Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 18 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.
Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations
Published Oct 9
Evaluated models LAYA-TD , LAYA-EN , LAYA-ML and others5 Abstract The authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.
提出 BRANCH 方法，用分支搜索绕过多扫描器护栏
Published Oct 8
Evaluated models Meta Llama Guard 3 8B , Meta Llama Guard 7B , Meta Llama Guard 3 1B and others18 提出 SAFESHIELD，组织小语言模型部署时的安全决策
Published Oct 6
Evaluated models Qwen3-4B-Instruct Abstract SAFESHIELD 用可审计决策轨迹组织 SLM 部署时的四项安全决策，并报告协调依赖影响端到端结果。SAFESHIELD 是面向小语言模型的部署时安全框架，把运行时安全从单项审核改写成可检查的决策过程。
提出校准重合成方法，以生成器反演保真度认证真实图像并防御对抗扰动
Published Oct 5 Abstract 论文提出基于反演保真度与阈值校准的健全认证框架，在对抗扰动下维持错误率界限，并指出真实内容可认证性随生成器演进而萎缩。
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 ClaimMirage，以域名自述声称改变 LLM 威胁告警判断
Published Sep 24
Evaluated models Llama 3.3 70B Instruct-Turbo , Gemma 3 4B it , Gemma 3 12B it and others5 提出 ALIBI，向恶意二进制注入不执行掩护叙事使分析器误判为良性
Published Sep 17
Evaluated models Gemini 2.5 Pro , GPT-5.5 Pro , Claude Opus 4.7 Abstract ALIBI 用二进制内的掩护叙事重释可疑静态证据，Gemini 上翻转多，另两模型主要为降级。ALIBI 是针对 LLM 恶意软件分诊的语义掩护叙事攻击：不覆盖系统指令，而把仍可见的可疑静态证据重释成良性安全产品的预期行为。
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。
形式化跨不可关联身份的分解攻击并评测状态化防御边界
Published Aug 18
Evaluated models Granite Guardian 3.1 2B 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 SeTox 检索增强框架，检测中文新词的隐性毒性
Published Jul 5
Evaluated models SeTox-Qwen2.5-7B Abstract SeTox 用检索把公共共识接入静态 LLM，以检测中文毒性新词。SeTox 研究中文新词上的隐性毒性检测：词表加检索增强，使静态 LLM 在不重训练的情况下利用公开网页上下文。
提出 HPAA 攻击，用排版视觉线索绕过内容审核系统
Published Jun 9
Evaluated models Llama-Guard-3-8B , Perspective API , ShieldGemma-2B and others13 Abstract 揭示了排版视觉线索与分词差异带来的审核盲区，HPAA 以极低查询实现近乎完全规避。这篇论文研究了人类视觉感知与大模型分词处理机制之间的差异所导致的内容审核漏洞 。
提出 BITE，用上下文赌博机选择风格修改抬高 LLM 评委打分
Published May 24
Evaluated models o3-mini , Gemini-2.5-Flash , Llama-3.3-70B-Instruct and others8 Abstract BITE 用黑盒赌博机利用风格偏差抬分，作者称这对 LLM-as-a-judge 构成威胁。BITE 是黑盒风格操纵：在保持答案语义的同时，抬高 LLM 评审给出的分数。
提出 CITA 三阶段框架，生成可绕过毒性检测器的中文隐式毒性文本
Published May 21
Evaluated models Tencent , Baidu , Gemini 3.1 Pro and others11 提出 SWhisper，用近超声波向语音驱动 LLM 隐蔽注入越狱提示
Published Mar 14
Evaluated models Meta-Llama-3.1-8B-Instruct , Gemma-3-4B , Qwen2.5-7B-Instruct and others9 提出 GradingAttack，用梯度后缀与角色扮演操纵教育评分智能体判定
Published Feb 1
Evaluated models Qwen2.5-7B , Qwen2.5-7B-Instruct , Qwen2.5-14B-Instruct and others8 提出 DECEIVE-AFC，以声明改写诱导搜索增强事实核查误判
Published Jan 31
Evaluated models HiSS , LEMMA , DEFAME and others4 提出 HASTE，挖掘 hard negative 再训练恶意提示检测器
Published Jan 27
Evaluated models protectai/deberta-v3-base-prompt-injection Abstract HASTE 用 hard negative 再训练检测器。HASTE 是检测器侧的闭环硬化框架：持续构造能绕过当前检测的对抗提示，再用来更新恶意提示分类器。
You have reached the end