Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.

Attack technique：Gradient and representation optimization Attack technique：Multi-turn escalation Attack technique：Encoding and obfuscation Attack technique：Conversation structure manipulation Impact：Harmful content Clear all

Another 213papers do not have category tags yet and are not included in filtered results.

Evaluation and benchmarksarXiv 2610.11766Oct 8
研究提出意图恢复率作为 LLM 安全评测的补充指标
提出 IRIS，用意图恢复率区分遮蔽越狱下无害输出的原因
arXiv
2610.11766
Published
Oct 8
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
GPT-4o, Claude Sonnet 4.5, Claude Opus 4.5 and others6
- AttacksJailbreaks
- TechniqueEncoding and obfuscation
Abstract无害输出的证据权重取决于任务是否被恢复。
IRIS 把意图恢复当作中间信号，用来解释意图遮蔽提示下为何没有出现有害协助。
Paper analysisRead analysis
AttacksarXiv 2610.09973Oct 7
从期望危害到似然：LLM 智能体越狱的概率重构
提出 OPUR 攻击，用似然梯度优化对抗后缀越狱 LLM 智能体
arXiv
2610.09973
Published
Oct 7
Layer
Application layer
Setting
AI Agent
Attacker
White-box
Evaluated models
Llama-3.1-8B-Instruct, Ministral-8B-Instruct-2410
- AttacksJailbreaks
- TechniqueGradient and representation optimization
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.09033Oct 7
研究发布 ASRD 数据集，评测五款开源模型在非规范输入下的安全表现
arXiv
2610.09033
Published
Oct 7
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Gemma 2 9B, Gemma 3 4B, Llama 3.1 8B and others6
- AttacksJailbreaks
- TechniqueEncoding and obfuscation
Abstract五模型、七族表面形式的四态评测里，低有害遵从不等于读懂后的安全处理。
ASRD 用四态标签检查五个开源模型如何处理非规范表面上的有害请求。
Paper analysisRead analysis
AttacksarXiv 2610.02302Oct 2
研究者提出意图隐藏越狱的信息论框架，分析组合式攻击
提出组合式意图隐藏越狱，按先验后验匹配选择辅助任务
arXiv
2610.02302
Published
Oct 2
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Qwen3-1.7B, Qwen3-4B, Qwen3-8B and others7
- AttacksJailbreaks
- TechniqueEncoding and obfuscation
Abstract用信息论选含目标的任务组合，再看查询能否既隐藏意图又让目标被执行。
这篇工作把组合式意图隐藏写成任务选择：有害目标必须留在 bundle 里，同时让估计的有害意图概率贴近全集先验，或降到阈值以下。
Paper analysisRead analysis
AttacksarXiv 2610.01367Oct 1
研究：高质量数据筛选挡不住投毒
提出 Bi-QSTO，优化能穿过质量筛选并在微调中削弱安全对齐的投毒样本
arXiv
2610.01367
Published
Oct 1
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama2-7B-Chat, Llama3-8B-Instruct, Qwen2-7B-Instruct and others5
- AttacksPoisoning and backdoors
- TechniqueGradient and representation optimization
- ComponentFine-tuning and open weights
Abstract质量筛选挡不住部分高分样本的安全削弱。
Bi-QSTO 研究一个实际训练缺口：基于质量的数据选择会先于微调决定样本去留，而以往微调投毒多假设毒样本直接进入训练集。已对齐 LLM 的拒答会被少量有害或看似无害的微调样本削弱。作者用三个问题串起实验：选择能否排除毒样本。
Paper analysisRead analysis
AttacksarXiv 2610.01062Oct 1
Kernelized Activation Steering：将激活引导推广到再生核希尔伯特空间的新框架
提出核化激活引导 KAS，在推理时自适应转向激活以诱导越狱
arXiv
2610.01062
Published
Oct 1
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen2.5-7B-Instruct, Gemma-2-9B-IT, Llama-3.1-8B-Instruct and others4
- AttacksModel tampering
- TechniqueGradient and representation optimization
AbstractKAS 用核梯度做局部自适应转向，并在线性核下恢复 DiM。
