相关论文: Conditioned Activation Transport for T2I Safety St…
The rapid evolution of text-to-image (T2I) models has enabled high-fidelity visual synthesis on a global scale. However, these advancements have introduced significant security risks, particularly regarding the generation of harmful…
Image-to-Video (I2V) generation models, which condition video generation on reference images, have shown emerging visual instruction-following capability, allowing certain visual cues in reference images to act as implicit control signals…
Recent text-to-image (T2I) models have made remarkable progress in generating visually realistic and semantically coherent images. However, they still suffer from randomness and inconsistency with the given prompts, particularly when…
Although progress has been made for text-to-image synthesis, previous methods fall short of generalizing to unseen or underrepresented attribute compositions in the input text. Lacking compositionality could have severe implications for…
Behavior-related research areas such as motion prediction/planning, representation/imitation learning, behavior modeling/generation, and algorithm testing, require support from high-quality motion datasets containing interactive driving…
Robust classification methods predominantly concentrate on algorithms that address a specific threat model, resulting in ineffective defenses against other threat models. Real-world applications are exposed to this vulnerability, as…
Most research in the area of intrusion detection requires datasets to develop, evaluate or compare systems in one way or another. In this field, however, finding suitable datasets is a challenge on to itself. Most publicly available…
Autonomous cars can reduce road traffic accidents and provide a safer mode of transport. However, key technical challenges, such as safe navigation in complex urban environments, need to be addressed before deploying these vehicles on the…
The growing use of generative models in daily life calls for efficient mechanisms to control their generation, to e.g., produce safe content or provide users with tools to explore style changes. Ideally, such mechanisms should require low…
Text-to-Video (T2V) models are capable of synthesizing high-quality, temporally coherent dynamic video content, but the diverse generation also inherently introduces critical safety challenges. Existing safety evaluation methods,which focus…
ControlNet has enabled detailed spatial control in text-to-image diffusion models by incorporating additional visual conditions such as depth or edge maps. However, its effectiveness heavily depends on the availability of visual conditions…
One of the key applications envisioned for C-V2I (Cellular Vehicle-to-Infrastructure) networks pertains to safety on the road. Thanks to the exchange of Cooperative Awareness Messages (CAMs), vehicles and other road users (e.g.,…
In recent years, text-to-image (T2I) generation models have made significant progress in generating high-quality images that align with text descriptions. However, these models also face the risk of unsafe generation, potentially producing…
Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two core capabilities: \textbf{\textit{composition}} and…
Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and formalize the inscriptive jailbreak, where an adversary coerces a T2I system into generating…
Content safety is a fundamental challenge for text-to-image (T2I) models, yet prevailing methods enforce a debilitating trade-off between safety and generation quality. We argue that mitigating this trade-off hinges on addressing systemic…
Cooperative Intelligent Transportation Systems (C-ITS) constitute technologies which enable vehicles to communicate with each other and with road infrastructure. Verification or testing is required for C-ITS applications, in order to assess…
Multi-conflict traffic is ubiquitous. Connected Automated Vehicles (CAVs) offer unprecedented opportunities to enhance safety, reduce emissions, and increase throughput through precise coordination and automation. However, existing CAV…
Controlling the behavior of text-to-image generative models is critical for safe and practical deployment. Existing safety approaches typically rely on model fine-tuning or curated datasets, which can degrade generation quality or limit…
Agentic AI represents a paradigm shift in enhancing the capabilities of generative AI models. While these systems demonstrate immense potential and power, current evaluation techniques primarily focus on assessing their efficacy in…