Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 11 papers Another 254 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 MFOTL 离线时序验证以监控工具 Agent 的危险动作链
Published Oct 7 Abstract 形式化验证可有效识别多步攻击，但其有效性高度依赖轨迹的可信历史记录。这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。
提出 UNTAG，绕过开源权重模型的 trigger-tag 滥用检测
Published Oct 2
Evaluated models Llama2 (7B) , Llama3 (8B) , Qwen2.5 (7B) Abstract 作者用 UNTAG 评估 trigger-tag，认为其不能充当开放权重滥用检测的主要边界。UNTAG 是针对开放权重 LLM 上条件滥用检测 trigger-tag 的统一攻击评估：信号可以在解码期注入，也可以写进权重，但攻击者若能改输出或改已发布权重，检测可以失效。
提出 Whiteout，用伪装样本微调覆盖个人敏感信息关联
Published Oct 1
Evaluated models Llama 3.2 , Phi-3-mini , Gemma 3 and others7 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。
提出 SEAL，在 MoE 共享专家上做 DPO-LoRA 对齐以抵御越狱与权重篡改
Published Sep 2
Evaluated models Qwen1.5-MoE-A2.7B , DeepSeekMoE-16B , GLM-4.7-Flash and others4 Abstract SEAL 把 DPO-LoRA 限制在混合 MoE 共享专家上，SEAL++再保护已有安全神经元方向。SEAL 是面向混合 MoE 的训练时防御：只对齐始终执行的共享专家，使安全不依赖路由器是否把 token 送到安全专家。
提出 SN-Guided Diffusion，利用安全神经元实现离线越狱
Published Aug 8
Evaluated models Qwen2.5-7B-Instruct , LLaDA-8B-Instruct , Dream-Instruct-7B and others15 Abstract 论文揭示了扩散语言模型对自回归安全神经元的继承性，并提出纯离线黑盒越狱框架 SN-Guided Diffusion。论文系统评估了扩散大语言模型（DLLM）在安全对齐中的双重角色——既作为白盒攻击目标，又作为黑盒越狱生成的对抗工具。
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。
训练自博弈红队智能体 GPT-Red，规模化生成提示注入与越狱攻击
Published Jul 29
Evaluated models GPT-5.6 , GPT-5.5 , GPT-5.4 and others8 提出针对 Agent 护栏的推理扩展拒绝服务攻击
Published Jun 12
Evaluated models TS-Guard-8B , Qwen3.5-9B , DeepSeek-V3.2 and others11 Attacks arXiv 2509.22067 · Sep 26, 2025 提出激活转向越狱，用随机向量在推理时绕过安全拒答
Published Sep 26, 2025
Evaluated models Llama3.1-8B , Llama3.1-70B , Qwen2.5-3B and others8 Abstract 作者称激活转向会系统性破坏 LLM 对齐，良性特征与随机向量均能诱发有害合规，聚合随机向量可构建通用攻击。
You have reached the end