Adversarial attacks can fool copyright detection systems.
problem Vulnerability of copyright detection systems to adversarial attacks.
method Used gradient methods to create adversarial music that fooled detection systems.
result Adversarial attacks can successfully deceive industrial copyright detection tools.
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.
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.
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.
Paper presents membership encoding for deep learning models to protect training data.
problem Protecting training data from inference attacks and ensuring copyright.
method Membership encoding algorithm for deep neural networks.
result Membership information can be encoded for a subset of training data, robust to model compression and fine-tuning.
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.
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.
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.
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.
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.
New link detection results using closures of 3-braids.
problem Link detection using homology theories.
method Closure operations on 3-braids and homology theories.
result Detection of specific links using link Floer homology, Khovanov homology, and annular Khovanov homology.
Deep learning improves anomaly detection across various fields.
problem Detecting anomalies in data with advanced approaches.
method Survey of deep learning methods for anomaly detection.
result Advancements in deep anomaly detection address unique challenges.
Deep learning improves combustor anomaly detection in gas turbines.
problem Improving anomaly detection performance in gas turbine combustors.
method Hierarchically learned features from exhaust gas temperature sensor measurements using deep learning.
result Deep learning-based anomaly detection significantly improved combustor anomaly detection performance.
Graph energy helps detect communities in networks better than traditional methods.
problem Detecting communities in sparse networks where traditional methods fail.
method Using graph energy based on the full spectrum of adjacency matrices.
result The difference in graph energy between a planted partition model and an Erdős--Rényi network has a distinct transition at the detectability threshold.
New ML-based detection improves PMH signal detection in load-modulated MIMO systems.
problem Detecting PMH signals without prior CSI is challenging and computationally expensive.
method Proposes HEM-ML and HEM-KD schemes using EM and KD-tree for efficient detection.
result Achieves comparable detection results to optimal ML detector with reduced complexity.
Develops slope detection for 3-manifolds with torus boundaries.
problem Determining slopes on the boundary of 3-manifolds with torus boundaries.
method Introduces order-detection and representation-detection of slopes, proving their equivalence.
result Shows how slopes' behavior changes with cabling, improving previous results.
2DSig-Detect detects adversarial perturbations in images.
problem Adversarial attacks degrade image model performance.
method 2D-signature embedded semi-supervised framework using rough path theory.
result 2DSig-Detect outperforms other methods in detecting adversarial perturbations.
Develops a method to detect changes in linear systems with temporal correlations.
problem Detect abrupt changes in time series data with temporal correlations.
method Data-dependent threshold for online change point detection in linear dynamical systems.
result Achieves a pre-specified upper bound on the probability of false alarms and provides a finite-sample-based bound for detection probability.
Tackles the computational hardness of HPC detection, conjecturing equivalence to PC detection.
problem Computational hardness of hypergraphic planted clique detection.
method No specific method mentioned; focuses on conjecturing equivalence.
result Equivalence of computational hardness between HPC and PC detection.
Real-time fuel leakage detection framework MOCPD improves accuracy.
problem Early detection of fuel leakage to prevent hazards and losses.
method Memory-based Online Change Point Detection (MOCPD) framework.
result MOCPD outperforms baseline methods in detection accuracy.
Study on detecting hierarchical community structures in networks.
problem Detecting hierarchical community structures in networks.
method Analysis of planted hierarchies of partitions in networks, identifying additional detectability phases.
result There are additional phases in which the presence of multiple consistent partitions can either help or hinder detection of hierarchical structures.
Deep object detection improves mitotic nucleus detection in breast cancer biopsies.
problem Challenges in automated mitotic nucleus detection in breast cancer histopathological images.
method Adapted Mask R-CNN for deep object detection, initially selects candidate regions with maximum recall, refines them with multi-object loss function.
result Improved discrimination ability (F-score of 0.86) and significant precision (0.86) for mitotic nuclei compared to two-stage models.
ECAD detects anomalies without data exchangeability, improving traffic flow detection.
problem Detecting anomalies in spatio-temporal data with missing values.
method ECAD uses conformal prediction to wrap around any regression algorithm, controlling Type-I error without data exchangeability.
result ECAD outperforms other methods in detecting anomalous traffic flow.
