Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 11 papers Another 265 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 Persona Guardrail，强制客服智能体守住功能边界
Published Oct 2
Evaluated models Qwen3-30B-A3B , Qwen3-VL-30B , Qwen3-8B and others5 Abstract Persona Guardrail 用功能边界做同步输入输出校验，并在 PAGE 与生产延迟预算下给出评测。Persona Guardrail 是客服向智能体的同步运行时防御：先写明功能边界，再决定放行或拦截，而不是只检测某一攻击类。
提出收缩约束 SSM 安全头，认证嵌入扰动并检测越狱
Published Oct 2
Evaluated models ToySSMClassifier , S4 safety head Abstract 收缩给出玩具 LTI 的有界认证。给 SSM 安全头一个收缩条件，并在越狱检测上使用收缩正则的 S4 头。 。
提出 ASA 与 AttestMCP，度量并降低 LLM 对输入序列扰动的敏感
Published Oct 2
Evaluated models Gemma-3-27B-Instruct , Gemma-3-4B-Instruct , Llama-3.2-3B-Instruct and others12 提出 OBELISK 三级流水线，权衡恶意软件检测的准确率、开销与鲁棒性
Published Sep 8
Evaluated models GBDT-ALL , GBDT-YARA , NEBULA-ALL and others4 Abstract 三级过滤以不大的检测损失换速度，同一机制扩大攻击面，部署应按约束选配置。OBELISK 把 Windows PE 恶意软件检测做成 YARA、EMBER-GBDT 与 Nebula 的顺序流水线，用来同时看检出、计算开销和对抗鲁棒性。
提出 SRD-GUARD，以语义改写与多模型联合评分拦截包装式越狱
Published Sep 6
Evaluated models Llama-3-8B-Uncensored , DeepSeek-V4-Flash 提出 LeakGauge，用行为后缀的 prefill 对数概率检测上下文泄露
Published Aug 18
Evaluated models Gemma-4-E4B-it , Gemma-4-31B-it , Qwen2.5-14B-Instruct and others11 提出 SPARED，用对抗编辑数据训练基于推理的 AI 生成图像检测器
Published Aug 13
Evaluated models Qwen3.5-9B Abstract SPARED 用防捷径的编辑对抗环训练 9B 推理检测器。SPARED 是一套用于可解释 AI 生成图像检测的攻防强化学习流程，报告模型是 Qwen3.5-9B 上的第三轮防御器。
提出 ColluSkill，用跨技能组合绕过 Agent 技能扫描器
Published Aug 10
Evaluated models GPT-5.5 , DeepSeek-V4-Pro , GLM-5.2 Abstract 论文揭示了单技能孤立扫描的盲区，提出多技能链攻击 ColluSkill 与上下文防御 ChainGuard 并验证了有效性。
提出分片监督，将评判标准分配给独立调用以抵御展示攻击
Published Aug 6
Evaluated models Claude Opus 4.8 , Claude Sonnet 4.6 , Claude Opus 4.6 and others4 Abstract 论文揭示决策负载是大模型监督的独立瓶颈，提出分片与辩论机制有效分离注意力与平衡证据，在多项高难度基准上实现稳健评判。本文系统研究了大语言模型在执行多标准监督与评判时的决策负载瓶颈及其安全风险。
提出 FoodGuardBench 与护栏 FoodGuard-4B，评测并降低食品危害越狱
Published Apr 2
Evaluated models Claude-3.7-Sonnet , GPT-4o , GPT-4.1 and others10 提出多轮多模态越狱，并用 FragGuard 拦截有害响应
Published Jan 9
Evaluated models LLaVa-1.6 (7B) , LLaVa-1.6 (13B) , Qwen-2-7B and others5 You have reached the end