Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.

System type：Models and APIs System type：coding agent System type：Browser and computer use Attack surface / entry point：User input Attack surface / entry point：Weights and gradients Layer：Training and data layer Clear all

Another 215papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.12644Oct 9
Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.
Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.
arXiv
2610.12644
Published
Oct 9
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentReasoning chains
AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.
Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.
Paper analysisRead analysis
DefensesarXiv 2610.12233Oct 9
ReSI: A recursive safety improvement framework for attack resistance and unknown-risk resistance.
Proposes ReSI, which recursively improves model safety alignment using automatic red teaming and recipe search.
arXiv
2610.12233
Published
Oct 9
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen3.6-27B, Ministral-3-14B-Reasoning-2512, DeepSeek-V4-Flash-0731 and others4
- DefensesModel hardening
- AttacksJailbreaks
Paper analysisRead analysis
DefensesarXiv 2610.11005Oct 8
研究：叙事包装可跨语言绕过 LLM 拒答
提出 GUISE 基准与 AXIS 训练，防御叙事包装越狱
arXiv
2610.11005
Published
Oct 8
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen3-1.7B, Qwen3-4B, GLM-4-9B
- DefensesModel hardening
- AttacksJailbreaks
AbstractGUISE 分开测包装与语域。
作者测量叙事包装下的拒答失效，并训练一个在未见包装上拒绝、同时仍回答同风格良性请求的适配器。问题是：安全对齐模型拒绝直说的有害请求，却回答嵌进角色或叙事里的同一请求。文言文被用来把语域和包装拆开。
Paper analysisRead analysis
DefensesarXiv 2610.09941Oct 7
OrthoPurify 用一步正交投影净化被后门污染的视觉语言模型
提出 OrthoPurify，用正交投影清除视觉语言模型适配器中的劫持方向
arXiv
2610.09941
Published
Oct 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
LLaVA-1.5-7B, Qwen3-VL-8B, LLaVA-1.5-13B and others5
- DefensesModel hardening
- AttacksPoisoning and backdoors
- ComponentFine-tuning and open weights
Abstract一次投影去掉劫持方向。
OrthoPurify 是部署前的 LVLM 后门净化方法，用一次正交投影去掉被劫持的权重更新方向。
Paper analysisRead analysis
DefensesarXiv 2610.10625Oct 7
研究揭示循环语言模型在不同循环深度下安全表现不一致
提出 SafeBridge，对齐循环语言模型不同循环深度的安全性
arXiv
2610.10625
Published
Oct 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Ouro-1.4B, Ouro-2.6B
- DefensesModel hardening
- AttacksJailbreaks
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
Analysis and theoryarXiv 2610.09004Oct 7
研究：去除有害信息不足以证明开源权重模型的抗篡改能力
论证发布时互信息不能认证开源权重抗微调恢复
arXiv
2610.09004
Published
Oct 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
EleutherAI/deep-ignorance-e2e-strong-filter, EleutherAI/deep-ignorance-unfiltered, Google BERT-Tiny and others6
- DefensesModel hardening
- AttacksModel tampering
- ComponentFine-tuning and open weights
Abstract作者称零信息仍可一步恢复，表观抗微调可来自参数化。
作者研究开源权重模型的篡改抵抗：发布时的互信息是否足以保证微调恢复很慢。
Paper analysisRead analysis
AttacksarXiv 2610.07723Oct 6
Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.
提出回答端后门，让模型自生成触发词以在干净有害请求下绕过拒答
arXiv
2610.07723
Published
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-2-7B-chat-hf, Mistral-7B-Instruct-v0.3, Gemma-7B-it and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract论文提出了多轮对话中回答端自生成触发词绕过安全拒绝的后门攻击，指出输入端防护存在盲区。
Paper analysisRead analysis
AttacksarXiv 2610.07654Oct 6
研究揭示策略蒸馏的安全后门风险
测量带后门教师经 OPD 向干净学生迁移潜伏后门
arXiv
2610.07654
Published
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen2.5-1.5B-Instruct, Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract作者称 OPD 可在压低无触发词有害率时迁入后门。
带后门的外部教师经 OPD，可在压低无触发词有害率的同时，把触发条件下的有害行为传给初始干净学生。。
Paper analysisRead analysis
InterpretabilityarXiv 2610.07518Oct 6
TRACE：仅凭 checkpoint 更新审计大语言模型有害目标
提出 TRACE，仅凭检查点更新审计有害合规微调目标
arXiv
2610.07518
Published
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3, Qwen3-8B and others6
- AttacksModel tampering
- ComponentFine-tuning and open weights
Abstract作者称有害合规 SFT 在检查点更新中留下可排序坐标，并据此做只读权重审计。
作者在检查点更新里寻找有害合规 SFT 的目标组成，并把读数做成不查询模型、不看未知训练数据的审计分 TRACE。
Paper analysisRead analysis
AttacksarXiv 2610.05793Oct 5