Autonomous driving requires 3D perception of vehicles and other objects in the in environment. Much of the current methods support 2D vehicle detection. This paper proposes a flexible pipeline to adopt any 2D detection network and fuse it with a 3D point cloud to generate 3D information with minimum changes of the 2D d…
PAC-Wrap provides provable guarantees for semi-supervised anomaly detection.
problem Ensuring reliable anomaly detection in safety-critical applications.
method PAC-Wrap wraps around existing anomaly detection methods to provide PAC guarantees.
result PAC-Wrap effectively provides rigorous guarantees for various anomaly detectors.
This paper offers a distribution-free method for post-detection changepoint localization.
problem Locating the exact time of a change in distribution after a sequential detection procedure.
method A distribution-free framework using conformal test martingales for sequential change detection and post-detection inference.
result Valid post-detection coverage guarantees and non-asymptotic bounds on confidence set size.
The study defines backdoor detection in ML and proves its infeasibility.
problem Backdoor detection in machine learning systems.
method Formal statistical definition and analysis of feasibility.
result Backdoor detection is impossible except for very small alphabet sizes.
Detects data drift in deep learning models using neural embeddings.
problem Detecting changes in data distribution in deep learning models.
method Formulates drift detection in a sequential decision framework and introduces a loss function to balance false alarms and quick detection.
result Demonstrates improved ability to balance false alarms and quick detection in change detection.
GANs improve anomaly detection accuracy.
problem Detecting unseen anomalies is challenging.
method Adversarial training of GANs.
result Remarkable results on anomaly detection.
End-to-end method learns geometry and appearance for multi-view object detection.
problem Challenges in multi-view object detection, including viewpoint, lighting, and scale variability.
method Jointly learns multi-view geometry and warping for robust cross-view object detection.
result Superior performance compared to baselines on a new street-level panorama data set.
It follows from earlier work of Silver-Williams and the authors that twisted Alexander polynomials detect the unknot and the Hopf link. We now show that twisted Alexander polynomials also detect the trefoil and the figure-8 knot, that twisted Alexander polynomials detect whether a link is split and that twisted Alexand…
This research identifies flaws in drift detection methods and creates adversarial data streams to exploit them.
problem The challenge of detecting data distribution changes (drift) in real-time systems.
method Developed adversarial data streams to show weaknesses in existing drift detection schemes.
result Demonstrated that common drift detection methods can be fooled by adversarial data streams.
Multimodal deep learning improves flaw detection in software programs.
problem Current flaw detection relies on single software representations.
method Adapted multimodal deep learning models for flaw detection.
result Multimodal models outperform traditional deep learning models.
New method detects OOD samples using neural network trajectories.
problem Lack of comprehensive layer exploration in OOD detection.
method Functional data perspective, analyzing sample trajectories through multi-layer classifier.
result Empirically validated as effective compared to state-of-the-art methods.
Proposes OCGNN for detecting anomalies in graph data.
problem Detecting anomalies in graph-structured data.
method One Class Graph Neural Network (OCGNN) combining Graph Neural Networks and one-class classification.
result Significant improvements in anomaly detection compared to baselines.
Early detection of cyber-attacks is crucial for a safe and reliable operation of the smart grid. In the literature, outlier detection schemes making sample-by-sample decisions and online detection schemes requiring perfect attack models have been proposed. In this paper, we formulate the online attack/anomaly detection…
A method detects vehicles far from tunnel CCTV using AI.
problem Tunnel CCTV's height limits detection of far-away vehicles.
method Object detection algorithm with inverse perspective transform.
result Deep learning model trained on warped images detects vehicles more accurately.
A novel semi-supervised outlier detection model detects anomalies with few labels.
problem Efficiently detecting group anomalies with limited labeled data.
method RCC-Dual-GAN model that combines RCC and M-GAN components for semi-supervised outlier detection.
result Significantly improved accuracy in outlier detection with few labeled anomalies.