Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 222 papers

Filter2

System component

MCP and skills43 Memory38 RAG22 Guardrails and judges33 Monitors11 Reasoning chains7 Permissions and sandboxing12 Fine-tuning and open weights30 Vision17 Audio4 Video4 Image generation10 Embeddings4 Multimodal33

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：Poisoning and backdoors Attack type：Detection evasion Clear all

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

AttacksarXiv 2610.13928Oct 10
AI models can provably hide arbitrary capabilities
Proposes digital lock compilation, encrypting executable networks into host weights to hide arbitrary capabilities
arXiv
2610.13928
Published
Oct 10
Layer
Model layer
Setting
Models and APIs
Evaluated models
Gemma 3 270M
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
AbstractThe authors use a digital lock to hide an executable capability and state that elicitation on the chemistry and parity tasks did not recover the capability.
The authors construct a class of backdoors that encrypt an executable network into the weights, used to discuss the limits of white-box elicitation audits under supply chain attacks.
Paper analysisRead analysis
Analysis and theoryarXiv 2610.13051Oct 9
Space beats statistics, retraining beats ranking: auditing training labels under label-only backdoors
Auditing training labels for label-only backdoors, comparing spaces and statistics, and judging by retraining
arXiv
2610.13051
Published
Oct 9
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
ResNet-32
- DefensesDetection and filtering
- AttacksPoisoning and backdoors
AbstractLabel inspection must be done in a space that has not been fitted to these labels, and judged by retrained models rather than detection scores.
The authors ask: can a defender without trusted data decide which training labels to keep, and how much clean data this destroys, and what the final model accuracy is.
Paper analysisRead analysis
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
AttacksarXiv 2610.12292Oct 9
The paper proposes an option channel attack: changing one option label can make an agent guardrail allow a prohibited operation
Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations
arXiv
2610.12292
Published
Oct 9
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
LAYA-TD, LAYA-EN, LAYA-ML and others5
- AttacksDetection evasion
- ComponentGuardrails and judges
AbstractThe authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.
Paper analysisRead analysis
AttacksarXiv 2610.11932Oct 8
A Fudan team measures the citation fragility of AI search: ordinary posts can enter citations and answer text
Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.
arXiv
2610.11932
Published
Oct 8
Layer
Application layer
Setting
LLM applications
Evaluated models
Grok, Doubao, ChatGPT and others10
- AttacksPoisoning and backdoors
- ComponentRAG
AbstractThe authors claim the paper quantifies vulnerabilities in AI search caused by citation preferences and low posting thresholds; tests show public web posts can penetrate AI citations, and they call for auditing the citation supply chain.
Paper analysisRead analysis
DefensesarXiv 2610.11848Oct 8
SemField: training-free semantic watermark
Proposes the semantic watermark SemField, which still identifies the attribution of generated text after paraphrasing and structural changes.
arXiv
2610.11848
Published
Oct 8
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama-3.2-1B, Qwen3-1.7B, OPT-1.3B
- DefensesWatermarking and provenance
- AttacksDetection evasion
AbstractTraining-independent document-level semantic watermark.
SemField is a zero-bit semantic watermark embedded by the provider at generation time and detected later with a key, used to identify the provider's own model text after paraphrasing and sentence-level structural changes.
Paper analysisRead analysis
AttacksarXiv 2610.10742Oct 8
BRANCH 方法绕过 6 套多扫描器护栏系统
提出 BRANCH 方法，用分支搜索绕过多扫描器护栏
arXiv
2610.10742
Published
Oct 8
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Meta Llama Guard 3 8B, Meta Llama Guard 7B, Meta Llama Guard 3 1B and others18
- AttacksDetection evasion
- TechniqueAutomated search
- ComponentGuardrails and judges
Paper analysisRead analysis
AttacksarXiv 2610.10000Oct 7
超越奖励压制：有界奖励热启动 Bandit 的近最优离线攻击
提出热启动 Bandit 的部署前有界离线注入攻击
arXiv
2610.10000
Published
Oct 7
Layer
Training and data layer
Setting
LLM applications
Evaluated models
UCB, Thompson Sampling, ϵ-greedy
- AttacksPoisoning and backdoors
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
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
DefensesarXiv 2610.09793Oct 7
用时序逻辑监控工具 Agent
提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链
arXiv
2610.09793
Published
Oct 7
Layer
Application layer
Setting
AI Agent
Attacker
Black-box
- DefensesMonitoring and auditing
- AttacksPrompt injection
- ComponentMonitors
Abstract形式化验证可有效识别多步攻击，但其有效性高度依赖轨迹的可信历史记录。
这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。
Paper analysisRead analysis
AttacksarXiv 2610.10612Oct 7
PyCache Trap 利用 Python 缓存替换绕过七款 Agent Skill 扫描器
提出 PyCache Trap，用字节码缓存替换绕过 Agent 技能扫描器
arXiv
2610.10612
Published
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
CISCO, HSS, AUDITOR and others8
- DefensesDetection and filtering
- AttacksDetection evasion
- TechniqueDefense-targeted
- ComponentMCP and skills
Abstract论文剖析智能体技能审查与执行脱节盲区，提出 PyCache Trap 攻击并构建基于可信复现的 EAV 防御。
这篇论文研究了智能体技能（Agent Skills）安全扫描中的“审查–执行脱节”问题，并提出了对应的攻击验证与防御方案。
Paper analysisRead analysis
AttacksarXiv 2610.09264Oct 7
研究者提出 PackHallu：经规则文件提示注入对编码 Agent 发起包幻觉攻击
提出 PackHallu，经规则文件提示注入诱导编码 Agent 换用攻击者指定包
arXiv
2610.09264
Published
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
Qwen2.5-Coder-7B, Qwen3-Coder-30B, Devstral-Small-2-24B and others19
- AttacksPrompt injection
- TechniqueAutomated search
AbstractPackHallu 诱导规则文件换包。
PackHallu 研究一种针对编程智能体规则文件的提示注入：让智能体在本应使用合法依赖时，改导入攻击者指定并控制的包。
Paper analysisRead analysis
DefensesarXiv 2610.08668Oct 7
SBW：面向 LLM 智能体的语义行为水印方法
提出 SBW，为 LLM Agent 轨迹做抗改写与伪造的语义行为水印
arXiv
2610.08668
Published
Oct 7
Layer
Application layer
Setting
AI Agent
Evaluated models
Qwen2.5-3B-Instruct, LLaMA-3.2-3B, Qwen2.5-7B and others5
- DefensesWatermarking and provenance
- AttacksDetection evasion
AbstractSBW 在语义簇上做溯源水印，改写检测高于精确符号，链式重放仍开放。
SBW 是免训练的智能体行为水印，把所有者标识放在离散动作选择上，而不是输出 token。
Paper analysisRead analysis
AttacksarXiv 2610.08331Oct 6
STCA：研究者提出针对自动驾驶视频 VLM 的时空一致性对抗攻击
提出 STCA，对驾驶视频 VLM 构造可迁移的时空对抗扰动
arXiv
2610.08331
Published
Oct 6
Layer
Prompt layer
Setting
Models and APIs
Attacker
No-box (offline transfer)
Evaluated models
Video-LLaVA-7B, Qwen2.5-VL-7B, Dolphins
- AttacksDetection evasion
- TechniqueGradient and representation optimization
- ComponentVideo
Paper analysisRead analysis
AttacksarXiv 2610.08098Oct 6
CORSA：面向技能路由器的技能注入攻击可跨路由器与 LLM 迁移
提出 CORSA，按任务簇优化技能注入的检索与执行
arXiv
2610.08098
Published
Oct 6
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.4, DeepSeek-V4-Pro, Qwen3.8-27B and others5
- AttacksPoisoning and backdoors
- TechniqueSelection manipulation
- ComponentMCP and skills
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.07939Oct 6
CCDF dataset: Grok Imagine, Veo 3.1, Sora 2 forge surveillance footage, ten deepfake detectors basically cannot recognize it
提出监控深伪基准 CCDF，在统一编码后评测检测器对伪造犯罪事故录像的识别
arXiv
2610.07939
Published
Oct 6
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
C2P-CLIP, ForgeLens, D3-Im and others10
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
Abstract提出消除格式捷径的监控深度伪造基准 CCDF，揭示现有检测器难以识别商用生成视频。
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
DefensesarXiv 2610.07657Oct 6
DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降
实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击
arXiv
2610.07657
Published
Oct 6
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
- DefensesPermissions and approval
- AttacksPrompt injection
- ComponentGuardrails and judges
AbstractDEFER 把确定性检查放在 judge 之前。
DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。
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

