Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.

System type：Models and APIs System type：web agent System type：Browser and computer use System component：Guardrails and judges Clear all

Another 233papers do not have category tags yet and are not included in filtered results.

Analysis and theoryarXiv 2610.12083Oct 8
Paper audits LLM judge reliability: repeated agreement does not equal correctness
Auditing LLM judge reliability and defining trustworthy verdict rate and accuracy upper bound
arXiv
2610.12083
Published
Oct 8
Layer
Model layer
Setting
Models and APIs
Evaluated models
GPT-5.2, GPT-4o, Gemini-2.5-Pro and others6
- ComponentGuardrails and judges
AbstractThe authors claim that comparing judges should look at T, not just accuracy.
The authors audit whether LLM-as-a-Judge decisions can still be treated as actionable ground truth under repeated queries, swapped candidate order, and changed prompt formats.
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.11599Oct 8
研究：大语言模型版本更替削弱 AI 辅助科研写作筛查
测量 LLM 版本更替对科学摘要 AI 改写检测器的影响
arXiv
2610.11599
Published
Oct 8
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
RoBERTa-base, Pangram
- DefensesDetection and filtering
- ComponentGuardrails and judges
Abstract作者称检测器的基准准确率只是临时的，每次发布都要连同更早版本重验。
作者量化的是：科学摘要的 AI 改写筛查，在 LLM 版本不断更换、而人类摘要误标必须少见时，会怎样变。问题来自期刊和会议已经按分数阈值筛查投稿，但基准多停在评估时可得的版本上。
Paper analysisRead analysis
DefensesarXiv 2610.11281Oct 8
包络采样：用少量真值标注重校准 LLM 评委以缓解奖励作弊
提出包络采样，用少量真值标注重标定 LLM 评委以缓解奖励作弊
arXiv
2610.11281
Published
Oct 8
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen3-4B, Qwen3.8-27B, Qwen2.5-14B-Instruct
- DefensesModel hardening
- RiskReward hacking
- ComponentGuardrails and judges
Abstract包络采样把真值标注打到代理尾部，同样预算下缓解 reward hacking。
作者研究后训练前如何选择真值标注的查询分布，使重标定后的廉价代理更适合被优化。真奖励昂贵时，实践用 LLM judge 代替人类。若失准只发生在基座很少生成的输出上，on-policy 标注修不到这些点，随后的 KL 正则优化会把质量集中到被高估的输出。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.11112Oct 8
EpiReal-Bench：商用图像生成模型虚假声明红队基准
构建 EpiReal-Bench，评测图像生成器将虚假主张渲染为可信证据
arXiv
2610.11112
Published
Oct 8
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
GPT-Image-2, Nano Banana 2, Grok Imagen 2.0 and others4
- AttacksJailbreaks
- ComponentImage generation
Abstract四款商用图像模型能把假主张画成可信证据。
EpiReal-Bench 用来量商用图像生成器会不会把虚假现实主张画成可信视觉证据。
Paper analysisRead analysis
DefensesarXiv 2610.09167Oct 7
Persist-3 用顺序检验识别未见越狱来源，提升 MTK 与 Prompt Guard 2 防御效果
提出 Persist-3 序贯检验，从隐藏表示识别未见越狱源
arXiv
2610.09167
Published
Oct 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama2-7B-chat, Qwen2.5-7B-Instruct, Gemma-2-9B-it and others4
- DefensesMonitoring and auditing
- AttacksJailbreaks
- ComponentMonitors
AbstractPersist-3 用有限窗口检验攻击流是否超出已知越狱源，检出率低于全历史 SR-DKW，但决策只依赖最近观测。
Persist-3 是一个有限记忆的序贯检测器，用来判断攻击表示流是否已经不能由任何一个已知越狱源解释。。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.07939Oct 6
CCDF dataset: Grok Imagine, Veo 3.1, Sora 2 forge surveillance footage, ten deepfake detectors basically cannot recognize it
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
arXiv
2610.07939
Published
Oct 6
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
C2P-CLIP, ForgeLens, D3-Im and others10
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
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。
Paper analysisRead analysis
AttacksarXiv 2610.07723Oct 6
Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.
