Copertina

Your Agent is More Brittle Than You Think: Uncovering Indirect Injection Vulnerabilities in Agentic LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zhu, Wenhui, Dong, Xuanzhao, Chen, Xiwen, Cai, Rui, Qiu, Peijie, Wang, Zhipeng, Frunza, Oana, Tang, Shao, Gu, Jindong, Wang, Yalin
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understanding
di: Dong, Xuanzhao, et al.
Pubblicazione: (2025)

Talk Before You Retrieve: Agent-Led Discussions for Better RAG in Medical QA
di: Dong, Xuanzhao, et al.
Pubblicazione: (2025)

PDL: Regularizing Multiple Instance Learning with Progressive Dropout Layers
di: Zhu, Wenhui, et al.
Pubblicazione: (2023)

STA-Unet: Rethink the semantic redundant for Medical Imaging Segmentation
di: Vasa, Vamsi Krishna, et al.
Pubblicazione: (2024)

Mags-RL: Wearing Multimodal LLMs a Magnifying Glass via Agentic Reinforcement Learning For Complex Scene Reasoning
di: Dong, Xuanzhao, et al.
Pubblicazione: (2026)

EyeBench: A Call for More Rigorous Evaluation of Retinal Image Enhancement
di: Zhu, Wenhui, et al.
Pubblicazione: (2025)

DRA-GRPO: Your GRPO Needs to Know Diverse Reasoning Paths for Mathematical Reasoning
di: Chen, Xiwen, et al.
Pubblicazione: (2025)

EVTP-IVS: Effective Visual Token Pruning For Unifying Instruction Visual Segmentation In Multi-Modal Large Language Models
di: Zhu, Wenhui, et al.
Pubblicazione: (2025)

nnMobileNet: Rethinking CNN for Retinopathy Research
di: Zhu, Wenhui, et al.
Pubblicazione: (2023)

OTPrune: Distribution-Aligned Visual Token Pruning via Optimal Transport
di: Chen, Xiwen, et al.
Pubblicazione: (2026)

Bridging Restoration and Diagnosis: A Comprehensive Benchmark for Retinal Fundus Enhancement
di: Dong, Xuanzhao, et al.
Pubblicazione: (2026)

VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement
di: Dong, Xuanzhao, et al.
Pubblicazione: (2025)

Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
di: Zhu, Wenhui, et al.
Pubblicazione: (2025)

RetinalGPT: A Retinal Clinical Preference Conversational Assistant Powered by Large Vision-Language Models
di: Zhu, Wenhui, et al.
Pubblicazione: (2025)

EViT-Unet: U-Net Like Efficient Vision Transformer for Medical Image Segmentation on Mobile and Edge Devices
di: Li, Xin, et al.
Pubblicazione: (2024)

SODA: Semi On-Policy Black-Box Distillation for Large Language Models
di: Chen, Xiwen, et al.
Pubblicazione: (2026)

DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification
di: Zhu, Wenhui, et al.
Pubblicazione: (2024)

AHA: Aligning Large Audio-Language Models for Reasoning Hallucinations via Counterfactual Hard Negatives
di: Chen, Yanxi, et al.
Pubblicazione: (2025)

SGW-GAN: Sliced Gromov-Wasserstein Guided GANs for Retinal Fundus Image Enhancement
di: Xiong, Yujian, et al.
Pubblicazione: (2026)

Many-MobileNet: Multi-Model Augmentation for Robust Retinal Disease Classification
di: Wang, Hao, et al.
Pubblicazione: (2024)

A BERT-Style Self-Supervised Learning CNN for Disease Identification from Retinal Images
di: Li, Xin, et al.
Pubblicazione: (2025)

Context-Aware Optimal Transport Learning for Retinal Fundus Image Enhancement
di: Vasa, Vamsi Krishna, et al.
Pubblicazione: (2024)

CUNSB-RFIE: Context-aware Unpaired Neural Schrödinger Bridge in Retinal Fundus Image Enhancement
di: Dong, Xuanzhao, et al.
Pubblicazione: (2024)

Cracking Instance Jigsaw Puzzles: An Alternative to Multiple Instance Learning for Whole Slide Image Analysis
di: Chen, Xiwen, et al.
Pubblicazione: (2025)

nnMobileNet++: Towards Efficient Hybrid Networks for Retinal Image Analysis
di: Li, Xin, et al.
Pubblicazione: (2025)

SelfReg-UNet: Self-Regularized UNet for Medical Image Segmentation
di: Zhu, Wenhui, et al.
Pubblicazione: (2024)

How Effective Can Dropout Be in Multiple Instance Learning ?
di: Zhu, Wenhui, et al.
Pubblicazione: (2025)

EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent
di: Wang, Hao, et al.
Pubblicazione: (2026)

Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
di: Hammoud, Hasan Abed Al Kader, et al.
Pubblicazione: (2025)

AriadneMem: Threading the Maze of Lifelong Memory for LLM Agents
di: Zhu, Wenhui, et al.
Pubblicazione: (2026)

Imaging Signal Recovery Using Neural Network Priors Under Uncertain Forward Model Parameters
di: Chen, Xiwen, et al.
Pubblicazione: (2024)

TimeMIL: Advancing Multivariate Time Series Classification via a Time-aware Multiple Instance Learning
di: Chen, Xiwen, et al.
Pubblicazione: (2024)

Sequence Complementor: Complementing Transformers For Time Series Forecasting with Learnable Sequences
di: Chen, Xiwen, et al.
Pubblicazione: (2025)

Your Embedding Model is SMARTer Than You Think
di: Zhang, Jianrui, et al.
Pubblicazione: (2026)

TPOT: Topology Preserving Optimal Transport in Retinal Fundus Image Enhancement
di: Dong, Xuanzhao, et al.
Pubblicazione: (2024)

Intermediate Outputs Are More Sensitive Than You Think
di: Huang, Tao, et al.
Pubblicazione: (2024)

RBAD: A Dataset and Benchmark for Retinal Vessels Branching Angle Detection
di: Wang, Hao, et al.
Pubblicazione: (2024)

SC-MIL: Sparsely Coded Multiple Instance Learning for Whole Slide Image Classification
di: Qiu, Peijie, et al.
Pubblicazione: (2023)

Model Checking for Reinforcement Learning in Autonomous Driving: One Can Do More Than You Think!
di: Gu, Rong
Pubblicazione: (2024)

OphIn-500K: Curating Web-Scale Visual Instructions for Scaling Ophthalmic Multimodal Large Language Models
di: Dong, Xuanzhao, et al.
Pubblicazione: (2026)