Related papers: Boosting Adversarial Transferability through Enhan…
The convolutional neural network is the crucial tool for the recent success of deep learning based methods on various computer vision tasks like classification, segmentation, and detection. Convolutional neural networks achieved…
Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However,…
Although the adoption rate of deep neural networks (DNNs) has tremendously increased in recent years, a solution for their vulnerability against adversarial examples has not yet been found. As a result, substantial research efforts are…
Attacking Neural Machine Translation models is an inherently combinatorial task on discrete sequences, solved with approximate heuristics. Most methods use the gradient to attack the model on each sample independently. Instead of…
While deep neural networks have proven to be a powerful tool for many recognition and classification tasks, their stability properties are still not well understood. In the past, image classifiers have been shown to be vulnerable to…
The vulnerability of deep neural networks to adversarial examples has drawn tremendous attention from the community. Three approaches, optimizing standard objective functions, exploiting attention maps, and smoothing decision surfaces, are…
While the untargeted black-box transferability of adversarial perturbations has been extensively studied before, changing an unseen model's decisions to a specific `targeted' class remains a challenging feat. In this paper, we propose a new…
The integration of an ensemble of deep learning models has been extensively explored to enhance defense against adversarial attacks. The diversity among sub-models increases the attack cost required to deceive the majority of the ensemble,…
Adversarial transferability in black-box scenarios presents a unique challenge: while attackers can employ surrogate models to craft adversarial examples, they lack assurance on whether these examples will successfully compromise the target…
Design of adversarial attacks for deep neural networks, as well as methods of adversarial training against them, are subject of intense research. In this paper, we propose methods to train against distributional attack threats, extending…
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…
To help adversarial examples generalize from surrogate machine-learning (ML) models to targets, certain transferability-based black-box evasion attacks incorporate data augmentations (e.g., random resizing). Yet, prior work has explored…
Neural networks are vulnerable to adversarial examples, malicious inputs crafted to fool trained models. Adversarial examples often exhibit black-box transfer, meaning that adversarial examples for one model can fool another model. However,…
Recent studies have shown that Deep Neural Networks (DNNs) are susceptible to adversarial attacks, with frequency-domain analysis underscoring the significance of high-frequency components in influencing model predictions. Conversely,…
Adversarial face examples possess two critical properties: Visual Quality and Transferability. However, existing approaches rarely address these properties simultaneously, leading to subpar results. To address this issue, we propose a novel…
Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ…
Deep learning models are vulnerable to adversarial examples, which poses an indisputable threat to their applications. However, recent studies observe gradient-masking defenses are self-deceiving methods if an attacker can realize this…
Ensemble-based attacks have been proven to be effective in enhancing adversarial transferability by aggregating the outputs of models with various architectures. However, existing research primarily focuses on refining ensemble weights or…
This paper substantially extends our work published at ECCV, in which an intermediate-level attack was proposed to improve the transferability of some baseline adversarial examples. Specifically, we advocate a framework in which a direct…
Recent development of adversarial attacks has proven that ensemble-based methods outperform traditional, non-ensemble ones in black-box attack. However, as it is computationally prohibitive to acquire a family of diverse models, these…