提出回答端后门，让模型自生成触发词以在干净有害请求下绕过拒答
arXiv
2610.07723
Published
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-2-7B-chat-hf, Mistral-7B-Instruct-v0.3, Gemma-7B-it and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract论文提出了多轮对话中回答端自生成触发词绕过安全拒绝的后门攻击，指出输入端防护存在盲区。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06503Oct 5
研究评测五款开源文生图模型的有害内容生成与审核缺口
评测文生图模型的有害内容生成能力与审核检测缺口
arXiv
2610.06503
Published
Oct 5
Layer
Model layer
Setting
Models and APIs
Evaluated models
SDXL, Stable Diffusion 3.5 Large, FLUX.1-dev and others12
- DefensesDetection and filtering
- AttacksMalicious use
- ComponentImage generation
Paper analysisRead analysis
DefensesarXiv 2610.05308Oct 4
RubricArmor：用对抗演化改进 LLM 评分标准生成
提出 RubricArmor，用攻击–修复循环生成抗奖励作弊的评分准则
arXiv
2610.05308
Published
Oct 4
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct, Qwen3-4B and others8
- RiskReward hacking
- ComponentGuardrails and judges
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.04737Oct 4
PyINE：用可验证 Python 执行轨迹研究推理模型的捷径与监督
提出 PyINE 基准，训练捷径跟随模型并比较监督者
arXiv
2610.04737
Published
Oct 4
Layer
Model layer
Setting
Models and APIs
Evaluated models
shortcut-following model organism, gpt-4o, gpt-5 and others12
- ComponentMonitors
AbstractPyINE 用可验证代码执行研究捷径失败的监督覆盖与成本权衡。
PyINE 是用可执行程序研究推理模型引出与监督的框架，PyINE-v1 是其第一次发布。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.03470Oct 2
CorrectGuard 提出黑盒安全护栏的免查看正确性估计框架
提出 CorrectGuard，在不可查看输入上估计黑盒护栏决策对错
arXiv
2610.03470
Published
Oct 2
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Granite Guardian 3.1 2B, Qwen3Guard 8B, GPT-OSS-Safeguard-20B and others7
- DefensesDetection and filtering
- ComponentGuardrails and judges
AbstractCorrectGuard 用外部模型估计黑盒护栏决策对错，排序和弃权可用，校准在偏移下变差。
CorrectGuard 面向不能人工检查生产输入、也没有生产标签的黑盒安全护栏，用外部模型估计单条决策是否正确，并据此排序和弃权。离线基准会随数据和攻击变化，未必代表生产分布。隐私约束还可能禁止模型查看原文或可反演的稠密嵌入。
Paper analysisRead analysis
DefensesarXiv 2610.03073Oct 2
SecJev：为 System One 决策模型引入安全专业知识
提出 SecJev，用场景加权训练把决策模型适配为安全类型化判断
arXiv
2610.03073
Published
Oct 2
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
SecJev-0.8B, SecJev-2B, SecJev-4B and others4
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
AbstractSecJev 用共享打分器做安全决策，0.8B 的 task-macro 超过 Kev-9B。
SecJev 是 0.8B 到 9B 的安全决策模型族，作者称据其所知是首个面向安全的 Jev-like 家族。
Paper analysisRead analysis
DefensesarXiv 2610.02853Oct 2
研究提出基于收缩约束状态空间模型的有界可达性与越狱检测方法
提出收缩约束 SSM 安全头，认证嵌入扰动并检测越狱
arXiv
2610.02853
Published
Oct 2
Layer
Prompt layer
Setting
Models and APIs
Attacker
White-box, Black-box
Evaluated models
ToySSMClassifier, S4 safety head
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
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。。
Paper analysisRead analysis
DefensesarXiv 2610.02824Oct 2
MetaRubric：面向评分标准强化学习的奖励方法
提出 MetaRubric，以证据感知奖励缓解评分标准强化学习的虚记分
arXiv
2610.02824
Published
Oct 2
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen3-4B, Qwen3-8B, Qwen3-VL and others5