研究者训练出按多智能体拓扑触发的代码后门模型
提出拓扑条件后门，使代码模型在推断多智能体部署时植入漏洞
arXiv
2610.05793
Published
Oct 5
Layer
Training and data layer
Setting
coding agent
Evaluated models
Qwen2.5-7B-Instruct, Qwen2.5-Coder-7B-Instruct
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract论文证实了拓扑条件后门的可训练性与泛化性，展示了常规评测盲区，并提出差异化拓扑审计作为检测防御方向。
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
DefensesarXiv 2610.05401Oct 5
AVCE：面向扩散模型可验证概念擦除的审计感知遗忘框架
提出审计感知遗忘框架 AVCE，从文本与视觉通路擦除扩散模型概念
arXiv
2610.05401
Published
Oct 5
Layer
Training and data layer
Setting
Models and APIs
Attacker
White-box, Black-box
Evaluated models
Stable Diffusion XL (SDXL), Stable Diffusion v1.5 (SD v1.5), Flux 1.0
- DefensesModel hardening
- AttacksJailbreaks
- ComponentImage generation
AbstractAVCE 在审计锚点上改两条注意力通路。
AVCE 是面向扩散模型的概念擦除方法，要让擦除经得起绕过文本条件的潜空间审计，而不只是挡住对抗提示词。
Paper analysisRead analysis
DefensesarXiv 2610.07023Oct 4
SSRFT：以安全角色内化替代拒答模式的 LLM 安全对齐框架
提出 SSRFT，用角色监督内化安全原则以替代拒答式对齐
arXiv
2610.07023
Published
Oct 4
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen2.5-3B, Gemma2-2B, Llama3.1-8B and others6
- DefensesModel hardening
- AttacksJailbreaks
AbstractSSRFT 用角色监督替代拒答中心对齐。
SSRFT是一种用监督微调把预定义安全角色写进参数的安全对齐方法。作者称它是首个以安全角色内化本身为对齐目标的框架。
Paper analysisRead analysis
DefensesarXiv 2610.04467Oct 3
无需目标答案的潜在空间安全对齐：无监督对抗训练提升 LLM 越狱鲁棒性
提出 Target-free LAT，用无目标多方向潜干预做对抗安全对齐以抵御越狱
arXiv
2610.04467
Published
Oct 3
Layer
Training and data layer
Setting
Models and APIs
Attacker
White-box, Black-box
Evaluated models
Qwen2.5-7B-Instruct, Llama-3-8B-Instruct, Mistral-7B-Instruct-v0.2
- DefensesModel hardening
- AttacksJailbreaks
AbstractTarget-free LAT 用无目标多方向潜干预扩大行为覆盖，作者称能提高越狱鲁棒性并保住效用。
Target-free LAT 是一种不监督有害输出的潜空间对抗对齐。它要处理的问题是：现有 LAT 每步大多只造一种有害行为，对不上真实越狱里的直接遵从、角色扮演、编码和多语言等模式。
Paper analysisRead analysis
AttacksarXiv 2610.04128Oct 3
研究显示拆分学习中的梯度可提升客户端文本重建率
衡量分裂学习中梯度相对激活对客户文本重建的额外贡献
arXiv
2610.04128
Published
Oct 3
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
GPT-2 (openai-community/gpt2, 124M), Qwen3-0.6B
- AttacksExtraction and theft
Abstract激活已恢复大部分 token。
这篇工作测量 split learning 分裂点上的文本泄漏：激活单独能恢复多少，训练回传的梯度再增加多少，以及按 token 还是按整篇计分会不会改写结论。
Paper analysisRead analysis
DefensesarXiv 2610.03980Oct 3
FADE：面向视频扩散模型的帧感知多概念擦除框架
提出 FADE，对文生视频模型做帧感知多概念擦除
arXiv
2610.03980
Published
Oct 3
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Wan2.1-T2V-1.3B, Wan2.1-T2V-14B, CogVideoX-2B and others4
- DefensesModel hardening
- AttacksMalicious use
- ComponentImage generation
AbstractFADE 用闭式编辑、帧感知适配器和软路由，在单骨干上擦除多概念并压低逐帧残差。
FADE 是面向文生视频扩散 Transformer 的多概念遗忘方法，用来抑制指定物体、画风、裸体、暴力、仇恨和名人身份，并尽量保持其他生成。作者要处理两件事。与帧无关的抑制会让概念在少数帧重现，片段均值会掩盖这一失败。
Paper analysisRead analysis
AttacksarXiv 2610.01365Oct 1
ReGap：无需真实隐私数据即可通过微调重新提取模型隐私关联
提出 ReGap，用自生成伪监督微调恢复模型中的隐私关联
arXiv
2610.01365
Published
Oct 1
Layer
Training and data layer
Setting
Models and APIs
Attacker
White-box, Gray-box
Evaluated models
GPT-2 Small, GPT-2 Medium, GPT-2 Large and others6
- AttacksExtraction and theft
- ComponentFine-tuning and open weights
Abstract提出无真实私有监督的恢复攻击 ReGap，实验显示微调可通过自生成数据唤醒模型潜在隐私关联，突显后适应隐私风险。
Paper analysisRead analysis
DefensesarXiv 2610.00685Oct 1
研究者提出用零空间投影净化 LoRA 微调 LLM 的后门
用零空间投影净化 LoRA 微调模型后门并保留基座与下游能力
arXiv
2610.00685
Published
Oct 1
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
LLaMA2-7B-Chat, LLaMA2-13B-Chat, Qwen2-7B-Instruct and others6
- DefensesModel hardening
- AttacksPoisoning and backdoors
- ComponentFine-tuning and open weights
Paper analysisRead analysis
DefensesarXiv 2609.40286Oct 1
研究者提出 COVER：在语言预算下选择源语言实现跨语言遗忘
提出 COVER，在语言预算下选择源语言实现跨语言知识遗忘
arXiv
2609.40286
Published
Oct 1
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Tiny Aya Global, Qwen3-4B-Instruct-2507, Llama-3.2-3B-Instruct
- DefensesModel hardening
- AttacksExtraction and theft
AbstractCOVER 在语言预算下选源语言，以降低未监督语言上相对 oracle 的残余访问。
语言预算下的多语言遗忘：遗忘监督只放在 K 种源语言上，目标是降低其余语言对同一事实的残余访问，而不是把每种评测语言都译成监督数据。
Paper analysisRead analysis

AI Safety Daily

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