Kernelized Activation Steering（KAS） 把推理时的激活转向写成核空间中的优化，使更新随当前激活相对源、目标参考集的位置而变化。
Paper analysisRead analysis
AttacksarXiv 2609.39902Sep 30
CodeMimicry: Exploiting code-domain safety generalization lag for structured code completion jailbreaks.
提出 CodeMimicry，以结构化代码补全诱导模型生成有害内容
arXiv
2609.39902
Published
Sep 30
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
GPT-4o, GPT-4.1, GPT-5-chat and others10
- AttacksJailbreaks
- TechniqueEncoding and obfuscation
Paper analysisRead analysis
AttacksarXiv 2609.39788Sep 30
研究：多智能体系统潜在通信链路可被训练用于提升有害顺从
提出只训练或篡改多智能体潜在通信链路来提高有害遵从
arXiv
2609.39788
Published
Sep 30
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct, Gemma-3-1B-IT and others7
- AttacksModel tampering
- TechniqueGradient and representation optimization
Abstract潜在链路本身即可改变冻结智能体系统的安全，奖励既能攻击也能修复。
学习得到的潜在通信链路会改变由冻结、对齐智能体组成的系统是否遵从有害请求。。作者研究三种拓扑：双智能体、三级顺序协作，以及双专家加汇总。
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
AttacksarXiv 2609.36956Sep 29
研究者提出 Controlled Decoding Attacks，通过纯文本接口越狱黑盒 LLM
提出 BLINDBIAS，通过纯文本续写与前缀控制越狱黑盒模型
arXiv
2609.36956
Published
Sep 29
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
GLM-5, Gemini-3.5-Flash, Qwen3-32B and others4
- AttacksJailbreaks
- TechniqueConversation structure manipulation
Abstract作者认为，隐藏数值概率并不足以消除支持重复采样和前缀续写的解码攻击面。
BLINDBIAS 是一种针对 sample-only 续写接口的 black-box 解码时越狱框架，研究没有目标数值概率时，采样能否支持逐步控制。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.36849Sep 29
研究评估 GradSafe 在多轮对话中的越狱检测脆弱性
评测多轮对话中 GradSafe 越狱检测的可分性与脆弱性
arXiv
2609.36849
Published
Sep 29
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Llama 3.1 8B Instruct, Qwen2.5-7B-Instruct
- DefensesDetection and filtering
- AttacksJailbreaks
- TechniqueMulti-turn escalation
- ComponentGuardrails and judges
AbstractCWS 显示不安全梯度在真实多轮流量中变弱，且随攻击族和模型而变。
作者评估梯度越狱检测从单条提示词迁到多轮对话后还剩多少可分性，方法是用 Context Window Scanner 把 GradSafe 原封不动地套到用户轮窗口上。
Paper analysisRead analysis
AttacksarXiv 2609.29775Sep 24
输出前缀攻击瞄准推理模型
提出推理通道预填与输出前缀组合攻击以越狱推理模型
arXiv
2609.29775
Published
Sep 24
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Gemini 3 Flash Preview, DeepSeek V4 Flash, Claude Haiku 4.5
- AttacksJailbreaks
- TechniqueReasoning-chain manipulation
- ComponentReasoning chains
Paper analysisRead analysis
InterpretabilityarXiv 2609.24801Sep 22
研究用 XAI 归因分析 Prompt Guard 2，同义词替换可翻转其提示注入判定
用词级归因指导同义词替换，翻转提示注入检测并验证越狱
arXiv
2609.24801
Published
Sep 22
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Prompt Guard 2 (86M), Llama 3.1 8B
- DefensesDetection and filtering
- AttacksDetection evasion
- TechniqueGradient and representation optimization
- ComponentGuardrails and judges
Abstract作者称检测靠分散的词法线索。
Paper analysisRead analysis
AttacksarXiv 2609.09553Sep 9
研究：任意密文攻击前沿大模型无需微调即可越狱
提出任意字母置换密码越狱，无需微调即可诱导有害输出
arXiv
2609.09553
Published
Sep 9
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Claude Sonnet 4, Claude Sonnet 4.5, Gemini 3 Flash (preview) and others7
