TNC-Defense

TNC-Defense TNC-Defense provides research code for detecting and detoxifying backdoors in text-to-image diffusion models. The repository currently includes detection pipelines for Stable Diffusion v1.4, Stable Diffusion v1.5, Stable Diffusion XL, and Stable Diffusion 3 Medium, together with...

SemPurify: Semantics-Aware Data Purification for Black-Box Backdoor Defense

Backdoor attacks have emerged as a critical security threat in machine learning, where adversaries embed triggers within poisoned training samples to manipulate a model's predictions on targeted inputs while leaving its general behavior unaffected. This stealthy nature makes backdoor attacks...

CVE-2026-16073

A security vulnerability has been detected in AstrBotDevs AstrBot up to 4.25.2. Affected by this issue is the function Star.texttoimage/NetworkRenderStrategy.render of the file astrbot/core/star/base.py of the component T2I Feature. The manipulation leads to cross site scripting. The attack is...

CVE-2026-16073

A security vulnerability has been detected in AstrBotDevs AstrBot up to 4.25.2. Affected by this issue is the function Star.texttoimage/NetworkRenderStrategy.render of the file astrbot/core/star/base.py of the component T2I Feature. The manipulation leads to cross site scripting. The attack is...

CVE-2026-16073 AstrBotDevs AstrBot T2I Feature base.py NetworkRenderStrategy.render cross site scripting

A security vulnerability has been detected in AstrBotDevs AstrBot up to 4.25.2. Affected by this issue is the function Star.texttoimage/NetworkRenderStrategy.render of the file astrbot/core/star/base.py of the component T2I Feature. The manipulation leads to cross site scripting. The attack is...

EUVD-2026-45244

A security vulnerability has been detected in AstrBotDevs AstrBot up to 4.25.2. Affected by this issue is the function Star.texttoimage/NetworkRenderStrategy.render of the file astrbot/core/star/base.py of the component T2I Feature. The manipulation leads to cross site scripting. The attack is...

CVE-2026-16073 AstrBotDevs AstrBot T2I Feature base.py NetworkRenderStrategy.render cross site scripting

A security vulnerability has been detected in AstrBotDevs AstrBot up to 4.25.2. Affected by this issue is the function Star.texttoimage/NetworkRenderStrategy.render of the file astrbot/core/star/base.py of the component T2I Feature. The manipulation leads to cross site scripting. The attack is...

PixJail: Self-Evolving Paper-To-Pipeline Reproduction for Text-To-Image Jailbreak Evaluation

As Text-to-Image T2I jailbreak techniques evolve rapidly, existing benchmarks and reproduction workflows often struggle to keep pace. More importantly, T2I jailbreak evaluation is not a single prompt-level test, but a pipeline-level problem shaped by multiple stages, including prompt...

Customization under Fire: Plugin Poisoning in Text-To-Image Ecosystem

The prosperity of text-to-image T2I models has fostered a vibrant share-and-play ecosystem centered on Low-Rank Adaptation LoRA plugins, which allow users to customize and share model capabilities with ease. This democratization, however, comes with a hidden but severe security risk. Malicious...

Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-To-Image Diffusion Models

Text-to-image diffusion models are increasingly developed through open-source reuse and repeated downstream fine-tuning, where reused checkpoints are difficult to verify and thus more susceptible to hidden backdoor behaviors. In such ecosystems, a single pretrained model may be sequentially adapt...

MAI-2024-0049

The Heuristic Token Search HTS Attack represents a sophisticated method for circumventing safety protocols in text-to-image T2I models, enabling the generation of Not Safe For Work NSFW content. This attack involves systematically substituting tokens within a malicious prompt with semantically...

MAI-2024-0046

Commercial text-to-image T2I generative AI systems are susceptible to automated prompt injection attacks that can bypass their safety protocols and facilitate the generation of copyrighted content. Attackers can deploy an automated pipeline to craft prompts that accurately describe copyrighted...

OrchJail: Jailbreaking Tool-Calling Text-To-Image Agents by Orchestration-Guided Fuzzing

Tool-calling text-to-image T2I agents can plan and execute multi-step tool chains to accomplish complex generation and editing queries. However, this capability introduces a new safety attack surface: harmful outputs may arise from tool orchestration, where individually benign steps combine into...

DREAM: Scalable Red Teaming for Text-To-Image Generative Systems Via Distribution Modeling

Despite the integration of safety alignment and external filters, text-to-image T2I generative models are still susceptible to producing harmful content, such as sexual or violent imagery. This raises serious concerns about unintended exposure and potential misuse. Red teaming, which aims to...

PLA: Prompt Learning Attack against Text-To-Image Generative Models

Text-to-Image T2I models have gained widespread adoption across various applications. Despite the success, the potential misuse of T2I models poses significant risks of generating Not-Safe-For-Work NSFW content. To investigate the vulnerability of T2I models, this paper delves into adversarial...

On the Feasibility of Poisoning Text-To-Image AI Models Via Adversarial Mislabeling

Today's text-to-image generative models are trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models VLMs. This part of the training pipeline is critical for supplying the models with large volumes of high-quality image-captio...

GenBreak: Red Teaming Text-To-Image Generators Using Large Language Models

Text-to-image T2I models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety risks. While most platforms employ content moderation...

BadReward: Clean-Label Poisoning of Reward Models in Text-To-Image RLHF

Reinforcement Learning from Human Feedback RLHF is crucial for aligning text-to-image T2I models with human preferences. However, RLHF's feedback mechanism also opens new pathways for adversaries. This paper demonstrates the feasibility of hijacking T2I models by poisoning a small fraction of...

Fooling the Watchers: Breaking AIGC Detectors Via Semantic Prompt Attacks

The rise of text-to-image T2I models has enabled the synthesis of photorealistic human portraits, raising serious concerns about identity misuse and the robustness of AIGC detectors. In this work, we propose an automated adversarial prompt generation framework that leverages a grammar tree...

Red-Teaming Text-To-Image Systems by Rule-Based Preference Modeling

Text-to-image T2I models raise ethical and safety concerns due to their potential to generate inappropriate or harmful images. Evaluating these models' security through red-teaming is vital, yet white-box approaches are limited by their need for internal access, complicating their use with...