# transfer
標記為「transfer」的 22 篇文章
Cross-Model Transfer Assessment
Assessment of attack transferability across model families, versions, and providers.
Research Challenge: Cross-Model Transfer
Research-oriented challenge exploring the transferability of adversarial techniques across model families, with published findings.
Knowledge Distillation Attacks
Attacking knowledge distillation pipelines to transfer backdoors from teacher to student models or extract proprietary capabilities.
Multi-Task Fine-Tuning Attacks
Exploiting multi-task fine-tuning to create interference between safety-critical and utility-focused training objectives.
Cross-Lingual Transfer and Security
Research on how cross-lingual transfer affects safety training and creates exploitable multilingual gaps.
Cross-Architecture Injection Transfer
Research into how injection techniques transfer across model architectures and what architectural properties determine transferability.
Cross-Model Transfer Attacks
Develop attacks on open-source models that transfer to closed-source commercial APIs.
Cross-Model GCG Transfer Attacks
Generate adversarial suffixes on open-source models and test their transferability to commercial APIs.
Cross-Architecture Transfer Lab
Develop attacks on one model architecture that reliably transfer to fundamentally different architectures.
Transferring Attacks Across Modalities
Techniques for crafting adversarial inputs that transfer across modalities, using one input channel to attack processing in another, including image-to-text, audio-to-action, and document-to-tool attack chains.
Cross-Modal Transfer Attacks
Attacks that transfer across modalities — using one input modality to attack processing in another.
Cross-模型 Transfer 評量
評量 of attack transferability across model families, versions, and providers.
Research Challenge: Cross-模型 Transfer
Research-oriented challenge exploring the transferability of adversarial techniques across model families, with published findings.
Knowledge Distillation 攻擊s
攻擊ing knowledge distillation pipelines to transfer backdoors from teacher to student models or extract proprietary capabilities.
Multi-Task Fine-Tuning 攻擊s
利用ing multi-task fine-tuning to create interference between safety-critical and utility-focused training objectives.
Cross-Lingual Transfer and 安全
Research on how cross-lingual transfer affects safety training and creates exploitable multilingual gaps.
Cross-Architecture Injection Transfer
Research into how injection techniques transfer across model architectures and what architectural properties determine transferability.
Cross-模型 Transfer 攻擊s
Develop attacks on open-source models that transfer to closed-source commercial APIs.
Cross-模型 GCG Transfer 攻擊s
Generate adversarial suffixes on open-source models and test their transferability to commercial APIs.
Cross-Architecture Transfer 實驗室
Develop attacks on one model architecture that reliably transfer to fundamentally different architectures.
Transferring 攻擊s Across Modalities
Techniques for crafting adversarial inputs that transfer across modalities, using one input channel to attack processing in another, including image-to-text, audio-to-action, and document-to-tool attack chains.
Cross-Modal Transfer 攻擊s
攻擊s that transfer across modalities — using one input modality to attack processing in another.