English
Related papers

Related papers: AI Safety in Practice: Enhancing Adversarial Robus…

200 papers

Deep learning achieves state-of-the-art performance in many tasks but exposes to the underlying vulnerability against adversarial examples. Across existing defense techniques, adversarial training with the projected gradient decent attack…

Cryptography and Security · Computer Science 2022-10-04 Tianjin Huang , Vlado Menkovski , Yulong Pei , Mykola Pechenizkiy

Adversarial training is an effective method to boost model robustness to malicious, adversarial attacks. However, such improvement in model robustness often leads to a significant sacrifice of standard performance on clean images. In many…

Machine Learning · Computer Science 2022-04-29 Pengyue Hou , Ming Zhou , Jie Han , Petr Musilek , Xingyu Li

As deep learning applications, especially programs of computer vision, are increasingly deployed in our lives, we have to think more urgently about the security of these applications.One effective way to improve the security of deep…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Xiao Tan , Jingbo Gao , Ruolin Li

In federated learning for medical image analysis, the safety of the learning protocol is paramount. Such settings can often be compromised by adversaries that target either the private data used by the federation or the integrity of the…

Machine Learning · Computer Science 2022-08-09 Dmitrii Usynin , Helena Klause , Johannes C. Paetzold , Daniel Rueckert , Georgios Kaissis

The convergence of cross-modal adversarial learning and physics-driven methods represents a cutting-edge direction for tackling challenges in complex multi-modal tasks and scientific computing. This review focuses on systematically…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Hana Satou , Alan Mitkiy

As Machine Learning (ML) is increasingly used in solving various tasks in real-world applications, it is crucial to ensure that ML algorithms are robust to any potential worst-case noises, adversarial attacks, and highly unusual situations…

Machine Learning · Computer Science 2023-09-25 Long Dang , Thushari Hapuarachchi , Kaiqi Xiong , Jing Lin

Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world contexts, the essential specifics of the deployed model are…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Jingwen Ye , Ruonan Yu , Songhua Liu , Xinchao Wang

Federated learning offers a privacy-preserving framework for medical image analysis but exposes the system to adversarial attacks. This paper aims to evaluate the vulnerabilities of federated learning networks in medical image analysis…

Cryptography and Security · Computer Science 2023-10-11 Erfan Darzi , Florian Dubost , N. M. Sijtsema , P. M. A van Ooijen

Deep neural networks are vulnerable to adversarial examples, which becomes one of the most important research problems in the development of deep learning. While a lot of efforts have been made in recent years, it is of great significance…

Computer Vision and Pattern Recognition · Computer Science 2019-12-30 Yinpeng Dong , Qi-An Fu , Xiao Yang , Tianyu Pang , Hang Su , Zihao Xiao , Jun Zhu

Are frontier AI systems becoming more capable? Certainly. Yet such progress is not an unalloyed blessing but rather a Trojan horse: behind their performance leaps lie more insidious and destructive safety risks, namely deception. Unlike…

Artificial Intelligence · Computer Science 2026-05-28 Sitong Fang , Shiyi Hou , Kaile Wang , Boyuan Chen , Donghai Hong , Jiayi Zhou , Josef Dai , Yaodong Yang , Jiaming Ji

Multimodal Large Language Models (MLLMs) have achieved remarkable success in tasks such as image captioning, visual question answering, and cross-modal reasoning by integrating visual and textual modalities. However, their multimodal nature…

Computer Vision and Pattern Recognition · Computer Science 2025-10-14 Fengling Zhu , Boshi Liu , Jingyu Hua , Sheng Zhong

Machine learning (ML) models are increasingly deployed in cybersecurity applications such as phishing detection and network intrusion prevention. However, these models remain vulnerable to adversarial perturbations small, deliberate input…

Cryptography and Security · Computer Science 2026-02-09 Mona Rajhans , Vishal Khawarey

While significant progress has been made in the image captioning task, video description is still in its infancy due to the complex nature of video data. Generating multi-sentence descriptions for long videos is even more challenging. Among…

Computer Vision and Pattern Recognition · Computer Science 2019-04-17 Jae Sung Park , Marcus Rohrbach , Trevor Darrell , Anna Rohrbach

We identify fragile and robust neurons of deep learning architectures using nodal dropouts of the first convolutional layer. Using an adversarial targeting algorithm, we correlate these neurons with the distribution of adversarial attacks…

Machine Learning · Computer Science 2022-02-01 Chandresh Pravin , Ivan Martino , Giuseppe Nicosia , Varun Ojha

In recent years, deep neural networks have demonstrated outstanding performance in many machine learning tasks. However, researchers have discovered that these state-of-the-art models are vulnerable to adversarial examples: legitimate…

Machine Learning · Computer Science 2018-10-10 Ting-Jui Chang , Yukun He , Peng Li

Modern self-driving perception systems have been shown to improve upon processing complementary inputs such as LiDAR with images. In isolation, 2D images have been found to be extremely vulnerable to adversarial attacks. Yet, there have…

Computer Vision and Pattern Recognition · Computer Science 2022-01-10 James Tu , Huichen Li , Xinchen Yan , Mengye Ren , Yun Chen , Ming Liang , Eilyan Bitar , Ersin Yumer , Raquel Urtasun

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

Machine Learning · Computer Science 2019-11-12 Bai Li , Changyou Chen , Wenlin Wang , Lawrence Carin

Adversarial examples cause neural networks to produce incorrect outputs with high confidence. Although adversarial training is one of the most effective forms of defense against adversarial examples, unfortunately, a large gap exists…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Saehyung Lee , Hyungyu Lee , Sungroh Yoon

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with…

As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…

Machine Learning · Computer Science 2020-07-07 Samuel Henrique Silva , Peyman Najafirad