Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.

System type：Models and APIs Attack surface / entry point：Distribution channels Attack surface / entry point：Inference services and hardware Clear all

Another 265papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.13928Oct 10
AI models can provably hide arbitrary capabilities
Proposes digital lock compilation, encrypting executable networks into host weights to hide arbitrary capabilities
arXiv
2610.13928
Published
Oct 10
Layer
Model layer
Setting
Models and APIs
Evaluated models
Gemma 3 270M
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
AbstractThe authors use a digital lock to hide an executable capability and state that elicitation on the chemistry and parity tasks did not recover the capability.
The authors construct a class of backdoors that encrypt an executable network into the weights, used to discuss the limits of white-box elicitation audits under supply chain attacks.
Paper analysisRead analysis
AttacksarXiv 2610.09819Oct 7
FAB 攻击：给 HuBERT/WavLM 植入后门，背景警笛声即可让下游语音任务失灵
提出 FAB 攻击，向声学基础模型植入可由环境声触发的后门
arXiv
2610.09819
Published
Oct 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
HuBERT-base, WavLM-base
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentAudio
Abstract论文提出了针对声学基模的 FAB 后门攻击，在弱威胁模型下实现了任务无关、物理可触发的后门植入。
Paper analysisRead analysis
DefensesarXiv 2610.07476Oct 6
研究量化功耗测量对隐藏算力的约束能力
量化片外功耗测量对隐藏算力的约束能力
arXiv
2610.07476
Published
Oct 6
Layer
Infrastructure layer
Setting
Models and APIs
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。
Paper analysisRead analysis
AttacksarXiv 2610.06848Oct 6
TranScope：利用 CPU 性能计数器对 Transformer 做成员推断攻击
提出 TRANSCOPE，用 CPU 硬件计数器推断训练集成员
arXiv
2610.06848
Published
Oct 6
Layer
Infrastructure layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
BERT (4.4M-340M), ViT (22M-307M), Pythia (70M-2.8B) and others5
- AttacksExtraction and theft
- TechniqueSide channels
AbstractTRANSCOPE 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。
Paper analysisRead analysis
AttacksarXiv 2610.06049Oct 5
研究者提出仅修改 SAE 解码器的后门攻击，可在不改动语言模型的情况下植入行为
提出只改 SAE 解码器的后门，在冻结语言模型上植入代码插入
arXiv
2610.06049
Published
Oct 5
Layer
Model layer
Setting
Models and APIs
Evaluated models
Gemma 3 4B Instruct, Qwen3 1.7B, Llama 3.1 8B Instruct
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
Abstract只改解码器的 SAE 可带上代码插入后门，且若干常规质量指标变化不大。
只改 SAE 解码器、冻结编码器与语言模型，即可把代码插入行为放进推理时的辅助组件。作者把这视为 SAE 供应链问题：checkpoint 一旦替换某一层激活，就参与后续计算，而不只是解释工具。
Paper analysisRead analysis
AttacksarXiv 2610.05894Oct 5
研究者提出闭环偏见注入攻击
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
arXiv
2610.05894
Published
Oct 5
Layer
Model layer
Setting
Models and APIs
Attacker
Gray-box
Evaluated models
LLaDA-8B-Instruct, Dream-v0-Instruct-7B, LLaDA-MoE-7B-A1B-Instruct
- AttacksModel tampering
- TechniqueGradient and representation optimization
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。
Paper analysisRead analysis
AttacksarXiv 2610.05453Oct 5
研究者提出 Privacy-Leaking Watermarks，可在本地多模态模型中泄露对话隐私
提出 PLW，用微调把先前对话敏感触发编码进后续生成图像
arXiv
2610.05453
Published
Oct 5
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
OmniGen2, BAGEL-7B
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
AbstractPLW 把先前对话线索写成后续图像中的隐水印，检出随触发、模型和间隔变化。
Paper analysisRead analysis
Analysis and theoryarXiv 2610.02504Oct 2
HXAI：分布式能源系统中的分层隐私保护可解释 AI 框架
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
arXiv
2610.02504
Published
Oct 2
Layer
Infrastructure layer
Setting
Models and APIs
Evaluated models
gradient-boosted tree regression models
- AttacksExtraction and theft
AbstractHXAI 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。
Paper analysisRead analysis
DefensesarXiv 2609.39548Sep 30
NDDL：用正常扩散动力学为文生图模型做后门防御
提出 NDDL，用良性扩散轨迹检测文生图后门提示并定位触发 token
arXiv
2609.39548
Published
Sep 30
Layer
Model layer
Setting
Models and APIs
Evaluated models
Stable Diffusion v1.5, Stable Diffusion XL, Stable Diffusion v3.5 and others4
- DefensesMonitoring and auditing
- AttacksPoisoning and backdoors
- ComponentImage generation
AbstractNDDL 从良性扩散轨迹学习正常转移，用动态不一致检测后门并定位触发 token。
NDDL 是面向文生图扩散模型的后门防御：防御者只有白盒模型访问和良性提示词，没有后门先验，需要区分后门提示词并找出触发 token。
Paper analysisRead analysis
