Related papers: Conditioned Activation Transport for T2I Safety St…

Text-to-Image (T2I) diffusion models enable high quality open ended synthesis, but practical use requires suppressing unsafe generations while preserving behavior on benign prompts. We study this tension relative to the frozen generator,…

As foundation models grow in capability, the ability to efficiently and reliably control their behavior becomes critical. Fine-tuning these models can be costly, and while prompting can be practical for controllability, it remains fragile…

Activation steering controls language model behavior by adding directions to internal representations at inference time, but standard residual-stream steering can fail in stateful dialogue. We identify KV-cache contamination as a key…

Driving safety is a top priority for autonomous vehicles. Orthogonal to prior work handling accident-prone traffic events by algorithm designs at the policy level, we investigate a Closed-loop Adversarial Training (CAT) framework for safe…

Malicious or manipulated prompts are known to exploit text-to-image models to generate unsafe images. Existing studies, however, focus on the passive exploitation of such harmful capabilities. In this paper, we investigate the proactive…

Text-to-Image (T2I) models have shown great performance in generating images based on textual prompts. However, these models are vulnerable to unsafe input to generate unsafe content like sexual, harassment and illegal-activity images.…

Text-to-image (T2I) models can generate not-safe-for-work (NSFW) content, motivating multi-stage safety pipelines with both text and image filters. Newer LLM-based filters detect latent intent beyond keywords, making token-level…

Recent text-to-image (T2I) models have had great success, and many benchmarks have been proposed to evaluate their performance and safety. However, they only consider explicit prompts while neglecting implicit prompts (hint at a target…

Text-to-image (T2I) generative models have achieved remarkable visual fidelity, yet remain vulnerable to generating unsafe content. Existing safety defenses typically intervene internally within the generative model, but suffer from severe…

Text-to-image (T2I) models have raised increasing safety concerns due to their capacity to generate NSFW and other banned objects. To mitigate these risks, safety filters and concept removal techniques have been introduced to block…

Standard transport protocols like TCP operate as a blind, FIFO conveyor belt for data, a model that is increasingly suboptimal for latency-sensitive and interactive applications. This paper challenges this model by introducing CATS…

Text-to-image (T2I) models have demonstrated remarkable generative capabilities but remain vulnerable to producing not-safe-for-work (NSFW) content, such as violent or explicit imagery. While recent moderation efforts have introduced soft…

Text-to-Image (T2I) diffusion models have demonstrated significant advancements in generating high-quality images, while raising potential safety concerns regarding harmful content generation. Safety-guidance-based methods have been…

Optimization-based jailbreaks typically adopt the Toxic-Continuation setting in large vision-language models (LVLMs), following the standard next-token prediction objective. In this setting, an adversarial image is optimized to make the…

Text-to-Image(T2I) models have achieved remarkable success in image generation and editing, yet these models still have many potential issues, particularly in generating inappropriate or Not-Safe-For-Work(NSFW) content. Strengthening…

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…

The key innovation of our analytical method, CaRT, lies in establishing a new hierarchical, distributed architecture to guarantee the safety and robustness of a given learning-based motion planning policy. First, in a nominal setting, the…

Text-to-image (T2I) diffusion models have drawn attention for their ability to generate high-quality images with precise text alignment. However, these models can also be misused to produce inappropriate content. Existing safety measures,…

Inference-time intervention (ITI) has emerged as a promising method for steering large language model (LLM) behavior in a particular direction (e.g., improving helpfulness) by intervening on token representations without costly updates to…

Using risky text prompts, such as pornography and violent prompts, to test the safety of text-to-image (T2I) models is a critical task. However, existing risky prompt datasets are limited in three key areas: 1) limited risky categories, 2)…