Image de couverture de livre

Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Yudong, Xie, Ruobing, Huang, Yiqing, Chen, Jiansheng, Sun, Xingwu, Kang, Zhanhui, Wang, Di, Wang, Yu
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
par: Zhang, Yudong, et autres
Publié: (2025)

DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
par: Zhang, Yudong, et autres
Publié: (2024)

PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions
par: Zhang, Yudong, et autres
Publié: (2024)

Enhancing Contrastive Learning Inspired by the Philosophy of "The Blind Men and the Elephant"
par: Zhang, Yudong, et autres
Publié: (2024)

The Security Threat of Compressed Projectors in Large Vision-Language Models
par: Zhang, Yudong, et autres
Publié: (2025)

MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs
par: Ding, Wei, et autres
Publié: (2026)

Exploring Forgetting in Large Language Model Pre-Training
par: Liao, Chonghua, et autres
Publié: (2024)

Multi-Grained Patch Training for Efficient LLM-based Recommendation
par: Liao, Jiayi, et autres
Publié: (2025)

Continuous Speech Tokenizer in Text To Speech
par: Li, Yixing, et autres
Publié: (2024)

The Climb Carves Wisdom Deeper Than the Summit: On the Noisy Rewards in Learning to Reason
par: Lv, Ang, et autres
Publié: (2025)

Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimization
par: Fu, Yuhan, et autres
Publié: (2024)

The Elephant in the Room: Rethinking the Usage of Pre-trained Language Model in Sequential Recommendation
par: Qu, Zekai, et autres
Publié: (2024)

Language Models "Grok" to Copy
par: Lv, Ang, et autres
Publié: (2024)

Fighting Fire with Fire: Adversarial Prompting to Generate a Misinformation Detection Dataset
par: Satapara, Shrey, et autres
Publié: (2024)

Fight Fire with Fire: Combating Adversarial Patch Attacks using Pattern-randomized Defensive Patches
par: Feng, Jianan, et autres
Publié: (2023)

PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset
par: Liu, Jiazhen, et autres
Publié: (2024)

Correction to ‘Fighting Fire With Fires: The Fire‐Fuel Feedback Effect in Canadian Forests’
Publié: (2026)

Lossless KV Cache Compression to 2%
par: Yang, Zhen, et autres
Publié: (2024)

More Expressive Attention with Negative Weights
par: Lv, Ang, et autres
Publié: (2024)

Autonomy-of-Experts Models
par: Lv, Ang, et autres
Publié: (2025)

Large Language Model Empowered Recommendation Meets All-domain Continual Pre-Training
par: Ma, Haokai, et autres
Publié: (2025)

Magnifier Prompt: Tackling Multimodal Hallucination via Extremely Simple Instructions
par: Fu, Yuhan, et autres
Publié: (2024)

Hybrid-Tower: Fine-grained Pseudo-query Interaction and Generation for Text-to-Video Retrieval
par: Lan, Bangxiang, et autres
Publié: (2025)

Fire-PPYOLOE: An Efficient Forest Fire Detector for Real-Time Wild Forest Fire Monitoring
par: Pei Yu, et autres
Publié: (2024)

RosePO: Aligning LLM-based Recommenders with Human Values
par: Liao, Jiayi, et autres
Publié: (2024)

Fight Fire with Fire: Defending Against Malicious RL Fine-Tuning via Reward Neutralization
par: Cao, Wenjun
Publié: (2025)

Fight Fire with Fire: How Much Can We Trust ChatGPT on Source Code-Related Tasks?
par: Yu, Xiao, et autres
Publié: (2024)

Negative Sampling in Recommendation: A Survey and Future Directions
par: Ma, Haokai, et autres
Publié: (2024)

Design Of A Fire-Fighting Robot For Various Applications
par: Krishna Pratap Singh Gaur, et autres
Publié: (2026)

Fighting Fire with Fire: Channel-Independent RF Fingerprinting via the Ratio of Linear to Logarithmic Differential Spectrum
par: Chen, Tianshu, et autres
Publié: (2025)

“Fight Fire with Fire”: Trace‐Water‐Induced Controllable Synthesis of Hydrophobic Armors to Stabilize Metal‐Organic Cage‐Based Crystalline Frameworks
par: Ze‐Jiu Diao, et autres
Publié: (2025)

TransMamba: A Sequence-Level Hybrid Transformer-Mamba Language Model
par: Li, Yixing, et autres
Publié: (2025)

Proximal Supervised Fine-Tuning
par: Zhu, Wenhong, et autres
Publié: (2025)

Scaling Laws for Floating Point Quantization Training
par: Sun, Xingwu, et autres
Publié: (2025)

Fire and Snow
par: DiPaolo, Marc
Publié: (2022)

Self-Distillation for Multi-Token Prediction
par: Zhao, Guoliang, et autres
Publié: (2026)

HMoE: Heterogeneous Mixture of Experts for Language Modeling
par: Wang, An, et autres
Publié: (2024)

ID-centric Pre-training for Recommendation
par: Wu, Yiqing, et autres
Publié: (2024)

DFGNN: Dual-frequency Graph Neural Network for Sign-aware Feedback
par: Wu, Yiqing, et autres
Publié: (2024)

Fire on Motion: Optimizing Video Pass-bands for Efficient Spiking Action Recognition
par: Ye, Shuhan, et autres
Publié: (2026)