Related papers: Learning Robust and Privacy-Preserving Representat…
Although deep networks achieve strong accuracy on a range of computer vision benchmarks, they remain vulnerable to adversarial attacks, where imperceptible input perturbations fool the network. We present both theoretical and empirical…
DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor attacks. A backdoored model always predicts a target class in…
The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…
Imitation learning can reproduce policies by observing experts, which poses a problem regarding policy privacy. Policies, such as human, or policies on deployed robots, can all be cloned without consent from the owners. How can we protect…
Nowadays, numerous applications incorporate machine learning (ML) algorithms due to their prominent achievements. However, many studies in the field of computer vision have shown that ML can be fooled by intentionally crafted instances,…
An information-theoretic framework is introduced to analyze last-layer embedding, focusing on learned representations for regression tasks. We define representation-rate and derive limits on the reliability with which input-output…
Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…
A common belief is that intrinsically interpretable deep learning models ensure a correct, intuitive understanding of their behavior and offer greater robustness against accidental errors or intentional manipulation. However, these beliefs…
The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…
In this study, we harness the information-theoretic Privacy Funnel (PF) model to develop a method for privacy-preserving representation learning using an end-to-end training framework. We rigorously address the trade-off between obfuscation…
Machine learning models, especially deep neural networks have been shown to be susceptible to privacy attacks such as membership inference where an adversary can detect whether a data point was used for training a black-box model. Such…
Optimizing prediction accuracy can come at the expense of fairness. Towards minimizing discrimination against a group, fair machine learning algorithms strive to equalize the behavior of a model across different groups, by imposing a…
Adversarial Machine Learning (AML) is emerging as a major field aimed at protecting machine learning (ML) systems against security threats: in certain scenarios there may be adversaries that actively manipulate input data to fool learning…
The burgeoning success of deep learning has raised the security and privacy concerns as more and more tasks are accompanied with sensitive data. Adversarial attacks in deep learning have emerged as one of the dominating security threat to a…
Convolutional neural networks have been used to achieve a string of successes during recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into…
We present a new algorithm to learn a deep neural network model robust against adversarial attacks. Previous algorithms demonstrate an adversarially trained Bayesian Neural Network (BNN) provides improved robustness. We recognize the…
We consider the theoretical problem of designing an optimal adversarial attack on a decision system that maximally degrades the achievable performance of the system as measured by the mutual information between the degraded signal and the…
Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from having provable guarantees against adversarial examples. The…
Security, privacy, and fairness have become critical in the era of data science and machine learning. More and more we see that achieving universally secure, private, and fair systems is practically impossible. We have seen for example how…
The reliability of a learning model is key to the successful deployment of machine learning in various industries. Creating a robust model, particularly one unaffected by adversarial attacks, requires a comprehensive understanding of the…