Cover Image

No Safe Dose: How Training Data Drives Unsafe Image Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Friedrich, Felix, Helff, Lukas, Hegde, Niharika, Schramowski, Patrick, Kersting, Kristian
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models
by: Helff, Lukas, et al.
Published: (2024)

How to Train your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions
by: Brack, Manuel, et al.
Published: (2025)

Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis
by: Struppek, Lukas, et al.
Published: (2022)

Does CLIP Know My Face?
by: Hintersdorf, Dominik, et al.
Published: (2022)

LEDITS++: Limitless Image Editing using Text-to-Image Models
by: Brack, Manuel, et al.
Published: (2023)

V-LoL: A Diagnostic Dataset for Visual Logical Learning
by: Helff, Lukas, et al.
Published: (2023)

DeiSAM: Segment Anything with Deictic Prompting
by: Shindo, Hikaru, et al.
Published: (2024)

Core Tokensets for Data-efficient Sequential Training of Transformers
by: Paul, Subarnaduti, et al.
Published: (2024)

Unsafe2Safe: Controllable Image Anonymization for Downstream Utility
by: Dinh, Mih, et al.
Published: (2026)

Disentangling Safe and Unsafe Corruptions via Anisotropy and Locality
by: Muthukumar, Ramchandran, et al.
Published: (2025)

Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
by: Struppek, Lukas, et al.
Published: (2023)

Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash
by: Struppek, Lukas, et al.
Published: (2021)

Finding DoRI: Discovery of Retained Images in Diffusion Models
by: Kowalczuk, Antoni, et al.
Published: (2025)

Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted Adaptation
by: Kim, Yongwoo, et al.
Published: (2026)

Defending Our Privacy With Backdoors
by: Hintersdorf, Dominik, et al.
Published: (2023)

SocialGrid: A Benchmark for Planning and Social Reasoning in Embodied Multi-Agent Systems
by: Shindo, Hikaru, et al.
Published: (2026)

A-BDD: Leveraging Data Augmentations for Safe Autonomous Driving in Adverse Weather and Lighting
by: Assion, Felix, et al.
Published: (2024)

SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification
by: Feuer, Benjamin, et al.
Published: (2024)

Boosting Object Representation Learning via Motion and Object Continuity
by: Delfosse, Quentin, et al.
Published: (2022)

ART: Adaptive Relation Tuning for Generalized Relation Prediction
by: Sudhakaran, Gopika, et al.
Published: (2025)

SafeAug: Safety-Critical Driving Data Augmentation from Naturalistic Datasets
by: Mo, Zhaobin, et al.
Published: (2025)

A Typology for Exploring the Mitigation of Shortcut Behavior
by: Friedrich, Felix, et al.
Published: (2022)

The Why, When, and How to Use Active Learning in Large-Data-Driven 3D Object Detection for Safe Autonomous Driving: An Empirical Exploration
by: Greer, Ross, et al.
Published: (2024)

The Influence of Faulty Labels in Data Sets on Human Pose Estimation
by: Schwarz, Arnold, et al.
Published: (2024)

Learning Differentiable Logic Programs for Abstract Visual Reasoning
by: Shindo, Hikaru, et al.
Published: (2023)

All Eyes on the Workflow: Automated and Efficient Event Discovery from Video Streams
by: Pegoraro, Marco, et al.
Published: (2026)

SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation
by: Yoon, Jaehong, et al.
Published: (2024)

OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments
by: Delfosse, Quentin, et al.
Published: (2023)

Efficient Denoising Method to Improve The Resolution of Satellite Images
by: Hegde, Jhanavi
Published: (2024)

Gating Syn-to-Real Knowledge for Pedestrian Crossing Prediction in Safe Driving
by: Bai, Jie, et al.
Published: (2024)

Image-based Outlier Synthesis With Training Data
by: Regmi, Sudarshan
Published: (2024)

Pix2Code: Learning to Compose Neural Visual Concepts as Programs
by: Wüst, Antonia, et al.
Published: (2024)

SLR: Automated Synthesis for Scalable Logical Reasoning
by: Helff, Lukas, et al.
Published: (2025)

Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You
by: Friedrich, Felix, et al.
Published: (2024)

Data-driven Crop Growth Simulation on Time-varying Generated Images using Multi-conditional Generative Adversarial Networks
by: Drees, Lukas, et al.
Published: (2023)

ICPR 2024 Competition on Safe Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather Conditions
by: Shaik, Furqan Ahmed, et al.
Published: (2024)

Beyond Memorization: Selective Learning for Copyright-Safe Diffusion Model Training
by: Kothandaraman, Divya, et al.
Published: (2025)

Attention Shift: Steering AI Away from Unsafe Content
by: Garg, Shivank, et al.
Published: (2024)

Beyond Overcorrection: Evaluating Diversity in T2I Models with DivBench
by: Friedrich, Felix, et al.
Published: (2025)

SAda-Net: A Self-Supervised Adaptive Stereo Estimation CNN For Remote Sensing Image Data
by: Hirner, Dominik, et al.
Published: (2024)