相关论文: Human Aligned Compression for Robust Models

Lossless image compression is an essential research field in image compression. Recently, learning-based image compression methods achieved impressive performance compared with traditional lossless methods, such as WebP, JPEG2000, and FLIF.…

In this work, we investigate the phenomenon that robust image classifiers have human-recognizable features -- often referred to as interpretability -- as revealed through the input gradients of their score functions and their subsequent…

State-of-the-art defense mechanisms are typically evaluated in the context of white-box attacks, which is not realistic, as it assumes the attacker can access the gradients of the target network. To protect against this scenario,…

In this paper, we propose a new key-based defense focusing on both efficiency and robustness. Although the previous key-based defense seems effective in defending against adversarial examples, carefully designed adaptive attacks can bypass…

Adversarial attacks present a significant security risk to image recognition tasks. Defending against these attacks in a real-life setting can be compared to the way antivirus software works, with a key consideration being how well the…

Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. This is perhaps the main reason why CNNs are vulnerable to adversarial examples. Here, we…

Preprocessing defenses such as pixel discretization are appealing to remove adversarial attacks due to their simplicity. However, they have been shown to be ineffective except on simple datasets like MNIST. We hypothesize that existing…

Deep neural networks have become the driving force of modern image recognition systems. However, the vulnerability of neural networks against adversarial attacks poses a serious threat to the people affected by these systems. In this paper,…

Adversarial attacks pose a critical security threat to real-world AI systems by injecting human-imperceptible perturbations into benign samples to induce misclassification in deep learning models. While existing detection methods, such as…

Autoencoder-based image codecs achieve state-of-the-art compression performance but often incur high computational complexity, particularly at decoding time. This work introduces a low-complexity learned image compression framework based on…

Lossless image compression is an important technique for image storage and transmission when information loss is not allowed. With the fast development of deep learning techniques, deep neural networks have been used in this field to…

Large text-to-image models have achieved astonishing performance in synthesizing diverse and high-quality images guided by texts. With detail-oriented conditioning control, even finer-grained spatial control can be achieved. However, some…

Adversarial attacks pose significant threats to deploying state-of-the-art classifiers in safety-critical applications. Two classes of methods have emerged to address this issue: empirical defences and certified defences. Although certified…

Deep learning-based discriminative classifiers, despite their remarkable success, remain vulnerable to adversarial examples that can mislead model predictions. While adversarial training can enhance robustness, it fails to address the…

Adversarial attacks significantly challenge the safe deployment of deep learning models, particularly in real-world applications. Traditional defenses often rely on computationally intensive optimization (e.g., adversarial training or data…

Model-based compression is an effective, facilitating, and expanded model of neural network models with limited computing and low power. However, conventional models of compression techniques utilize crafted features [2,3,12] and explore…

Deep Learning has been shown to be particularly vulnerable to adversarial samples. To combat adversarial strategies, numerous defensive techniques have been proposed. Among these, a promising approach is to use randomness in order to make…

In recent years, many forensic detectors have been proposed to detect AI-generated images and prevent their use for malicious purposes. Convolutional neural networks (CNNs) have long been the dominant architecture in this field and have…

Mammalian brains handle complex reasoning tasks in a gestalt manner by integrating information from regions of the brain that are specialised to individual sensory modalities. This allows for improved robustness and better generalisation…

Deep neural networks are vulnerable to so-called adversarial examples: inputs which are intentionally constructed to cause the model to make incorrect predictions or classifications. Adversarial examples are often visually indistinguishable…