- AttacksJailbreaks
- TechniqueEncoding and obfuscation
- ComponentGuardrails and judges
Abstract前沿大模型无需微调即可通过提示词学会字母置换密码，进而绕过分类器与对齐，作者呼吁关注能力提升带来的安全风险。
Paper analysisRead analysis
AttacksarXiv 2609.08373Sep 8
结构越狱可跨厂商泛化但不叠加：IICL 的跨厂商与多语言研究
检验结构越狱 IICL 能否跨厂商泛化并与语言约束叠加
arXiv
2609.08373
Published
Sep 8
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
gemini-2.5-flash, gemini-2.5-flash-lite
- AttacksJailbreaks
- TechniqueConversation structure manipulation
Paper analysisRead analysis
AttacksarXiv 2609.07216Sep 7
DIVA：利用视觉锚点对视频生成模型实施多模态越狱
提出 DIVA，将有害意图拆成视觉锚点与运动文本以越狱视频生成模型
arXiv
2609.07216
Published
Sep 7
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Wan, CogVideoX, LTX-Video and others9
- AttacksJailbreaks
- TechniqueCross-modal payloads
- ComponentImage generation
AbstractDIVA 用视觉锚点抑制语义漂移做视频越狱，并给出多条件安全基准 TI2VSafetyBench。
DIVA 是针对带参考图的视频生成模型的免训练 black-box 越狱：用一致性机制本身堵住语义漂移这条安全逃逸路径。。
Paper analysisRead analysis
AttacksarXiv 2609.02414Sep 2
Blueprint 框架用世界观模拟与 18 个影响因子提升多轮越狱成功率
提出多轮越狱框架 BLUEPRINT，用世界观模拟与心理因素诱导有害输出
arXiv
2609.02414
Published
Sep 2
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Qwen3-Next-80B, DeepSeek-V3.2, GLM-4.7 and others6
- AttacksJailbreaks
- TechniqueMulti-turn escalation
AbstractBLUEPRINT 解耦多轮越狱策略与情境模拟，揭示任务具象化是摆脱拒绝的核心机制，为多轮安全防御提供新视角。
BLUEPRINT 是一个将因子化社会影响力策略空间与跨轮世界观模拟解耦的多轮大语言模型安全评测框架。
Paper analysisRead analysis
AttacksarXiv 2609.02172Sep 2
BOSS：以广度优先后缀搜索改进 GCG 越狱优化
提出广度优先后缀搜索 BOSS，改进 GCG 越狱优化
arXiv
2609.02172
Published
Sep 2
Layer
Prompt layer
Setting
Models and APIs
Attacker
White-box
Evaluated models
Llama-2-7B-Chat, Yi-1.5-9B-Chat, Qwen2-7B-Instruct and others8
- AttacksJailbreaks
- TechniqueGradient and representation optimization
AbstractBOSS 把 GCG 类优化从单条深搜索改为多条短轨迹加源侧诊断。
BOSS 是插在 GCG 类离散 suffix 优化上的搜索框架：局部梯度更新不变，变的是固定预算花在深度还是广度。
Paper analysisRead analysis
AttacksarXiv 2609.05525Sep 2
DIVA：针对离散扩散视觉语言模型的跨步条件传播视觉越狱
提出 DIVA，利用跨步条件传播对离散扩散视觉语言模型实施视觉越狱
arXiv
2609.05525
Published
Sep 2
Layer
Prompt layer
Setting
Models and APIs
Attacker
White-box
Evaluated models
LLaDA-V, MMaDA, LLaDA2.0-Uni
- AttacksJailbreaks
- TechniqueGradient and representation optimization
- ComponentVision
Paper analysisRead analysis
AttacksarXiv 2608.07430Aug 8
研究者提出 SN-Guided Diffusion，利用扩散大模型安全神经元实现离线越狱
提出 SN-Guided Diffusion，利用安全神经元实现离线越狱
arXiv
2608.07430
Published
Aug 8
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box, White-box
Evaluated models
Qwen2.5-7B-Instruct, LLaDA-8B-Instruct, Dream-Instruct-7B and others15
- AttacksJailbreaks
- TechniqueGradient and representation optimization
Abstract论文揭示了扩散语言模型对自回归安全神经元的继承性，并提出纯离线黑盒越狱框架 SN-Guided Diffusion。
论文系统评估了扩散大语言模型（DLLM）在安全对齐中的双重角色——既作为白盒攻击目标，又作为黑盒越狱生成的对抗工具。
Paper analysisRead analysis

AI Safety Daily

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