相关论文: Adversarial Infidelity Learning for Model Interpre…

Despite their remarkable performance, deep neural networks exhibit a critical vulnerability: small, often imperceptible, adversarial perturbations can lead to drastically altered model predictions. Given the stringent reliability demands of…

We propose a novel one-step supervised imitation learning (IL) framework called Adversarial Density Regression (ADR). This IL framework aims to correct the policy learned on unknown-quality to match the expert distribution by utilizing…

Understanding black-box machine learning models is crucial for their widespread adoption. Learning globally interpretable models is one approach, but achieving high performance with them is challenging. An alternative approach is to explain…

While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some…

Although adversarial training (AT) has proven effective in enhancing the model's robustness, the recently revealed issue of fairness in robustness has not been well addressed, i.e. the robust accuracy varies significantly among different…

Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a…

Model interpretability is an increasingly important component of practical machine learning. Some of the most common forms of interpretability systems are example-based, local, and global explanations. One of the main challenges in…

Self-attention heads are characteristic of Transformer models and have been well studied for interpretability and pruning. In this work, we demonstrate an altogether different utility of attention heads, namely for adversarial detection.…

Imitation Learning (IL) is an appealing approach to learn desirable autonomous behavior. However, directing IL to achieve arbitrary goals is difficult. In contrast, planning-based algorithms use dynamics models and reward functions to…

Although the remarkable performance of deep neural networks (DNNs) in image classification, their vulnerability to adversarial attacks remains a critical challenge. Most existing detection methods rely on complex and poorly interpretable…

An end-to-end (E2E) ASR model implicitly learns a prior Internal Language Model (ILM) from the training transcripts. To fuse an external LM using Bayes posterior theory, the log likelihood produced by the ILM has to be accurately estimated…

Interpretation of a machine learning induced models is critical for feature engineering, debugging, and, arguably, compliance. Yet, best of breed machine learning models tend to be very complex. This paper presents a method for model…

Reinforcement learning provides a powerful and general framework for decision making and control, but its application in practice is often hindered by the need for extensive feature and reward engineering. Deep reinforcement learning…

As AI systems become increasingly autonomous, aligning their decision-making to human preferences is essential. In domains like autonomous driving or robotics, it is impossible to write down the reward function representing these…

Attention-based encoder-decoder (AED) models learn an implicit internal language model (ILM) from the training transcriptions. The integration with an external LM trained on much more unpaired text usually leads to better performance. A…

We show new connections between adversarial learning and explainability for deep neural networks (DNNs). One form of explanation of the output of a neural network model in terms of its input features, is a vector of feature-attributions.…

The rise of deep learning technique has raised new privacy concerns about the training data and test data. In this work, we investigate the model inversion problem in the adversarial settings, where the adversary aims at inferring…

While deep neural networks have shown impressive performance in many tasks, they are fragile to carefully designed adversarial attacks. We propose a novel adversarial training-based model by Attention Guided Knowledge Distillation and…

Recent attacks on Machine Learning (ML) models such as evasion attacks with adversarial examples and models stealing through extraction attacks pose several security and privacy threats. Prior work proposes to use adversarial training to…

Interpretable Machine Learning (IML) methods are used to gain insight into the relevance of a feature of interest for the performance of a model. Commonly used IML methods differ in whether they consider features of interest in isolation,…