DefensesarXiv 2609.37054
ACTR：对齐推理与回答以提升推理大语言模型的多语言安全
提出 ACTR，只更新安全思考神经元以对齐推理与回答的安全类别
- arXiv
- 2609.37054
- Published
- Setting
- Models and APIs
- Evaluated models
- Qwen3-8B, Gemma4-12B-it
- DefensesModel hardening
- AttacksJailbreaks
- ComponentReasoning chains
Defenses and guardrails · Papers
- DefensesarXiv 2609.36562
ThinkingGuard：通过逐步风险归因解码多模态大语言模型中的隐式危害
构建 TriggerBench 并训练 ThinkingGuard，检测图文隐式风险
- arXiv
- 2609.36562
- Published
- Layer
- Prompt layer
- Setting
- Models and APIs
- Evaluated models
- ThinkingGuard（Qwen3-VL-8B-Instruct）
- DefensesDetection and filtering
- AttacksJailbreaks
- ComponentGuardrails and judges
AbstractTriggerBench 隔离触发条件，ThinkingGuard 用分步归因在隐式风险检测上取得作者报告的较高平均分。
这篇工作研究多模态隐式风险检测：图文各自良性，风险只在关键元素与触发元素交互时出现。
- DefensesarXiv 2609.34519
EOPSA：高效在策略自蒸馏安全对齐方法
提出 EOPSA，用 TRR 截断与安全类过滤做在策略自蒸馏安全对齐
- arXiv
- 2609.34519
- Published
- Setting
- Models and APIs
- Evaluated models
- Qwen3-1.7B, Qwen3-4B, Qwen3-14B and others5
- DefensesModel hardening
- AttacksJailbreaks
- ComponentReasoning chains
论文提出拒答的几何解释：事后安全训练脆弱，预训练期持续安全共训更抗攻击
解释后验安全的权重几何脆弱性，并提出预训练持续安全共训练
- arXiv
- 2609.06934
- Published
- Layer
- Model layer
- Setting
- Models and APIs
- Evaluated models
- Qwen-2.5-7B, Qwen-2.5-7B-Instruct, Llama-3-8B and others15
- DefensesModel hardening
- AttacksModel tampering
- RiskInappropriate refusal
- ComponentFine-tuning and open weights
Abstract论文将后验安全脆弱性归因于正交抑制，并提出通过预训练持续共训练实现具备微调抗性的安全防护。
- DefensesarXiv 2609.04714
无需拒答的拒答：减少语言模型误拒的安全微调响应结构分析
提出 Rationale-Only 安全微调，去掉拒答声明以降低误拒
- arXiv
- 2609.04714
- Published
- Setting
- Models and APIs
- Evaluated models
- Llama-3.1-8B, Mistral-7B-v0.3, Gemma-2-9B and others8
- DefensesModel hardening
- RiskInappropriate refusal
- ComponentFine-tuning and open weights
Abstract去掉套话拒答声明、只训理由，可降低假拒答，有害查询上的服从率仍低。
这是一项针对安全微调数据的结构分析：假拒答被作者追溯到回答里的套话式拒答声明，而不是只靠推理时补救。
- DefensesarXiv 2607.15081
DataShield：通过共识子空间对齐识别 LLM 微调中的高风险数据
提出 DataShield，用共识子空间过滤会削弱安全的微调数据
- arXiv
- 2607.15081
- Published
- Setting
- Models and APIs
- Evaluated models
- Phi3-medium-4k-it, Qwen3-4B-it, Gemma2-27B-it and others4
- DefensesDetection and filtering
- RiskInappropriate refusal
- ComponentFine-tuning and open weights
- DefensesarXiv 2604.00012
研究提出 SafeReAct：恢复后训练大模型被掩盖的安全机制
提出 SafeReAct，用 LoRA 重激活后训练模型被掩盖的安全机制
- arXiv
- 2604.00012
- Published
- Layer
- Model layer
- Setting
- Models and APIs
- Evaluated models
- DeepSeek-R1-distilled LLaMA-8B, DeepSeek-R1-distilled Qwen-7B, DeepSeek-R1-distilled Qwen-14B and others9
- DefensesModel hardening
- RiskInappropriate refusal
- ComponentReasoning chains
AbstractSafeReAct 用剪枝得到的安全表示做 LoRA 对齐，以恢复后训练模型被掩盖的拒绝行为。
这篇工作针对后训练 LLM 的安全下降，提出表示对齐方法SafeReAct。
- DefensesarXiv 2602.11096
Safety Recovery of Reasoning Models Only Needs a Few Early Steps of Guidance
提出推理时防御 SafeThink，监视思维链并在低于阈值时注入转向前缀
- arXiv
- 2602.11096
- Published
- Layer
- Model layer
- Setting
- Models and APIs
- Evaluated models
- R1-Onevision-7B, OpenVLThinker-7B, VLAA-Thinker-7B and others6
- DefensesInference-time intervention
- AttacksJailbreaks
- ComponentReasoning chains
You have reached the end