Poisoning attacks pose significant challenges to the robustness of diffusion models (DMs). In this paper, we systematically analyze when and where poisoning attacks textual inversion (TI), a widely used personalization technique for DMs. W e first introduce Semantic Sensitivity Maps, a novel method for visualizing the influence of poisoning on text embeddings. Second, we identify and experimentally verify that DMs exhibit non-uniform learning behavior across timesteps, focusing on lower-noise samples. Poisoning attacks inherit this bias and inject adversarial signals predominantly at lower timesteps. Lastly, we observe that adversarial signals distract learning away from relevant concept regions within training data, corrupting the TI process. Based on these insights, we propose Safe-Zone Training (SZT), a novel defense mechanism comprised of 3 key components: (1) JPEG compression to weaken high-frequency poison signals, (2) restriction to high timesteps during TI training to avoid adversarial signals at lower timesteps, and (3) loss masking to constrain learning to relevant regions. Extensive experiments across multiple poisoning methods demonstrate that SZT greatly enhances the robustness of TI against all poisoning attacks, improving generative quality beyond prior published defenses.

The (generative) artificial intelligence (AI) era has profoundly reshaped the meaning and value of data. No longer confined to static content, data now permeates every stage of the AI lifecycle from the training samples that shape model parameters to the prompts and outputs that drive real-world model deployment. This shift renders traditional notions of data protection insufficient, while the boundaries of what needs safeguarding remain poorly defined. Failing to safeguard data in AI systems can inflict societal and individual, underscoring the urgent need to clearly delineate the scope of and rigorously enforce data protection. In this perspective, we propose a four-level taxonomy, including non-usability, privacy preservation, traceability, and deletability, that captures the diverse protection needs arising in modern (generative) AI models and systems. Our framework offers a structured understanding of the trade-offs between data utility and control, spanning the entire AI pipeline, including training datasets, model weights, system prompts, and AI-generated content. We analyze representative technical approaches at each level and reveal regulatory blind spots that leave critical assets exposed. By offering a structured lens to align future AI technologies and governance with trustworthy data practices, we underscore the urgency of rethinking data protection for modern AI techniques and provide timely guidance for developers, researchers, and regulators alike.

OpenAI previously announced that it was considering allowing teens to add a trusted emergency contact to their account. But the company did not outline concrete plans to add such a measure in its most recent blog post. "These steps are only the beginning. We will continue learning and strengthening our approach, guided by experts, with the goal of making ChatGPT as helpful as possible," the company said. This announcement comes a week after the parents of teenage boy who died by suicide sued OpenAI, alleging its ChatGPT helped their son Adam "explore suicide methods."

Yesterday, OpenAI announced that it will be introducing new parental controls in ChatGPT within a month. The feature will allow parents to link their own accounts to those of their teenage children and control how the AI chatbot can be used by them. Among other things, the memory and chat history features can be switched off via parental controls, and the system can also send automatic notifications to the parent if it detects that a child is in "acute distress." OpenAI also states that more security features are on the way in the next 120 days as part of a broader effort to make ChatGPT safer to use, and these initiatives are "guided by experts." The launch of parental controls comes after OpenAI was sued in a high-profile case in which the parents of a teenage suicide victim claim that ChatGPT helped him plan and go through with his suicide.

OpenAI has announced plans to introduce parental controls for ChatGPT amid growing controversy over how artificial intelligence is affecting young people's mental health. In a blog post on Tuesday, the California-based AI company said it was rolling out the features in recognition of families needing support "in setting healthy guidelines that fit a teen's unique stage of development". Under the changes, parents will be able to link their ChatGPT accounts with those of their children, disable certain features, including memory and chat history, and control how the chatbot responds to queries via "age-appropriate model behavior rules." Parents will also be able to receive notifications when their teen shows signs of distress, OpenAI said, adding that it would seek expert input in implementing the feature to "support trust between parents and teens". OpenAI, which last week announced a series of measures aimed at enhancing safety for vulnerable users, said the changes would come into effect within the next month.

