New method reduces copyright risks in AI-generated images.
problem Copyright issues in AI-generated images.
method Genericization method using originality estimation and PREGen technique.
result PREGen reduces likelihood of generating copyrighted characters by over half.
Study copyright's impact on creative industries using AI-generated fonts.
problem Estimating supply and demand in creative industries with AI-generated content.
method Neural network embeddings, spatial regression, event-study analyses, structural model of supply and demand.
result Copyright can raise consumer welfare by encouraging product relocation.
It is well-known that many machine learning models are susceptible to adversarial attacks, in which an attacker evades a classifier by making small perturbations to inputs. This paper discusses how industrial copyright detection tools, which serve a central role on the web, are susceptible to adversarial attacks. We di…
Proves bounds on copyright risk for generative models.
problem Generative models risk producing similar content to copyrighted data.
method Defines NAF, proves bounds, and provides learning algorithms.
result Generative models can be made less likely to produce copyrighted content.
NegToMe uses images to guide text-based models away from unwanted visual elements.
problem Insufficient text-based adversarial guidance for complex visual concepts.
method Negative token merging (NegToMe) using visual features from reference images.
result Significantly enhances output diversity and reduces visual similarity to copyrighted content.
Machine learning as a service (MLaaS), and algorithm marketplaces are on a rise. Data holders can easily train complex models on their data using third party provided learning codes. Training accurate ML models requires massive labeled data and advanced learning algorithms. The resulting models are considered as intell…
Algorithm removes backdoor watermarks from neural networks robustly.
problem Protecting neural networks from backdoor attacks.
method Neural network laundering algorithm.
result Effective removal of backdoor watermarks with high test accuracy.
The paper tackles data misappropriation in LLMs by embedding watermarks and testing for their presence.
problem Detecting data misappropriation in LLMs trained on copyrighted data.
method Embedding watermarks, formulating as hypothesis testing, developing statistical framework, constructing test statistics, determining optimal thresholds, controlling errors, establishing asymptotic optimality.
result The proposed statistical testing framework effectively detects data misappropriation in LLMs.
When machine learning systems fail because of adversarial manipulation, how should society expect the law to respond? Through scenarios grounded in adversarial ML literature, we explore how some aspects of computer crime, copyright, and tort law interface with perturbation, poisoning, model stealing and model inversion…
In-Run Data Shapley offers efficient data attribution for large-scale models.
problem Existing data attribution methods are computationally intensive and cannot target specific models.
method In-Run Data Shapley, which efficiently attributes data contributions to a specific model without re-training.
result In-Run Data Shapley achieves significant efficiency, enabling data attribution for pretraining models.
Generative AI tasks analyzed for text, images, audio, video, code, and molecules.
problem What is the core question when using generative AI?
method Survey of generative model families, probabilistic framework, game-theoretic setup, post-training modifications, socially responsible considerations.
result Generative AI is a distinct machine learning task with connections to prediction, compression, and decision-making.
Designing AI market for content creation
problem Balancing technological progress and individual incentives for content creation
method Dynamic Stackelberg game model
result Inducing greater reliance on AI-assisted creation
A new method for unlearning trained models without needing the original data.
problem Lack of access to original training data for privacy-preserving unlearning.
method Uses a surrogate dataset to approximate statistical properties and calibrates noise based on statistical distance.
result Effective unlearning of trained models with strong privacy guarantees, even without access to the original data.
NPO method improves LLM unlearning without catastrophic collapse.
problem Efficiently unlearning undesirable data from LLMs without losing model utility.
method Negative Preference Optimization (NPO) method based on alignment.
result NPO-based methods achieve better unlearning results and maintain model utility.
This paper examines how Higher-Order Langevin Dynamics reduces memorization in diffusion models.
problem Memorization of training samples in diffusion models, violating copyright and privacy.
method Introduces Higher-Order Langevin Dynamics (HOLD) to regularize diffusion model trajectories.
result The dynamics of the data variable in HOLD are governed by a low-pass-filtered version of the learned score function, with smoothness increasing with model order.
These are lecture notes for a course on machine learning with neural networks for scientists and engineers that I have given at Gothenburg University and Chalmers Technical University in Gothenburg, Sweden. The material is organised into three parts: Hopfield networks, supervised learning of labeled data, and learning …
A new method for forgetting data from trained models using information theory.
problem Efficiently forgetting private or copyrighted data from trained machine learning models.
method An information-theoretic approach to zero-shot unlearning, minimizing gradient smoothing.
result Our method successfully unlearns data while maintaining model performance.
AutoAnchor uses cross-attention to improve text-to-image model unlearning.
problem Mitigating harmful or copyrighted content in text-to-image models.
method Two-stage framework that automatically synthesizes manifold-proximal anchors using cross-attention consistency loss.
result Effective robust and unbiased unlearning across various baselines.
The study uncovers the conditions under which diffusion models memorize or generalize.
problem Understanding the balance between memorization and generalization in diffusion models.
method Theoretical and mathematical framework to investigate memorization and generalization in diffusion models.
result Theoretical crossover point predicts a phase transition in diffusion models, validating the hypothesis.
A statistical framework for removing unwanted data domains in machine learning.
problem Removing unwanted data domains in machine learning while preserving desired performance.
method Modeling domains as probability distributions and using hypothesis testing to select samples to remove.
result Characterization of allowable edited data distributions and removal-preservation Pareto frontiers for various distribution families.