后验重加权解释上下文越狱的缩放，并支持风险门控的良性示例防御。Zhang 等把多模态 ICL 越狱写成对齐模型在安全与有害隐模式之间的推理时后验漂移，并据此做风险门控防御。
提出 AgentKernel，用四支柱强制中介 Agent 的输入、工具与记忆
Published Aug 29 Abstract AgentKernel 是四支柱智能体 OS 设计，安全论证未附带实测数字。AgentKernel 是把安全做成组织原则的智能体 OS 架构，不是带跑分的攻防评测。
提出依赖引导回滚修复，恢复记忆增强 Agent 的回答与状态
Published Aug 11
Evaluated models GPT-4o , Gemini-3.6-Flash , Qwen3.6-27B 提出 TMA-NM，以写时来源绑定抵御 Agent 长期记忆投毒
Published Jun 23
Evaluated models gpt-5-chat , gpt-4o-mini , claude-opus-4.1 and others8 Abstract TMA-NM 用来源绑定的行动权限挡住记忆洗白。TMA-NM 把 LLM 智能体长期记忆的行动权限绑到写时来源，用来挡住跨会话记忆投毒。
提出对齐五阶段的纵深防御，缓解自主 Agent 跨阶段威胁
Published Mar 12 Abstract 这是对 OpenClaw 的生命周期威胁分析与分层缓解设计，案例为定性证据。这是对 OpenClaw 的生命周期威胁分析，并配套一套分层缓解设计。要处理的问题是：自主智能体把即时通讯、持久记忆、第三方插件和高权限执行连在一起之后，攻击不再限于单轮越狱，而会跨初始化到执行的多个阶段复合。作者认为只加固单个接口的防御，挡不住这种跨时间攻击。
Propose SAFT, which uses semantic description ensembles to construct adversarial examples and fine-tune the image encoder
Published Feb 13
Evaluated models ViT-B/32 , CLIP-L/14 Abstract SAFT fine-tunes the CLIP image encoder with ensemble adversarial examples from refined class descriptions to improve the trade-off between zero-shot accuracy and robustness.SAFT is a method for adversarially fine-tuning the CLIP image encoder to improve the accuracy–robustness trade-off in zero-shot classification.
提出 Aura，用可信内核中介移动 Agent 的身份、感知与动作控制
Published Feb 11
Evaluated models Gemini-3-Flash Abstract Aura mediates structured interactions via the Agent Kernel.Aura uses kernel-mediated structured agent interaction, replacing screen-interface mobile assistants. .
You have reached the end