United States

We introduce OmniMark, a novel and efficient fingerprinting method for Latent Diffusion Models. 
OmniMark can encode user-specific fingerprints across multiple dimensions of the diffusion model&#39;s weights, including kernels, filters, channels, and spatial dimensions, which ends up with the presence of invisible fingerprints in any generated images that can be subsequently extracted by a decoder.
This approach thus achieves efficient and scalable ad-hoc generation (&lt;100 ms) of numerous models with unique fingerprints that enable user responsibility tracking and attribution of the model.
Our experiments demonstrate that OmniMark applies to various image generation and editing tasks, and achieves Highly accurate fingerprint detection without compromising image quality. 
Furthermore, we show that our approach exhibits good robustness, against both white-box model attacks and image attacks, including fine-tuning and JPEG compression.

AAAI 2025

OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting

autoencoders

deep generative models

### Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

Message from the General Chair: 
*It is my great pleasure and honor to welcome you to the 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), held in beautiful Vienna, Austria, from July 27 to August 1, 2025. ACL2025continues our field’s tradition of excellence in scholarship, innovation, and inclusivity, and I am deeply grateful to the many volunteers who have worked tirelessly to bring this event to life.* 
[Read more](https://drive.google.com/file/d/1GI_hvOpjswAuYdUTromfeDiPpCcqidwg/view?usp=sharing)

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to ACL 2025". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you need to log in with the **email address you registered with**. 

ACL 2025

Welcome to The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025)

We introduce OmniMark, a novel and efficient fingerprinting method for Latent Diffusion Models. 
OmniMark can encode user-specific fingerprints across multiple dimensions of the diffusion model's weights, including kernels, filters, channels, and spatial dimensions, which ends up with the presence of invisible fingerprints in any generated images that can be subsequently extracted by a decoder.
This approach thus achieves efficient and scalable ad-hoc generation (<100 ms) of numerous models with unique fingerprints that enable user responsibility tracking and attribution of the model.
Our experiments demonstrate that OmniMark applies to various image generation and editing tasks, and achieves Highly accurate fingerprint detection without compromising image quality. 
Furthermore, we show that our approach exhibits good robustness, against both white-box model attacks and image attacks, including fine-tuning and JPEG compression.

technical paper

We are pleased to announce the Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), which will be held in Philadelphia, Pennsylvania at the Pennsylvania Convention Center from February 25 to March 4, 2025.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

### [Invited Speakers](https://aaai.org/conference/aaai/aaai-25/aaai-25-invited-speakers/)

Register [here](https://aaai.org/conference/aaai/aaai-25/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-25 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.



With rapid advances, generative large language models (LLMs) dominate various Natural Language Processing (NLP) tasks from understanding to reasoning. Yet, language models' inherent vulnerabilities may be exacerbated due to increased accessibility and unrestricted model training on massive textual data from the Internet. A malicious adversary may publish poisoned data online and conduct backdoor attacks on the victim LLMs pre-trained on the poisoned data. Backdoored LLMs behave innocuously for normal queries and generate harmful responses when the backdoor trigger is activated. Despite significant efforts paid to LLMs' safety issues, LLMs are still struggling against backdoor attacks. As Anthropic recently revealed, existing safety training strategies, including supervised fine-tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF), fail to revoke the backdoors once the LLM is backdoored during the pre-training stage. In this paper, we present Simulate and Eliminate (SANDE) to erase the undesired backdoored mappings for generative LLMs. We initially propose Overwrite Supervised Fine-tuning (OSFT) for effective backdoor removal when the trigger is known. Then, to handle the scenarios where the trigger patterns are unknown, we integrate OSFT into our two-stage framework, SANDE. Unlike previous works that center on the identification of backdoors, our safety-enhanced LLMs are able to behave normally even when the exact triggers are activated. We conduct comprehensive experiments to show that our proposed SANDE is effective against backdoor attacks while bringing minimal harm to LLMs' powerful capability without any additional access to unbackdoored clean models. We will release the reproducible code.

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models

The application of graph neural networks (GNNs) to learn heuristic functions in classical planning is gaining traction. Despite the variety of methods proposed in the literature to encode classical planning tasks for GNNs, a comparative study evaluating their relative performances has been lacking. Moreover, some encodings have been assessed solely for their expressiveness rather than practical effectiveness in planning. This paper provides an extensive comparative analysis of existing encodings. Our results indicate that the smallest encoding based on Gaifman graphs, not yet applied in planning, outperforms the rest due to its fast evaluation times and the informativeness of the resulting heuristic. The overall coverage measured on the IPC almost reaches that of the state-of-the-art planner LAMA, while exhibiting rather complementary strengths across different domains.

