Related papers: Ungeneralizable Examples
Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose unrestricted…
Across various domains, the growing advocacy for open science and open-source machine learning has made an increasing number of models publicly available. These models allow practitioners to integrate them into their own contexts, reducing…
Machine learning models may inadvertently memorize sensitive, unauthorized, or malicious data, posing risks of privacy breaches, security vulnerabilities, and performance degradation. To address these issues, machine unlearning has emerged…
Growing concerns surrounding AI safety and data privacy have driven the development of Machine Unlearning as a potential solution. However, current machine unlearning algorithms are designed to complement the offline training paradigm. The…
Machine unlearning aims to remove the influence of specific data from trained models while preserving general utility. Existing approximate unlearning methods often rely on performance-degradation heuristics, such as loss maximization or…
Privacy protection laws, such as the GDPR, grant individuals the right to request the forgetting of their personal data not only from databases but also from machine learning (ML) models trained on them. Machine unlearning has emerged as a…
In the last decade, data-driven algorithms outperformed traditional optimization-based algorithms in many research areas, such as computer vision, natural language processing, etc. However, extensive data usages bring a new challenge or…
Graph neural networks (GNNs) are widely used for learning from graph-structured data in domains such as social networks, recommender systems, and financial platforms. To comply with privacy regulations like the GDPR, CCPA, and PIPEDA,…
The demand for data privacy has led to the development of frameworks like Federated Graph Learning (FGL), which facilitate decentralized model training. However, a significant operational challenge in such systems is adhering to the right…
In order to adhere to regulatory standards governing individual data privacy and safety, machine learning models must systematically eliminate information derived from specific subsets of a user's training data that can no longer be…
Owing much to the revolution of information technology, the recent progress of deep learning benefits incredibly from the vastly enhanced access to data available in various digital formats. However, in certain scenarios, people may not…
Recent data-privacy laws have sparked interest in machine unlearning, which involves removing the effect of specific training samples from a learnt model as if they were never present in the original training dataset. The challenge of…
With the rapid growth of graph-structured data in critical domains, unsupervised graph-level anomaly detection (UGAD) has become a pivotal task. UGAD seeks to identify entire graphs that deviate from normal behavioral patterns. However,…
Currently, various uncertainty quantification methods have been proposed to provide certainty and probability estimates for deep learning models' label predictions. Meanwhile, with the growing demand for the right to be forgotten, machine…
This paper reveals a data bias issue that can severely affect the performance while conducting a machine learning model for malicious URL detection. We describe how such bias can be identified using interpretable machine learning…
Machine learning models are vulnerable to Adversarial Examples: minor perturbations to input samples intended to deliberately cause misclassification. Current defenses against adversarial examples, especially for Deep Neural Networks (DNN),…
Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles and medical diagnosis. However, recent studies indicate that DNNs are vulnerable to adversarial examples (AEs),…
Large language models trained on web-scale data can memorize private or sensitive knowledge, raising significant privacy risks. Although some unlearning methods mitigate these risks, they remain vulnerable to "relearning" during subsequent…
Deep learning based models are vulnerable to adversarial attacks. These attacks can be much more harmful in case of targeted attacks, where an attacker tries not only to fool the deep learning model, but also to misguide the model to…
The generalization ability of deep learning has been extensively studied in supervised settings, yet it remains less explored in unsupervised scenarios. Recently, the Unsupervised Domain Generalization (UDG) task has been proposed to…