Understanding health information is essential in achieving and maintaining a healthy life. We focus on simplifying health information for better understanding. With the availability of generative AI, the simplification process has become efficient and of reasonable quality, however, the algorithms remove information that may be crucial for comprehension. In this study, we compare generative AI to detect missing information in simplified text, evaluate its importance, and fix the text with the missing information. We collected 50 health information texts and simplified them using gpt-4-0613. We compare five approaches to identify missing elements and regenerate the text by inserting the missing elements. These five approaches involve adding missing entities and missing words in various ways: 1) adding all the missing entities, 2) adding all missing words, 3) adding the top-3 entities ranked by gpt-4-0613, and 4, 5) serving as controls for comparison, adding randomly chosen entities. We use cosine similarity and ROUGE scores to evaluate the semantic similarity and content overlap between the original, simplified, and reconstructed simplified text. We do this for both summaries and full text. Overall, we find that adding missing entities improves the text. Adding all the missing entities resulted in better text regeneration, which was better than adding the top-ranked entities or words, or random words. Current tools can identify these entities, but are not valuable in ranking them.

Natural disasters, including earthquakes, wildfires and cyclones, bear a huge risk on human lives as well as infrastructure assets. An effective response to disaster depends on the ability to rapidly and efficiently assess the intensity of damage. Artificial Intelligence (AI) and Generative Artificial Intelligence (GenAI) presents a breakthrough solution, capable of combining knowledge from multiple types and sources of data, simulating realistic scenarios of disaster, and identifying emerging trends at a speed previously unimaginable. In this paper, we present a comprehensive review on the prospects of AI and GenAI in damage assessment for various natural disasters, highlighting both its strengths and limitations. We talk about its application to multimodal data such as text, image, video, and audio, and also cover major issues of data privacy, security, and ethical use of the technology during crises. The paper also recognizes the threat of Generative AI misuse, in the form of dissemination of misinformation and for adversarial attacks. Finally, we outline avenues of future research, emphasizing the need for secure, reliable, and ethical Generative AI systems for disaster management in general. We believe that this work represents the first comprehensive survey of Gen-AI techniques being used in the field of Disaster Assessment and Response.

3D generative AI enables rapid and accessible creation of 3D models from text or image inputs. However, translating these outputs into physical objects remains a challenge due to the constraints in the physical world. Recent studies have focused on improving the capabilities of 3D generative AI to produce fabricable outputs, with 3D printing as the main fabrication method. However, this workshop paper calls for a broader perspective by considering how fabrication methods align with the capabilities of 3D generative AI. As a case study, we present a novel system using discrete robotic assembly and 3D generative AI to make physical objects. Through this work, we identified five key aspects to consider in a physical making process based on the capabilities of 3D generative AI. 1) Fabrication Constraints: Current text-to-3D models can generate a wide range of 3D designs, requiring fabrication methods that can adapt to the variability of generative AI outputs. 2) Time: While generative AI can generate 3D models in seconds, fabricating physical objects can take hours or even days. Faster production could enable a closer iterative design loop between humans and AI in the making process. 3) Sustainability: Although text-to-3D models can generate thousands of models in the digital world, extending this capability to the real world would be resource-intensive, unsustainable and irresponsible. 4) Functionality: Unlike digital outputs from 3D generative AI models, the fabrication method plays a crucial role in the usability of physical objects. 5) Accessibility: While generative AI simplifies 3D model creation, the need for fabrication equipment can limit participation, making AI-assisted creation less inclusive. These five key aspects provide a framework for assessing how well a physical making process aligns with the capabilities of 3D generative AI and values in the world.

The rapid evolution of artificial intelligence (AI), together with the increased availability of social media and news for epidemiological surveillance, are marking a pivotal moment in epidemiology and public health research. Leveraging the power of generative AI, we use an ensemble approach which incorporates multiple Large Language Models (LLMs) to extract valuable actionable epidemiological information from the World Health Organization (WHO) Disease Outbreak News (DONs). DONs is a collection of regular reports on global outbreaks curated by the WHO and the adopted decision-making processes to respond to them. The extracted information is made available in a daily-updated dataset and a knowledge graph, referred to as eKG, derived to provide a nuanced representation of the public health domain knowledge. We provide an overview of this new dataset and describe the structure of eKG, along with the services and tools used to access and utilize the data that we are building on top. These innovative data resources open altogether new opportunities for epidemiological research, and the analysis and surveillance of disease outbreaks.

Many scientists use generative AI in their scientific work. People working in technology assessment (TA) are no exception. TA's approach to generative AI is twofold: on the one hand, generative AI is used for TA work, and on the other hand, generative AI is the subject of TA research. After briefly outlining the phenomenon of generative AI and formulating requirements for its use in TA, the following article discusses in detail the structural causes of the problems associated with it. Although generative AI is constantly being further developed, the structurally induced risks remain. The article concludes with proposed solutions and brief notes on their feasibility, as well as some examples of the use of generative AI in TA work.