- DefensesModel hardening
- RiskReward hacking
- ComponentGuardrails and judges
AbstractMetaRubric 用证据约束并在训练中改 rubric，医学基准上相对静态 GRPO 有提高。
MetaRubric 针对 rubric-based RL 里的空记分：评审在准则要求的信息或动作缺失时仍给高分。
Paper analysisRead analysis
Analysis and theoryarXiv 2610.02586Oct 2
Study finds typed decision models answer primarily based on option labels rather than definitions
揭示类型化决策模型按选项标签而非定义规则作答
arXiv
2610.02586
Published
Oct 2
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
laya-typed-decisions, laya, laya-multilingual and others9
- ComponentGuardrails and judges
Abstract揭示类型化决策模型被标签误导的机理，证实源于提示词渲染并给出实操建议。
Paper analysisRead analysis
DefensesarXiv 2610.01058Oct 1
MOMAT：面向量化 LLM 低功耗越狱防御的多图集混合框架
提出 MOMAT 多图集检索与轻量判定，防御量化模型越狱
arXiv
2610.01058
Published
Oct 1
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Llama2-13B, Llama2-7B, Mistral-7B
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
Paper analysisRead analysis
DefensesarXiv 2610.00883Oct 1
DeBERTa-ConPara：面向部署的 AI 生成文本检测，推理端 Unicode 归一化提升对抗鲁棒性
提出推理时 Unicode 归一化的检测器，识别遭字符级扰动的 AI 生成文本
arXiv
2610.00883
Published
Oct 1
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
microsoft/deberta-v3-large, deberta-v3-base, bert-large-cased and others4
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
Abstract推理时归一化消除两类 Unicode 攻击，训练时归一化则会删掉对抗监督。
DeBERTa-ConPara 是一个面向部署的 AI 文本检测器：DeBERTa-v3-large 在多数据集原始文本上训练，推理前做确定性 Unicode 归一化，用一个固定阈值面对没有目标域标签的场景。
Paper analysisRead analysis
DefensesarXiv 2609.38847Sep 30
ProRubric：通过协议级评分标准缓解 Rubric-RL 中的奖励作弊
提出 ProRubric，把加性评分聚合改为合取协议以抑制奖励作弊
arXiv
2609.38847
Published
Sep 30
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen3-4B, Qwen3-8B
- DefensesModel hardening
- RiskReward hacking
- ComponentGuardrails and judges
AbstractProRubric 用离线合取维度替换加性求和，在继续学习时抬高适当性且不损失覆盖率。
Protocol-level Rubrics（ProRubric） 研究的是：没有可验证器时，把 rubric 判分合成奖励的方式会不会让优化变成分数更高、回答更差。
Paper analysisRead analysis
AttacksarXiv 2609.38253Sep 29
CollageAttack: Exploiting cross-modal alignment defects for spatial text composition jailbreaks against T2I models.
提出 CollageAttack，用空间文本碎片重组越狱文生图模型
arXiv
2609.38253
Published
Sep 29
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
GPT-Image-2, Doubao-Seedream-5.0-Lite, Wan2.7-Image-Pro and others5
- AttacksJailbreaks
- TechniqueEncoding and obfuscation
- ComponentImage generation
Abstract系统揭示 T2I 跨模态空间合成安全漏洞，证实离散无害元素可在图像层面重构有害意图并放大传播强度。
Paper analysisRead analysis
DefensesarXiv 2609.36900Sep 29
STAR-GRPO：用可靠性优先优势估计抑制奖励作弊
提出 STAR-GRPO，用成对可靠性约束抑制奖励作弊
arXiv
2609.36900
Published
Sep 29
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-3.2-1B-Instruct, Qwen3-4B
- DefensesModel hardening
- RiskReward hacking
- ComponentGuardrails and judges
AbstractSTAR-GRPO 用成对可靠性约束 GRPO 优势，在两种奖励黑客设定中限制无支撑分数。
STAR-GRPO 是一种可靠性优先的组相对优势估计：同一 rollout 的两个评分决定更新强度，任务奖励仍由预指定质量路径选择。
Paper analysisRead analysis

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop