AttacksarXiv 2610.09708
研究者提出利用祖先 VLM 的黑盒对抗补丁攻击，可降低 VLA 任务成功率
提出利用祖先 VLM 优化对抗补丁，使已部署 VLA 任务失败
- arXiv
- 2610.09708
- Published
- Layer
- Prompt layer
- Evaluated models
- OpenVLA, UniVLA, π0.5
- TechniqueGradient and representation optimization
- ComponentVision
All papers
Filter3
Attack type
Attack technique
Defense type
Impact
System type
Attacker access
Attack surface / entry point
User input59Web pages and interfaces16Documents and messages28Tool responses17Tool and skill descriptions5Code repositories and dependencies6Retrieval corpus28Memory writes8Inter-agent messages10Images, audio and video51Training data33Weights and gradients15Distribution channels16Inference services and hardware7
Layer
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Another 233papers do not have category tags yet and are not included in filtered results.
- AttacksarXiv 2610.09264
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
- 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。
- AttacksarXiv 2610.09027
P-VMI：对抗图像经 KV cache 持续影响多轮对话
提出持久视觉记忆注入，使对抗图像经缓存在触发时操控输出
- arXiv
- 2610.09027
- Published
- Layer
- Infrastructure layer
- Setting
- Models and APIs
- Evaluated models
- Qwen3-8B, Qwen3-VL-8B-Instruct, Gemma-4-12B
- AttacksPrompt injection
- TechniqueDormant triggers
- ComponentVision
Abstract论文提出 P-VMI，证实对抗输入被掩蔽后仍可经 KV 缓存持久控制模型，强调了保留状态的安全风险。
- AttacksarXiv 2610.08331
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
- 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
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
- 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。
- AttacksarXiv 2610.07323
ATLAS：用自适应信任域与主动学习搜索潜在对抗样本集
提出 ATLAS 用水平集估计恢复黑盒分类器的对抗输入集合
- arXiv
- 2610.07323
- Published
- Layer
- Prompt layer
- Setting
- Models and APIs
- Attacker
- Black-box
- Evaluated models
- LeNet5, ResNet50 (CIFAR-10 standard), ResNet50 (ImageNet standard) and others5
- AttacksDetection evasion
- TechniqueAutomated search
AbstractATLAS 用主动水平集估计构造黑盒对抗集，作者称其集合比单点攻击更具代表性。
ATLAS 是一个查询式 black-box 框架，用来构造诱发失败的对抗输入集合，供鲁棒性审计使用。
BabelFake：面向多语言音视频 DeepFake 检测的基准数据集
构建多语言音视频 DeepFake 基准 BabelFake 并评测检测器
- arXiv
- 2610.06339
- Published
- Layer
- Model layer
- Setting
- Models and APIs
- Evaluated models
- SpeechForensics, AVH-Align, (B)RAVEn
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentAudio
AbstractBabelFake 为五语同意采集基准。
BabelFake 是经同意与 IRB 批准采集的多语音视频 DeepFake 检测基准，用来把视觉操纵和语音合成拆开比较。
- DefensesarXiv 2610.05870
MBZUAI 提出可校准的真实图像认证方法
提出校准重合成方法，以生成器反演保真度认证真实图像并防御对抗扰动
- arXiv
- 2610.05870
- Published
- Layer
- Application layer
- Setting
- LLM applications
- Attacker
- White-box
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentImage generation
Abstract论文提出基于反演保真度与阈值校准的健全认证框架，在对抗扰动下维持错误率界限，并指出真实内容可认证性随生成器演进而萎缩。
- AttacksarXiv 2610.05139
研究揭示代码注释中的上下文注入攻击面
提出推理时上下文注入，用代码注释诱导补全生成含弱点的代码
- arXiv
- 2610.05139
- Published
- Layer
- Prompt layer
- Setting
- coding agent
- Evaluated models
- StarCoderBase, DeepSeek-Coder-base, Qwen2.5-base and others10
- AttacksPrompt injection
- AttacksarXiv 2610.06977
IAU-FOA：面向闭源多模态大模型的可迁移对抗攻击方法
提出 IAU-FOA，构造可迁移图像扰动以诱导多模态模型输出目标语义
- arXiv
- 2610.06977
- Published
- Layer
- Prompt layer
- Setting
- Models and APIs
- Evaluated models
- Qwen2.5-VL-7B, Qwen2.5-VL-72B, InternVL3-14B and others17
- TechniqueGradient and representation optimization
- ComponentVision
- DefensesarXiv 2610.04235
