English
Related papers

Related papers: White-Box Multi-Objective Adversarial Attack on Di…

200 papers

Due to their complex nature, it is hard to characterize the ways in which machine learning models can misbehave or be exploited when deployed. Recent work on adversarial examples, i.e. inputs with minor perturbations that result in…

Machine Learning · Computer Science 2018-02-27 Zhengli Zhao , Dheeru Dua , Sameer Singh

Deep learning-based object detection has become ubiquitous in the last decade due to its high accuracy in many real-world applications. With this growing trend, these models are interested in being attacked by adversaries, with most of the…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Pham Phuc , Son Vuong , Khang Nguyen , Tuan Dang

Deep Neural Networks (DNNs) have been widely employed across various domains, including safety-critical systems, necessitating comprehensive testing to ensure their reliability. Although numerous DNN model testing methods have been proposed…

Machine Learning · Computer Science 2025-03-25 Bin Duan , Matthew B. Dwyer , Guowei Yang

Adversarial attacks, wherein slight inputs are carefully crafted to mislead intelligent models, have attracted increasing attention. However, a critical gap persists between theoretical advancements and practical application, particularly…

Cryptography and Security · Computer Science 2025-06-26 Sabrine Ennaji , Elhadj Benkhelifa , Luigi V. Mancini

Machine learning (ML) models, e.g., deep neural networks (DNNs), are vulnerable to adversarial examples: malicious inputs modified to yield erroneous model outputs, while appearing unmodified to human observers. Potential attacks include…

Cryptography and Security · Computer Science 2017-03-21 Nicolas Papernot , Patrick McDaniel , Ian Goodfellow , Somesh Jha , Z. Berkay Celik , Ananthram Swami

Because "out-of-the-box" large language models are capable of generating a great deal of objectionable content, recent work has focused on aligning these models in an attempt to prevent undesirable generation. While there has been some…

Computation and Language · Computer Science 2023-12-22 Andy Zou , Zifan Wang , Nicholas Carlini , Milad Nasr , J. Zico Kolter , Matt Fredrikson

Recent work has shown it is possible to construct adversarial examples that cause an aligned language model to emit harmful strings or perform harmful behavior. Existing attacks work either in the white-box setting (with full access to the…

Computation and Language · Computer Science 2024-12-10 Jonathan Hayase , Ema Borevkovic , Nicholas Carlini , Florian Tramèr , Milad Nasr

Fooling deep neural networks (DNNs) with the black-box optimization has become a popular adversarial attack fashion, as the structural prior knowledge of DNNs is always unknown. Nevertheless, recent black-box adversarial attacks may…

Computer Vision and Pattern Recognition · Computer Science 2022-01-14 Jie Wang , Zhaoxia Yin , Jing Jiang , Yang Du

Deep learning (DL), despite its enormous success in many computer vision and language processing applications, is exceedingly vulnerable to adversarial attacks. We consider the use of DL for radio signal (modulation) classification tasks,…

Information Theory · Computer Science 2018-08-24 Meysam Sadeghi , Erik G. Larsson

Deep neural networks have been shown to be vulnerable to small perturbations of their inputs, known as adversarial attacks. In this paper, we investigate the vulnerability of Neural Machine Translation (NMT) models to adversarial attacks…

Computation and Language · Computer Science 2023-06-19 Sahar Sadrizadeh , Ljiljana Dolamic , Pascal Frossard

With the development of high computational devices, deep neural networks (DNNs), in recent years, have gained significant popularity in many Artificial Intelligence (AI) applications. However, previous efforts have shown that DNNs were…

Computation and Language · Computer Science 2019-04-12 Wei Emma Zhang , Quan Z. Sheng , Ahoud Alhazmi , Chenliang Li

Deep neural networks are vulnerable to adversarial examples that mislead models with imperceptible perturbations. In audio, although adversarial examples have achieved incredible attack success rates on white-box settings and black-box…

Sound · Computer Science 2022-10-13 Deng JiaCheng , Dong Li , Yan Diqun , Wang Rangding , Zeng Jiaming

Deep neural networks have been widely used in various downstream tasks, especially those safety-critical scenario such as autonomous driving, but deep networks are often threatened by adversarial samples. Such adversarial attacks can be…

Computer Vision and Pattern Recognition · Computer Science 2023-08-16 Yutong Zhang , Yao Li , Yin Li , Zhichang Guo

Recent advances in Multimodal Large Language Models (MLLMs) have significantly enhanced the naturalness and flexibility of human computer interaction by enabling seamless understanding across text, vision, and audio modalities. Among these,…

Computation and Language · Computer Science 2025-05-27 Binhao Ma , Hanqing Guo , Zhengping Jay Luo , Rui Duan

We demonstrate substantial performance gains in zero-shot dialogue state tracking (DST) by enhancing training data diversity through synthetic data generation. Existing DST datasets are severely limited in the number of application domains…

Computation and Language · Computer Science 2024-06-14 James D. Finch , Jinho D. Choi

Adversarial attacks on deep neural networks traditionally rely on a constrained optimization paradigm, where an optimization procedure is used to obtain a single adversarial perturbation for a given input example. In this work we frame the…

Machine Learning · Computer Science 2020-01-22 Avishek Joey Bose , Andre Cianflone , William L. Hamilton

Adversarial attack algorithms are dominated by penalty methods, which are slow in practice, or more efficient distance-customized methods, which are heavily tailored to the properties of the distance considered. We propose a white-box…

Machine Learning · Computer Science 2021-08-20 Jérôme Rony , Eric Granger , Marco Pedersoli , Ismail Ben Ayed

We present a method for adversarial input generation against black box models for reading comprehension based question answering. Our approach is composed of two steps. First, we approximate a victim black box model via model extraction…

Machine Learning · Computer Science 2020-11-03 Naveen Jafer Nizar , Ari Kobren

Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input. This is natural given the increasing applications of deep neural networks…

Computer Vision and Pattern Recognition · Computer Science 2021-01-13 Hanwei Zhang , Yannis Avrithis , Teddy Furon , Laurent Amsaleg

Machine learning models are vulnerable to Adversarial Examples: minor perturbations to input samples intended to deliberately cause misclassification. Current defenses against adversarial examples, especially for Deep Neural Networks (DNN),…

Cryptography and Security · Computer Science 2019-01-04 Kathrin Grosse , David Pfaff , Michael Thomas Smith , Michael Backes