Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 25 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.
Proposes the semantic watermark SemField, which still identifies the attribution of generated text after paraphrasing and structural changes.
Published Oct 8
Evaluated models Llama-3.2-1B , Qwen3-1.7B , OPT-1.3B Abstract Training-independent document-level semantic watermark.SemField is a zero-bit semantic watermark embedded by the provider at generation time and detected later with a key, used to identify the provider's own model text after paraphrasing and sentence-level structural changes.
量化片外功耗测量对隐藏算力的约束能力
Published Oct 6 Abstract 作者称功耗单独只能弱约束隐藏算力。这篇工作定量估计片外功耗能为算力核验排除多少未声明运算。
提出 TRANSCOPE，用 CPU 硬件计数器推断训练集成员
Published Oct 6
Evaluated models BERT (4.4M-340M) , ViT (22M-307M) , Pythia (70M-2.8B) and others5 Abstract TRANSCOPE 揭示了分词器在嵌入表引发的硬件访问局部性差异，证实微架构计数器可突破恒定时间与置信度遮蔽防御。
提出闭环激活引导，在扩散语言模型去噪过程中注入定向偏见
Published Oct 5
Evaluated models LLaDA-8B-Instruct , Dream-v0-Instruct-7B , LLaDA-MoE-7B-A1B-Instruct Abstract 通过去噪中间概率反馈动态调节残差流转向，证明扩散语言模型在推理服务栈中存在闭环偏见注入脆弱性。
把 SynthID 嵌入基因组语言模型采样，并用位置无关检测追溯生成序列
Published Oct 4
Evaluated models Carbon-500M , GENERator-v2-eukaryote-1.2b-base Abstract 两个六碱基基因组模型嵌入 SynthID 后，位置无关验证能找回水印，作者称这只是统计检测。作者在两个六碱基基因组模型的采样里嵌入 SynthID，并让验证者在不知道起点、链和 token phase 时做一次校正后的检出。
提出抗删除水印 RMCW，在生成时注入 Reed-Muller 结构并做局部检验
Published Oct 2
Evaluated models OPT-1.3B , Llama-3.1-8B-Instruct 提出 HXAI 分层隐私解释框架，本地保留细解释并只发布加噪摘要
Published Oct 2
Evaluated models gradient-boosted tree regression models Abstract HXAI 把无噪声局部 SHAP 留在家庭内，只聚合差分隐私摘要。HXAI 是面向分布式能源系统的分层隐私保护解释框架，服务规划、监测与诊断，而不是实时控制。
提出 AutoMark，自动搜索并统计检验 LLM 文本水印
Published Sep 29
Evaluated models Llama-3.1-8B-Instruct , Qwen3.8-27B , GPT-6 Astra and others5 Abstract AutoMark 的贡献同时包含搜索出的水印，以及用于约束自动研究误报与评测漏洞的验证框架。AutoMark 是一套自动水印研究框架 ：先检查生成分布和误报性质，再比较检测、编辑鲁棒性与质量，最后人工分析组件并做留出评测。
用 SCM 合成会话并训练检测器识别推理层滥用
Published Sep 29
Evaluated models gradient-boosted detector (GBDT/XGBoost) 提出成对无失真水印 TTMARK，增强低熵下的机器文本检测
Published Sep 29
Evaluated models Llama3.2-3B-Instruct , Mistral-v0.3-7B-Instruct , Qwen2.5-7B-Instruct Abstract TTMARK 用水印化相邻 token 对利用条件熵，在多种无失真方案上提高检测并保持生成质量。TTMARK 是一种成对、无失真的文本水印：对相邻 token 的联合分布重加权，而不是逐 token 独立重加权。
部署蜜罐测量针对暴露 LLM 基础设施的攻击
Published Sep 24 提出 DenMark，在扩散语言模型去噪时注入可抵抗保义编辑的语义水印
Published Sep 13
Evaluated models LLaDA-8B , LLaDA1.5-8B , LLaDA2.0-mini and others4 Abstract DenMark 用 rollout 在 DLM 去噪中累积语义水印，扫描检测以抵抗保义编辑。DenMark 是面向扩散语言模型的语义水印：在去噪的局部更新里注入密钥相关语义信号，并在编辑改变 token 边界后仍检测。现有句子级语义水印要先完成整个语义单元再打分取舍，而 DLM 以任意顺序更新掩码，中间单元不完整。DenMark 把续写划成固定 token 区域，对每个局部候选做不提交的 rollout 补全，按语义分 gb 的平均选择更新，从而沿轨迹累积证据。
提出 PMA，用流形对齐从 E2EO 混淆向量恢复明文
Published Sep 7
Evaluated models BERT-base , RoBERTa-base , T5-base and others6 Propose GIFT, isolating user data in shared LLM serving using encryption and GPU information flow tracking
Published Aug 26
Evaluated models Qwen2.5-14B , Qwen2.5-32B , Qwen2.5-72B and others6 Abstract GIFT uses cryptographic isolation plus GPU information flow rules to enforce user data isolation on vLLM and DistServe, and reports throughput overhead.GIFT is the authors' user data isolation system for shared LLM serving, with GIFT-CC enabling confidential computing. In the conclusion, the authors state it is the first IFT design for this scenario.
Proposing KeyPooling to measure where API relays break prompt cache isolation
Published Aug 18
Evaluated models grok-4-fast-non-reasoning , grok-4-1-fast-non-reasoning , grok-3 and others11 Abstract Shared upstream credentials place relay customers in the same cache domain; preserving identity or separate principals can separate them.KeyPooling measures where LLM API relays drop customer identity, causing prompt caches to no longer be isolated per downstream customer.
提出 Cocktail 水印，共嵌稳健与脆弱信号以溯源并发现篡改
Published Aug 13
Evaluated models Llama-3.2-1B , Gemma-3-4B 提出 EXE-Bench 比较 Windows 恶意软件检测器的可用性权衡
Published Jul 27
Evaluated models EmberGBDT , BBDnn , BBDnnFDRS and others15 Abstract 统一四指标后，手工特征的 EmberGBDT 综合居首，只看准确率会误导部署。EXE-Bench 用同一设置给 AI Windows 恶意软件检测器做四指标排序，而不是只比一次测试集准确率。 。
提出 CodeSpear 越狱，借语法约束解码生成恶意代码，并给出 CodeShield 防御
Published Jun 10
Evaluated models Qwen2.5-Coder-7B , Qwen2.5-Coder-32B , Qwen2.5-7B and others10 Abstract 论文发现语法约束解码会破坏自然语言安全对齐，提出 CodeSpear 越狱攻击与基于蜜罐代码对齐的 CodeShield 防御。
构造可通过计费审计的 token 虚报，使服务商系统性超收
Published May 28
Evaluated models PALACE domain-adapted auditor Abstract 不诚实提供方可在三种 token 审计上虚报并通过检查，作者认为需改用提供方不控制的证据。不透明 LLM 的按 token 计费里，现有审计核验的是提供方可控的证据，不诚实提供方可以虚报并通过检查。 。
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。