No article text was recorded for this version.
harmful content generation
Version 1 of 154 papers74 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Systematic Analysis of the Unintentional CSAM-Generation-Potential of Text-to-Image Models
- Blog: Position: Towards Implicit Prompt For Text-To-Image Models
- Blog: PurifyGen: A Risk-Discrimination and Semantic-Purification Model for Safe Text-to-Image Generation
- Blog: Typology of Risks of Generative Text-to-Image Models
- Blog: SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
- Blog: HateImgPrompts: Mitigating Generation of Images Spreading Hate Speech
- Blog: Lexically-constrained automated prompt augmentation: A case study using adversarial T2I data
- Blog: AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts
- Blog: On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts
- Blog: ACE: Concept Editing in Diffusion Models without Performance Degradation
- Blog: Adversarial Nibbler: An Open Red-Teaming Method for Identifying Diverse Harms in Text-to-Image Generation
- Blog: SneakyPrompt: Jailbreaking Text-to-image Generative Models
- Blog: A Single Neuron Works: Precise Concept Erasure in Text-to-Image Diffusion Models
- Blog: Beautiful Images, Toxic Words: Understanding and Addressing Offensive Text in Generated Images
- Blog: DREAM: Scalable Red Teaming for Text-to-Image Generative Systems via Distribution Modeling
- Blog: TWIGMA: A dataset of AI-Generated Images with Metadata From Twitter
- Blog: Exploring the Use of Abusive Generative AI Models on Civitai
- Blog: ARTIST: A Transformer-based Chinese Text-to-Image Synthesizer Digesting Linguistic and World Knowledge
- Blog: M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models
- Blog: Exploring the Boundaries of Content Moderation in Text-to-Image Generation
- Blog: OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure
- Blog: DiffExplainer: Towards cross-modal global explanations with diffusion models
- Blog: SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation
- Blog: PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
- Blog: TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models
- Blog: RusCode: Russian Cultural Code Benchmark for Text-to-Image Generation
- Blog: On Guardrail Models’ Robustness to Mutations and Adversarial Attacks
- Blog: Ensuring Visual Commonsense Morality for Text-to-Image Generation
- Blog: PLA: Prompt Learning Attack against Text-to-Image Generative Models
- Blog: Inference-Only Prompt Projection for Safe Text-to-Image Generation with TV Guarantees
- Blog: Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Models
- Blog: Civiverse: A Dataset for Analyzing User Engagement with Open-Source Text-to-Image Models
- Blog: Antelope: Potent and Concealed Jailbreak Attack Strategy
- Blog: Pruning for Robust Concept Erasing in Diffusion Models
- Blog: TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis
- Blog: Unlearning in Diffusion models under Data Constraints: A Variational Inference Approach
- Blog: Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization
- Blog: SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
- Blog: Hiding and Recovering Knowledge in Text-to-Image Diffusion Models via Learnable Prompts
- Blog: Continual Learning for Forgetting in Deep Generative Models
- Blog: Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
- Blog: GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
- Blog: Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
- Blog: Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs
- Blog: SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing
- Blog: AI Tools Can Generate Misculture Visuals! Detecting Prompts Generating Misculture Visuals For Prevention
- Blog: Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal Gestures
- Blog: Multi-concept Model Immunization through Differentiable Model Merging
- Blog: USD: NSFW Content Detection for Text-to-Image Models via Scene Graph
- Blog: When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
- Blog: T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model
- Blog: Rapid Diffusion: Building Domain-Specific Text-to-Image Synthesizers with Fast Inference Speed
- Blog: ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning
- Blog: Universally Unfiltered and Unseen: Input-Agnostic Multimodal Jailbreaks against Text-to-Image Model Safeguards
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_harmful_content_generation_a156b7e9,
title = {harmful content generation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/harmful-content-generation/rdr_a156b7e995c64abbbe5b9ec30452a09c},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_harmful_content_generation_a156b7e9_v1,
title = {harmful content generation},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/harmful-content-generation/rdr_a156b7e995c64abbbe5b9ec30452a09c/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}