AI Safety Daily

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

All papers

Attack type

Attack technique

Model risks

Defense type

Impact

System type

Attacker access

Attack surface / entry point

Layer

System component

AI models can provably hide arbitrary capabilities

Space beats statistics, retraining beats ranking: auditing training labels under label-only backdoors

Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.

The paper proposes an option channel attack: changing one option label can make an agent guardrail allow a prohibited operation

A Fudan team measures the citation fragility of AI search: ordinary posts can enter citations and answer text

SemField: training-free semantic watermark

BRANCH 方法绕过 6 套多扫描器护栏系统

超越奖励压制：有界奖励热启动 Bandit 的近最优离线攻击

OrthoPurify 用一步正交投影净化被后门污染的视觉语言模型

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

用时序逻辑监控工具 Agent

PyCache Trap 利用 Python 缓存替换绕过七款 Agent Skill 扫描器

研究者提出 PackHallu：经规则文件提示注入对编码 Agent 发起包幻觉攻击

SBW：面向 LLM 智能体的语义行为水印方法

STCA：研究者提出针对自动驾驶视频 VLM 的时空一致性对抗攻击

CORSA：面向技能路由器的技能注入攻击可跨路由器与 LLM 迁移

CCDF dataset: Grok Imagine, Veo 3.1, Sora 2 forge surveillance footage, ten deepfake detectors basically cannot recognize it

Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.

DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

研究揭示策略蒸馏的安全后门风险