Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 15 papers Another 255 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.
提出监控深伪基准 CCDF，在统一编码后评测检测器对伪造犯罪事故录像的识别
Published Oct 6
Evaluated models C2P-CLIP , ForgeLens , D3-Im and others10 Abstract 提出消除格式捷径的监控深度伪造基准 CCDF，揭示现有检测器难以识别商用生成视频。
构建多语言音视频 DeepFake 基准 BabelFake 并评测检测器
Published Oct 5
Evaluated models SpeechForensics , AVH-Align , (B)RAVEn Abstract BabelFake 为五语同意采集基准。BabelFake 是经同意与 IRB 批准采集的多语音视频 DeepFake 检测基准，用来把视觉操纵和语音合成拆开比较。
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。
提出基准 OLMo-Detect 评测 LLM 成员推断
Published Oct 2
Evaluated models OLMo 2 1B , OLMo 2 7B , OLMo 2 13B and others9 提出 COVER，在语言预算下选择源语言实现跨语言知识遗忘
Published Oct 1
Evaluated models Tiny Aya Global , Qwen3-4B-Instruct-2507 , Llama-3.2-3B-Instruct Abstract COVER 在语言预算下选源语言，以降低未监督语言上相对 oracle 的残余访问。语言预算下的多语言遗忘 ：遗忘监督只放在 K 种源语言上，目标是降低其余语言对同一事实的残余访问，而不是把每种评测语言都译成监督数据。
Published Sep 28
Evaluated models E-Branchformer Abstract 梯度上升类方法更接近简单评测下的重训参照，复杂方法会被知情攻击认出，多说话人更差。
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 PrivDrift 基准，审计话题漂移后的用户秘密复述
Published Sep 25
Evaluated models GPT-OSS-120B , DeepSeek-R1 , Qwen3-VL-235B 提出 SinoGlyphBench，用配对字形混淆诊断中文审核稳定性
Published Sep 5
Evaluated models GPT-5.4 mini , GPT-5.5 , DeepSeek V4 Flash and others12 Abstract SinoGlyphBench 显示中文字形混淆会同时增加有害漏报和误报，全文扰动最重。SinoGlyphBench 是一个配对诊断基准，用来看内容审核在可还原的中文字形混淆下是否还保持原决定。
提出 aiXamine 黑盒基准，统一评测 LLM 安全、稳健与隐私权衡
Published Aug 21
Evaluated models openai/gpt-5-mini , openai/gpt-4o , anthropic/claude-haiku-4.5 and others15 Abstract aiXamine 用九服务黑盒协议比较百余个模型，作者称单轴信任度进展可能削弱其他轴。aiXamine 是一套黑盒评测协议，用来在同一条件下比较 LLM 的 safety、security 与 privacy，而不是再产出一个能力分。
复现 AgentCF 上的多智能体攻防并刻画连通性作用
Published Aug 4
Evaluated models Qwen3-235B-A22B , Claude Haiku 4.5 , Mixtral 8×7B and others4 Abstract 连通性沿 k 与ρ改变攻防，且用户/物品与早期/稳态需要分开看。作者在 AgentCF 上研究连通性如何改变多智能体协同过滤的攻防，复现已有方法而不是提出新载荷。
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。 。
提出最小范数攻击集成，用鲁棒性曲线评测图像分类器
Published Jul 22
Evaluated models C1–C20（CIFAR-10，Table 1） , I1–I10（ImageNet，Table 1） Abstract 预算可控的最小范数集成用 AOI 逼近攻击前沿，DOI 给出不依赖单一ε的防御排序。这篇工作把对抗鲁棒评测从单一 ε、固定集成，改成可按查询预算收紧的曲线估计。
Propose soft prompt defense AREA, re-anchoring attention to mitigate system prompt leakage
Published Jun 17
Evaluated models Llama-2-7B-chat-hf , Llama-3.1-8B-Instruct , Mistral-7B-Instruct-v0.3 and others8 Abstract The authors measure commercial prompt leakage, propose attention drift, and use AREA to strike a trade-off between usability and leakage resistance.The authors study system prompt leakage in real LLM applications and propose AREA, a mitigation method that does not modify weights.
提出 SoftHateBench，评测审核模型对推理驱动软仇恨的检测
Published Jan 28
Evaluated models HateBERT (IMSyPP) , HateBERT (GroNLP) , HateRoBERTa and others12 You have reached the end