Related papers: How to Protect Models against Adversarial Unlearni…

The renaissance of deep learning has led to the massive development of automated driving. However, deep neural networks are vulnerable to adversarial examples. The perturbations of adversarial examples are imperceptible to human eyes but…

Adversarial Training has proved to be an effective training paradigm to enforce robustness against adversarial examples in modern neural network architectures. Despite many efforts, explanations of the foundational principles underpinning…

Adversarial machine learning, i.e., increasing the robustness of machine learning algorithms against so-called adversarial examples, is now an established field. Yet, newly proposed methods are evaluated and compared under unrealistic…

Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain…

Federated learning allows multiple clients to collaboratively train a global model with the assistance of a server. However, its distributed nature makes it susceptible to poisoning attacks, where malicious clients can compromise the global…

Adversarial reprogramming allows repurposing a machine-learning model to perform a different task. For example, a model trained to recognize animals can be reprogrammed to recognize digits by embedding an adversarial program in the digit…

Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains. However, this utility comes with increasing concerns about privacy, as the training data may…

Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models. Unlike other defense strategies, adversarial training aims to promote the robustness of models intrinsically.…

Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieved empirical success in practice, it still remains unclear…

Machine learning is vulnerable to a wide variety of attacks. It is now well understood that by changing the underlying data distribution, an adversary can poison the model trained with it or introduce backdoors. In this paper we present a…

Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms…

Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering trigger patterns but fail to restore the correct semantic…

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…

It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence. In this work, we take the opposite stance: an overly confident model is more likely to be vulnerable to…

Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unlearning via statistical indistinguishability from re-trained…

Forecasting irregular time series presents significant challenges due to two key issues: the vulnerability of models to mean regression, driven by the noisy and complex nature of the data, and the limitations of traditional error-based…

Advances in machine learning have led to broad deployment of systems with impressive performance on important problems. Nonetheless, these systems can be induced to make errors on data that are surprisingly similar to examples the learned…

There have been recent adversarial attacks that are difficult to find. These new adversarial attacks methods may pose challenges to current deep learning cyber defense systems and could influence the future defense of cyberattacks. The…

Large Language Models (LLMs) are foundational to AI advancements, facilitating applications like predictive text generation. Nonetheless, they pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted…

Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks without knowledge of the target model's parameters. Adversarial…