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.

Attack type：Jailbreaks Defense type：Inference-time intervention Defense type：Permissions and approval Clear all

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

Evaluation and benchmarksarXiv 2610.10276Oct 7
PatchBench 提出激活补丁局部评测协议，揭示越狱修复的附带损伤
提出 PatchBench-Local 协议，评测激活补丁修复越狱的局部附带损伤
arXiv
2610.10276
Published
Oct 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen2.5-3B-Instruct, Qwen2.5-14B-Instruct, gemma-3-4b-it and others8
- DefensesInference-time intervention
- AttacksJailbreaks
Abstract论文提出 PatchBench 与局部评估协议，揭示了激活补丁在全局能力无损下仍存局部良性退化。
Paper analysisRead analysis
DefensesarXiv 2610.09703Oct 7
研究揭示 Token-Pruning 对 VLM 安全性的影响并提出 SAP 缓解机制
提出 Safety-Aware Pruning，缓解视觉 token 剪枝放大的多模态越狱
arXiv
2610.09703
Published
Oct 7
Layer
Model layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
LLaVA-1.5-7B
- DefensesInference-time intervention
- AttacksJailbreaks
- ComponentVision
Abstract剪枝去掉背景 token 后注意力塌向恶意前景。
这篇工作评估视觉 token 剪枝如何改变 VLM 在多模态越狱下的行为，并给出推理时防御 SAP。
Paper analysisRead analysis
DefensesarXiv 2610.08678Oct 7
研究揭示投机解码的安全代价并提出 SecureSD 加固方法
测量有损投机解码的安全代价，并提出 SecureSD 收紧早期验证
arXiv
2610.08678
Published
Oct 7
Layer
Model layer
Setting
AI Agent
Attacker
Black-box
Evaluated models
Qwen3-8B, Qwen3-32B, Llama-3.1-8B-Instruct and others6
- DefensesInference-time intervention
- AttacksJailbreaks
Abstract有损推测解码的早期偏离更快抬高越狱与注入风险。
作者研究有损推测解码在换取速度时，是否会比效用更快地损害越狱与提示注入防护，并给出按位置校正的 SecureSD。
Paper analysisRead analysis
DefensesarXiv 2610.04470Oct 3
SENTINEL：通过意图感知的输入-输出匹配防御 LLM 越狱
提出生成时防御 SENTINEL，匹配输入输出以抽出越狱意图并停写
arXiv
2610.04470
Published
Oct 3
Layer
Model layer
Setting
Models and APIs
Attacker
White-box
Evaluated models
Llama2-7B, Llama3-8B, Mistral-7B-v0.2 and others6
- DefensesInference-time intervention
- AttacksJailbreaks
Paper analysisRead analysis
DefensesarXiv 2609.36657Sep 29
Constitutional adapters：用推理期干预防御越狱与失准
提出 Constitutional adapters，蒸馏宪法行为以缓解越狱与失准
arXiv
2609.36657
Published
Sep 29
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3.5-4B, Llama-3.1-8B-Instruct, Gemma-4-E4B and others4
- DefensesInference-time intervention
- AttacksJailbreaks
- RiskMisalignment and value divergence
Abstract差分宪法适配器在长上下文和多轮上更稳，并可按 α 换取遵从。
Paper analysisRead analysis
DefensesarXiv 2609.34518Sep 28
SEAD 论文提出工具型 Agent 的状态视角攻击与防御方法 DART 与 SAGE
提出工具型 Agent 的自适应攻击 DART 与预执行防御 SAGE
arXiv
2609.34518
Published
Sep 28
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-5.6 Luna, GPT-5.6 Terra, Gemini 3.8 Flash and others5
- DefensesPermissions and approval
- AttacksJailbreaks
- ComponentPermissions and sandboxing
Abstract论文提出状态控制框架 SEAD、攻击 DART 与防御 SAGE，实验显示执行反馈与环境探测在攻防交互中具有关键作用。
Paper analysisRead analysis
DefensesarXiv 2609.34514Sep 28
CAM-Steer：面向大语言模型的多类别自适应安全引导框架
提出 CAM-Steer，推理时按多类别风险引导隐藏状态以降低有害回复
arXiv
2609.34514
Published
Sep 28
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3-8B, Llama-3.1-8B-Instruct, Gemma-2-9B-IT
- DefensesInference-time intervention
- AttacksJailbreaks
Paper analysisRead analysis
DefensesarXiv 2609.29287Sep 24
AEGIS：用内部信号在中间层拦截大型音频语言模型越狱
提出 AEGIS，用中层内部信号选择性激活后层适配器拦截音频越狱
arXiv
2609.29287
Published
Sep 24
Layer
Model layer
Setting
Models and APIs
Attacker
White-box
Evaluated models
Qwen2-Audio-7B, VITA-1.5, Ultravox v0.5 and others6
- DefensesInference-time intervention
- AttacksJailbreaks
- ComponentAudio
Paper analysisRead analysis
DefensesarXiv 2609.28693Sep 24
skilder：以角色化技能包为工具型 LLM 智能体做访问控制
提出 Skilder，按角色渐进下发企业工具并确定性拦截越权调用
arXiv
2609.28693
Published
Sep 24
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Haiku 4.5, Qwen 3.5 122B, Gemma 4 31B and others6
- DefensesPermissions and approval
- AttacksJailbreaks
- ComponentMCP and skills
AbstractSkilder 用单 MCP 服务器按角色交付工具并硬拦截。
