Image de couverture de livre

NDM: A Noise-driven Detection and Mitigation Framework against Implicit Sexual Intentions in Text-to-Image Generation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Yitong, Huang, Yao, Zhang, Ruochen, Chen, Huanran, Ruan, Shouwei, Duan, Ranjie, Wei, Xingxing
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

The Path to Reconciling Quality and Safety in Text-to-Image Generation: Dataset, Method, and Evaluation
par: Ruan, Shouwei, et autres
Publié: (2025)

Mitigating Overthinking in Large Reasoning Models via Manifold Steering
par: Huang, Yao, et autres
Publié: (2025)

Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
par: Huang, Yao, et autres
Publié: (2025)

MESA: Improving MoE Safety Alignment via Decentralized Expertise
par: Sun, Yitong, et autres
Publié: (2026)

When Lighting Deceives: Exposing Vision-Language Models' Illumination Vulnerability Through Illumination Transformation Attack
par: Liu, Hanqing, et autres
Publié: (2025)

Embodied Laser Attack:Leveraging Scene Priors to Achieve Agent-based Robust Non-contact Attacks
par: Sun, Yitong, et autres
Publié: (2023)

DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios
par: Huang, Yao, et autres
Publié: (2025)

Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
par: Zhao, Shiji, et autres
Publié: (2023)

Towards Transferable Targeted 3D Adversarial Attack in the Physical World
par: Huang, Yao, et autres
Publié: (2023)

Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models
par: Ruan, Shouwei, et autres
Publié: (2024)

Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency
par: Zhao, Shiji, et autres
Publié: (2025)

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
par: Kang, Caixin, et autres
Publié: (2023)

Real-world Adversarial Defense against Patch Attacks based on Diffusion Model
par: Wei, Xingxing, et autres
Publié: (2024)

MoAPT: Mixture of Adversarial Prompt Tuning for Vision-Language Models
par: Zhao, Shiji, et autres
Publié: (2025)

OODFace: Benchmarking Robustness of Face Recognition under Common Corruptions and Appearance Variations
par: Kang, Caixin, et autres
Publié: (2024)

Knowledge-Guided Adversarial Training for Infrared Object Detection via Thermal Radiation Modeling
par: Zhao, Shiji, et autres
Publié: (2026)

Towards Class-wise Fair Adversarial Training via Anti-Bias Soft Label Distillation
par: Zhao, Shiji, et autres
Publié: (2025)

Unveiling Trust in Multimodal Large Language Models: Evaluation, Analysis, and Mitigation
par: Zhang, Yichi, et autres
Publié: (2025)

AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?
par: Ruan, Shouwei, et autres
Publié: (2024)

Improving Safety Alignment via Balanced Direct Preference Optimization
par: Zhao, Shiji, et autres
Publié: (2026)

Mind over Space: Can Multimodal Large Language Models Mentally Navigate?
par: Zhu, Qihui, et autres
Publié: (2026)

Implicit Bias Injection Attacks against Text-to-Image Diffusion Models
par: Huang, Huayang, et autres
Publié: (2025)

SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
par: Li, Xinfeng, et autres
Publié: (2024)

From reactive to cognitive: brain-inspired spatial intelligence for embodied agents
par: Ruan, Shouwei, et autres
Publié: (2025)

HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models
par: Gao, Sensen, et autres
Publié: (2024)

An Amplitude-Encoding-Based Classical-Quantum Transfer Learning framework: Outperforming Classical Methods in Image Recognition
par: Hu, Shouwei, et autres
Publié: (2025)

VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack
par: Zhao, Shiji, et autres
Publié: (2025)

Noise-Mitigated Variational Quantum Eigensolver with Pre-training and Zero-Noise Extrapolation
par: Sun, Wanqi, et autres
Publié: (2025)

IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
par: Cao, Yue, et autres
Publié: (2023)

Evaluating Concept Filtering Defenses against Child Sexual Abuse Material Generation by Text-to-Image Models
par: Cretu, Ana-Maria, et autres
Publié: (2025)

Intention-driven Ego-to-Exo Video Generation
par: Luo, Hongchen, et autres
Publié: (2024)

TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning in Text-to-Image Models
par: Hsiao, Teng-Fang, et autres
Publié: (2025)

The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation
par: Wang, Ruoyu, et autres
Publié: (2024)

MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
par: Zhang, Yichi, et autres
Publié: (2024)

Pruning as a Cooperative Game: Surrogate-Assisted Layer Contribution Estimation for Large Language Models
par: Ding, Xuan, et autres
Publié: (2026)

Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation
par: Cheng, Ruoxi, et autres
Publié: (2026)

The broad‐spectrum antimicrobial peptide BMAP‐27B potentiates carbapenems against NDM‐producing pathogens in food animals
par: Xiaoxiao Zhang, et autres
Publié: (2025)

VEAT Quantifies Implicit Associations in Text-to-Video Generator Sora and Reveals Challenges in Bias Mitigation
par: Sun, Yongxu, et autres
Publié: (2026)

Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
par: Han, Hyeonggeun, et autres
Publié: (2025)

PGTuner: An Efficient Framework for Automatic and Transferable Configuration Tuning of Proximity Graphs
par: Duan, Hao, et autres
Publié: (2025)