AttacksarXiv 2609.39047Sep 30
BadAction：通过动作引导触发器对交互式视频生成模型实施后门攻击
提出 BadAction，通过动作触发器给交互式视频生成植入后门
arXiv
2609.39047
Published
Sep 30
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Astra (Wan2.1-T2V-1.3B)
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Paper analysisRead analysis
DefensesarXiv 2609.38239Sep 29
推理层安全：防御对抗性推理与基础设施滥用
用 SCM 合成会话并训练检测器识别推理层滥用
arXiv
2609.38239
Published
Sep 29
Layer
Infrastructure layer
Setting
Models and APIs
Evaluated models
gradient-boosted detector (GBDT/XGBoost)
- DefensesDetection and filtering
- AttacksJailbreaks
Paper analysisRead analysis
AttacksarXiv 2609.33569Sep 27
信息黑洞：3D 点云重建中的后门机制研究
提出 Information Blackhole 与 AGM，控制点云自编码器后门重建到指定形状
arXiv
2609.33569
Published
Sep 27
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
FoldingNet, PointDiffusion
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
AbstractAGM 用自适应高斯匹配压制 PCAE 投毒潜码中的源几何，九组设置的 CD-ASD 均下降。
这篇工作研究点云自编码器的训练时后门：干净输入仍自重建，带触发的输入应重建成攻击者指定形状。分类后门只需把预测推向离散标签。PCAE 把源几何与目标信息编进同一个连续潜空间，残留源几何会把重建拉回源形状。
Paper analysisRead analysis
Analysis and theoryarXiv 2609.29757Sep 24
OllamaDrama：用蜜罐测量暴露 LLM 基础设施遭受的攻击
部署蜜罐测量针对暴露 LLM 基础设施的攻击
arXiv
2609.29757
Published
Sep 24
Layer
Infrastructure layer
Setting
Models and APIs
Paper analysisRead analysis
AttacksarXiv 2609.06749Sep 7
PMA 攻击：针对隐私保护 LLM 中嵌入到嵌入混淆的语义流形对齐方法
提出 PMA，用流形对齐从 E2EO 混淆向量恢复明文
arXiv
2609.06749
Published
Sep 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
BERT-base, RoBERTa-base, T5-base and others6
- AttacksExtraction and theft
- ComponentEmbeddings
Paper analysisRead analysis
OtherarXiv 2609.05241Sep 4
10a Labs 测绘无审查开源模型生态：3,471 个原始模型与 8,164 次再分发
梳理去护栏开源模型的生产、再分发与部署供应链
arXiv
2609.05241
Published
Sep 4
Layer
Training and data layer
Setting
Models and APIs
- AttacksModel tampering
- ComponentFine-tuning and open weights
Abstract这是一份去护栏模型供应链调查，作者将再分发层视为持续供给和下游部署的连接点。
10a Labs 调查的是去护栏模型的公开供应链，而非去护栏技术的效果排行榜。作者关注安全行为被移除后，模型如何继续被复制、转换并接入应用。
Paper analysisRead analysis
DefensesarXiv 2608.25431Aug 26
GIFT：通过 GPU 信息流追踪在 LLM 服务中实现用户数据隔离
提出 GIFT，用加密与 GPU 信息流跟踪隔离共享 LLM 服务中的用户数据
arXiv
2608.25431
Published
Aug 26
Layer
Infrastructure layer
Setting
Models and APIs
Evaluated models
Qwen2.5-14B, Qwen2.5-32B, Qwen2.5-72B and others6
- DefensesInstruction–data separation
- AttacksExtraction and theft
AbstractGIFT 以加密隔离加 GPU 信息流规则，在 vLLM 与 DistServe 上强制用户数据隔离，并报告了吞吐开销。
GIFT 是作者为共享 LLM serving 做的用户数据隔离系统，并有启用机密计算的 GIFT-CC。作者在结论中称它是该场景的首个 IFT 设计。
Paper analysisRead analysis
DefensesarXiv 2608.24354Aug 25
RACER：面向多模态大模型后门的区域感知一致性修复框架
提出 RACER，用区域感知一致性对抗微调去除多模态大模型后门
arXiv
2608.24354
Published
Aug 25
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
LLaVA-1.5-7B, Qwen2-VL-7B, Qwen2.5-VL-7B
- DefensesModel hardening
- AttacksPoisoning and backdoors
- ComponentVision
Paper analysisRead analysis
AttacksarXiv 2608.17485Aug 18
KeyPooling：测量 LLM API 中继路径在何处瓦解提示缓存隔离
提出 KeyPooling，测量 API 中继何处瓦解提示缓存隔离
arXiv
2608.17485
Published
Aug 18
Layer
Infrastructure layer
Setting
Models and APIs
Evaluated models
grok-4-fast-non-reasoning, grok-4-1-fast-non-reasoning, grok-3 and others11
- AttacksExtraction and theft
- TechniqueSide channels
Abstract共享上游凭证使中继客户进入同一缓存域，保留身份或独立 principal 可分开。
KeyPooling测量 LLM API 中继在何处丢掉客户身份，使 prompt cache 不再按下游客户隔离。
Paper analysisRead analysis
DefensesarXiv 2608.05578Aug 6
AMS 工具通过激活分析检测语言模型的安全训练改动
提出 AMS，用激活分离与方向相似度检测安全训练改动
arXiv
2608.05578
Published
Aug 6
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama-3.1-8B-Instruct, Llama-3.2-3B-Instruct, Llama-3.2-1B-Instruct and others14
- DefensesMonitoring and auditing
- AttacksModel tampering
- ComponentFine-tuning and open weights
AbstractAMS 按激活签名把安全改动分四类，前三类可由两级扫描覆盖，行为微调会漏。
AMS 是面向开放权重模型、部署前使用的激活扫描器，用来看安全训练被拿掉或改写之后，激活空间里还留着什么几何痕迹。
Paper analysisRead analysis
DefensesarXiv 2608.02271Aug 3
Z-PEFT：基于规范谱特征的参数高效微调零样本后门检测
提出 Z-PEFT，用逐头谱特征零样本检测 PEFT 后门
arXiv
2608.02271
Published
Aug 3
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Z-PEFT, Llama-2-7B, Llama-2-13B and others6
- DefensesDetection and filtering
- AttacksPoisoning and backdoors
- ComponentFine-tuning and open weights
Paper analysisRead analysis

AI Safety Daily

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