Skilder 把企业工具型智能体的能力按角色打包，经一个 MCP 服务器做渐进发现，使工具范围由服务器而不是提示词来执行。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.22076Sep 19
APort Vault released: evaluating AI agent payment authorization with 4,371 human-written attacks
构建 APort Vault 基准，对比支付智能体模型拒答与确定性授权
arXiv
2609.22076
Published
Sep 19
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Fable 5.1, Claude Sonnet 5, Claude Haiku 4.5 and others14
- DefensesPermissions and approval
- AttacksJailbreaks
- ComponentPermissions and sandboxing
Paper analysisRead analysis
DefensesarXiv 2609.14258Sep 13
SPARK：在 KV 记忆层对齐表征以防御视觉语言模型越狱
提出 SPARK，在预填充阶段修复多模态 KV 记忆以防御视觉语言模型越狱
arXiv
2609.14258
Published
Sep 13
Layer
Model layer
Setting
Models and APIs
Attacker
White-box
Evaluated models
LLaVA-OneVision-7B, Chameleon-7B, Qwen2-VL-7B and others4
- DefensesInference-time intervention
- AttacksJailbreaks
- ComponentVision
Paper analysisRead analysis
DefensesarXiv 2609.14003Sep 12
FlowSeal：用信息流控制阻断 LLM Agent 的隐私泄露
提出 FLOWSEAL，用工具级信息流控制阻断智能体隐私泄露
arXiv
2609.14003
Published
Sep 12
Layer
Application layer
Setting
AI Agent
Evaluated models
DeepSeek-V3.2, GPT-4.1-mini, Gemini-Flash-2.5
- DefensesInstruction–data separation
- AttacksJailbreaks
- ComponentPermissions and sandboxing
Abstract作者分析大模型智能体隐私检查与攻击面重合问题，提出外部拦截防御 FLOWSEAL 并验证有效性。
Paper analysisRead analysis
DefensesarXiv 2609.05903Sep 5
EvoSafeHarness：为 Agent 自动演化模型与领域专属安全护栏
为冻结模型与目标域自动搜索可部署的 Agent 安全 harness
arXiv
2609.05903
Published
Sep 5
Layer
Application layer
Setting
AI Agent
Evaluated models
Sonnet 4.6, GLM-5, Kimi-K2.5 and others11
- DefensesInstruction–data separation
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Paper analysisRead analysis
InterpretabilityarXiv 2609.04721Sep 4
研究：拒答方向可跨架构迁移，安全工具可按写入位置重新估计
在写入点定位拒答方向，经刚性旋转跨架构迁移并门控放大
arXiv
2609.04721
Published
Sep 4
Layer
Model layer
Setting
Models and APIs
Evaluated models
Falcon-Mamba-7B, Falcon3-Mamba-7B, Llama-3.1-8B and others8
- DefensesInference-time intervention
- AttacksJailbreaks
- RiskInappropriate refusal
- ComponentMonitors
Abstract拒答方向可经刚性旋转跨架构迁移，但必须在各架构的写入点读取。
作者研究拒答表示是否随架构改变，结论是表示共享、读取位置随架构变。
Paper analysisRead analysis
DefensesarXiv 2608.28233Aug 28
REINS：用 SAE 特征同时抑制有害续写并增强拒答的引导方法
提出 REINS，在 SAE 空间抑制有害延续并增强拒答
arXiv
2608.28233
Published
Aug 28
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3.5-4B-Base, Qwen3.5-2B-Base, Gemma-3-1B-IT
- DefensesInference-time intervention
- AttacksJailbreaks
AbstractREINS 分角色抑制有害延续并增强拒答。
REINS 是一种推理时 SAE 安全转向方法，并配有用于上下文伪装的基准 GUISE。
Paper analysisRead analysis
DefensesarXiv 2606.08234Jun 6
SciTrace：面向科学发现智能体的轨迹感知安全推理框架
提出 SciTrace，为科学发现智能体加入跨阶段安全推理与工具轨迹核验
arXiv
2606.08234
Published
Jun 6
Layer
Application layer
Setting
science agent, Multi-agent systems
Evaluated models
Llama-3.1-70B-Instruct, Qwen2.5-72B-Instruct, DeepSeek-V3 and others4
- DefensesInference-time intervention
- AttacksPrompt injection
- RiskDangerous capabilities
- ComponentGuardrails and judges
AbstractSciTrace 把安全推理织入科学智能体各阶段，在 SciSafetyBench 上提高安全指标并保持输出质量。
SciTrace 是加在科学发现智能体流水线上的安全框架，不是再在各阶段出口放一个独立过滤器。
Paper analysisRead analysis
InterpretabilityarXiv 2603.08234Mar 9
续写与拒答之争：大语言模型中续写触发越狱的机制分析
分析续写触发越狱的注意力头机制并提出 HCS
arXiv
2603.08234
Published
Mar 9
Layer
Model layer
Setting
Models and APIs
Evaluated models
LLaMA-2-7B-Chat, Qwen2.5-7B-Instruct
- DefensesInference-time intervention
- AttacksJailbreaks
- TechniqueConversation structure manipulation
Abstract作者称越狱来自两类头竞争，HCS 加蒸馏可把该竞争用于推理时干预。
作者用注意力头机制分析 continuation-triggered jailbreak：同一有害指令下，把 continuation 后缀从指令后面挪到提示词边界外，模型更容易顺着后缀继续生成。
Paper analysisRead analysis
DefensesarXiv 2602.11096Feb 12
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
Feb 12
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
Paper analysisRead analysis

You have reached the end

AI Safety Daily

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