Thrive：面向自回归 TTS 的抗重建攻击多比特语音水印框架
提出 THRIVE，为自回归 TTS 嵌入抗重建的多比特语音水印
- arXiv
- 2610.04235
- Published
- Layer
- Model layer
- Setting
- Models and APIs
- Evaluated models
- Qwen3-TTS (0.6B), Dots.tts (2B)
- DefensesWatermarking and provenance
- AttacksDetection evasion
- ComponentAudio
- DefensesarXiv 2610.03498
检测与抑制：针对 VLA 模型对抗补丁的机制可解释性防御
提出条件特征抑制防御，检出对抗补丁后抑制 VLA 内部特征
- arXiv
- 2610.03498
- Published
- Layer
- Model layer
- Evaluated models
- π0.5, SmolVLA
- DefensesInference-time intervention
- ComponentVision
Abstract条件抑制与 patch 相关的 SAE 特征，间歇攻击下可提高 SR，持续攻击下则不能。
- AttacksarXiv 2610.03166
LiBRA：通过双向隐空间优化实现检测感知的图像水印去除
提出 LiBRA，在潜空间双向优化以规避图像水印双侧检测
- arXiv
- 2610.03166
- Published
- Layer
- Model layer
- Setting
- Models and APIs
- Attacker
- White-box
- Evaluated models
- Stable Signature, YU1, HiDDeN and others4
- AttacksDetection evasion
- TechniqueDefense-targeted
AbstractLiBRA 用双向潜空间优化规避双侧水印检测，并提高相对反转基线的保真。
- DefensesarXiv 2610.00780
TAILOR：面向图像水印的组合方案定制框架
提出 TAILOR，按请求组合图像水印以满足抗攻击与画质延迟规格
- arXiv
- 2610.00780
- Published
- Layer
- Model layer
- Setting
- Models and APIs
- DefensesWatermarking and provenance
- AttacksDetection evasion
- ComponentImage generation
DIBench：面向移动 GUI 智能体多候选选择决策完整性的安全基准
用 DIBench 评测移动 GUI 智能体被 UI 注入后的决策完整性
- arXiv
- 2610.06898
- Published
- Layer
- Application layer
- Setting
- Browser and computer use
- Evaluated models
- Qwen2.5-VL(32B), Qwen3-VL(32B), GUI-Owl(32B) and others7
- AttacksPrompt injection
- ComponentVision
Abstract论文提出移动智能体决策完整性基准 DIBench，发现欺诈 UI 注入诱导目标选择并推高完成率，通用防御收益不稳定。
- DefensesarXiv 2609.34744
现代图像后置水印信道的优化与安全：SNW 方案
提出带密钥的 SNW，抵御事后图像水印的身份伪造
- arXiv
- 2609.34744
- Published
- Layer
- Model layer
- Setting
- Models and APIs
- Evaluated models
- SNW
- DefensesWatermarking and provenance
- AttacksDetection evasion
- ComponentImage generation
AbstractSNW 用密钥与满秩各向同性投影提高事后水印的 Shannon 容量，并对 PCA 完全安全。
Gesny 与 Giboulot 针对生成内容追溯所依赖的多比特事后图像水印，批评端到端 DNN 方案既无容量理论、又无密钥。
- DefensesarXiv 2609.31282
基于区块链的 Agentic AI 框架：面向安全软件供应链的资源优化与能耗感知
提出 AttestChain，将供应链安全智能体报告签名上链并据此控制发布
- arXiv
- 2609.31282
- Published
- Layer
- Application layer
- Setting
- Multi-agent systems
- Evaluated models
- GPT-class LLM
- DefensesWatermarking and provenance
- ComponentPermissions and sandboxing
AbstractAttestChain 将智能体报告与链上发布门控结合，现有证据来自受控合成构建的总体结果。
AttestChain 是一个把 LLM 安全检查、智能体身份验证和许可链发布策略连接起来的软件供应链防御框架。。
- DefensesarXiv 2609.28239
ODPure：通过集成破坏共识实现目标检测后门净化
提出 ODPure，在输入阶段用腐蚀重建与共识净化目标检测后门
- arXiv
- 2609.28239
- Published
- Layer
- Prompt layer
- Setting
- Models and APIs
- Evaluated models
- YOLOv5, Faster R-CNN
- AttacksPoisoning and backdoors
- ComponentVision
- DefensesarXiv 2609.27378
PALS：面向全双工语音对话模型对抗鲁棒性的心理声学对齐潜空间平滑
提出 PALS，用潜空间平滑防御全双工语音对话的对抗扰动
- arXiv
- 2609.27378
- Published
- Layer
- Model layer
- Setting
- Models and APIs
- Attacker
- White-box
- Evaluated models
- Moshi-style agent
- DefensesModel hardening
- AttacksJailbreaks
- ComponentAudio
- DefensesarXiv 2609.23596
StyleAT：用对抗训练防御人脸识别的语义攻击
提出 BoundStyle 与 StyleAT，对抗训练防御人脸识别语义攻击
- arXiv
- 2609.23596
- Published
- Setting
- Models and APIs
- Evaluated models
- MobileFaceNet (MobileFace), ResNet (ResNet-152, IR-SE), RepVGG and others7
- DefensesModel hardening
- AttacksDetection evasion
AbstractBoundStyle 用 StyleGAN3 有界潜编辑快速攻击 FR。
StyleAT 用可调的 StyleGAN3 潜空间攻击 BoundStyle 对人脸识别做对抗训练，以抵抗一般语义编辑，并在评测中面对训练时未见的 DiffPrivate。