State Encodings for GNN-Based Lifted Planners

Retrosynthesis prediction focuses on identifying reactants capable of synthesizing a target product. Typically, the retrosynthesis prediction involves two phases: Reaction Center Identification and Reactant Generation. However, we argue that most existing methods suffer from two limitations in the two phases: 1) Existing models do not adequately capture the "face" information in molecular graphs for the reaction center identification. 2) Current approaches for the reactant generation predominantly use sequence generation in a 2D space, which lacks versatility in generating reasonable distributions for completed reactive groups and overlooks molecules' inherent 3D properties. To overcome the above limitations, we propose GDiffRetro. For the reaction center identification, GDiffRetro uniquely integrates the original graph with its corresponding dual graph to represent molecular structures, which helps guide the model to focus more on the faces in the graph. For the reactant generation, GDiffRetro employs a conditional diffusion model in 3D to further transform the obtained synthon into a complete reactant. Our experimental findings reveal that GDiffRetro outperforms contemporary state-of-the-art semi-template models across various evaluative metrics (for example, GDiffRetro achieves a performance improvement of up to 12.0% on top-1 accuracy).

GDiffRetro: Retrosynthesis Prediction with Dual Graph Enhanced Molecular Representation and Diffusion Generation

Human–Computer Interaction for AI Systems Design is an eight-week short online course aimed at professional students. It is part of an online course platform called Cambridge Advance Online, which is a joint effort between Cambridge University Press & Assessment and the University of Cambridge. This course launched in July 2023 amidst a massive increase in interest in AI and its applications, and quickly became one of the platform's highest-enrolling courses, attracting about 50 students per quarterly course run. To date, more than 200 students have completed the course, and more than 90 percent have rated their experience `good' or `excellent'. This paper reports on our experiences in designing and teaching this course.

Human-Computer Interaction for AI Systems Design: Reflections on an Online Course on Human-AI Interaction for Professionals

Concerns about the risks and harms posed by artificial intelligence (AI) have resulted in significant study into algorithmic transparency, giving rise to a sub-field known as Explainable AI (XAI). Unfortunately, despite a decade of development in XAI, an existential challenge remains: progress in research has not been fully translated into the actual implementation of algorithmic transparency by organizations. In this work, we test an approach for addressing the challenge by creating transparency advocates, or motivated individuals within organizations who drive a ground-up cultural shift towards improved algorithmic transparency.

Over several years, we created an open-source educational workshop on algorithmic transparency and advocacy. We delivered the workshop to professionals across two separate domains to improve their algorithmic transparency literacy and willingness to advocate for change. In the weeks following the workshop, participants applied what they learned, such as speaking up for algorithmic transparency at an organization-wide AI strategy meeting. We also make two broader observations: first, advocacy is not a monolith and can be broken down into different levels. Second, individuals' willingness for advocacy is affected by their professional field. For example, news and media professionals may be more likely to advocate for algorithmic transparency than those working at technology start-ups.

Making Transparency Advocates: An Educational Approach Towards Better Algorithmic Transparency in Practice

Responsible AI (RAI) encompasses the science and practice of ensuring that AI design, development, and use are socially sustainable--—maximizing the benefits of technology while mitigating its risks. Industry practitioners play a crucial role in achieving the objectives of RAI, yet there is a persistent a shortage of consolidated educational resources and effective methods for teaching RAI to practitioners.

In this paper, we present a stakeholder-first educational approach using interactive case studies to foster organizational and practitioner-level engagement and enhance learning about RAI. We detail our partnership with Meta, a global technology company, to co-develop and deliver RAI workshops to a diverse company audience. Assessment results show that participants found the workshops engaging and reported an improved understanding of RAI principles, along with increased motivation to apply them in their work.

Using Case Studies to Teach Responsible AI to Industry Practitioners

In a prior paper, we argued that Artificial Intelligence (AI) should be placed on a different foundation, one based on pattern recognition and feature learning rather than symbol manipulation and feature engineering. In this paper, we provide a proof of concept of an AI course that follows that proposed approach. Students study how these systems become so incredibly powerful through machine learning of features and through pattern matching. Students learn how those systems represent knowledge and they study their currently limited reasoning abilities. Students spend time discussing the accomplishments of current systems, positive as well as negative and they study the projected impact of anticipated systems. In this paper, we give a brief argument of why one would want to offer such a course. We present a detailed outline of the contents of such a course, together with learning materials and their proposed use. We summarize relevant anonymous student feedback and offer a subjective evaluation of the pilot course.

Towards an AI Course Based on Neural Networks

AI Reasoning and System 2 Thinking

The media are agog with claims that recent advances in AI put artificial general intelligence (AGI) within reach. Is this true?  If so, is that a good thing? Alan Turing predicted that AGI would result in the machines taking control. Turing was right to express concern but wrong to think that doom is inevitable. Yet the question of whether superior AI systems can really benefit humanity remains unanswered. It may be that they can do so only by their absence.

Can AI Benefit Humanity?

Over the past few years, Artificial Intelligence has bounded into the mainstream of society.  Remarkable technical achievements in the use of Deep Learning and  Large Language Models have given rise to expectations and hype regarding the possibility of achieving artificial general intelligence, as well as general concerns over the potential deleterious consequences of emerging AI technologies and how to ensure their responsible use. In this panel we engage four Past AAAI Presidents to discuss their views on questions relating to the current state and future of AI research, including such topics as important emerging application areas, current technical challenges, the eventual prospects for achieving artificial general intelligence, and potential AI risks and solutions.

Downloads

Next from AAAI 2025

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models

Similar lecture

MEraser: An Effective Fingerprint Erasure Approach for Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2025

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models

Similar lecture

MEraser: An Effective Fingerprint Erasure Approach for Large Language Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads