English
Related papers

Related papers: ADDMU: Detection of Far-Boundary Adversarial Examp…

200 papers

Deep neural networks (DNNs) are vulnerable to adversarial examples that are carefully designed to cause the deep learning model to make mistakes. Adversarial examples of 2D images and 3D point clouds have been extensively studied, but…

Computer Vision and Pattern Recognition · Computer Science 2021-12-28 Wooju Lee , Hyun Myung

Deep neural networks (DNNs) are vulnerable to adversarial examples, which may lead to catastrophe in security-critical domains. Numerous detection methods are proposed to characterize the feature uniqueness of adversarial examples, or to…

Cryptography and Security · Computer Science 2023-04-03 Ruoxi Chen , Haibo Jin , Jinyin Chen , Haibin Zheng

Optimization-based adversarial suffixes can jailbreak aligned large language models (LLMs) while remaining fluent, weakening static and windowed perplexity-based detectors. We cast adversarial suffix detection as an online change-point…

Machine Learning · Computer Science 2026-05-20 Mohammed Alshaalan , Miguel R. D. Rodrigues

Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on…

Machine Learning · Computer Science 2019-11-19 Rey Reza Wiyatno , Anqi Xu , Ousmane Dia , Archy de Berker

Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect unseen attacks or detect different attack types with a high level of accuracy. In this…

Cryptography and Security · Computer Science 2025-10-06 Chinthana Wimalasuriya , Spyros Tragoudas

This paper studies the adversarial robustness of conformal novelty detection. In particular, we focus on two powerful learning-based frameworks that come with finite-sample false discovery rate (FDR) control: one is AdaDetect (by Marandon…

Machine Learning · Statistics 2026-04-03 Daofu Zhang , Mehrdad Pournaderi , Hanne M. Clifford , Yu Xiang , Pramod K. Varshney

Deep learning models, which are increasingly being used in the field of medical image analysis, come with a major security risk, namely, their vulnerability to adversarial examples. Adversarial examples are carefully crafted samples that…

Image and Video Processing · Electrical Eng. & Systems 2019-08-01 Utku Ozbulak , Arnout Van Messem , Wesley De Neve

Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by \emph{adversarial examples} that are generated by adding small but purposeful distortions to natural examples. Previous studies to…

Computer Vision and Pattern Recognition · Computer Science 2017-12-07 Weilin Xu , David Evans , Yanjun Qi

In recent years, deep learning has shown performance breakthroughs in many applications, such as image detection, image segmentation, pose estimation, and speech recognition. However, this comes with a major concern: deep networks have been…

Machine Learning · Computer Science 2019-01-11 Felix Kreuk , Assi Barak , Shir Aviv-Reuven , Moran Baruch , Benny Pinkas , Joseph Keshet

An adversarial attack paradigm explores various scenarios for the vulnerability of deep learning models: minor changes of the input can force a model failure. Most of the state of the art frameworks focus on adversarial attacks for images…

Machine Learning · Computer Science 2020-06-22 I. Fursov , A. Zaytsev , N. Kluchnikov , A. Kravchenko , E. Burnaev

Adversarial samples exploit irregularities in the manifold `learned' by deep learning models to cause misclassifications. The study of these adversarial samples provides insight into the features a model uses to classify inputs, which can…

Machine Learning · Computer Science 2026-03-04 Max Collins , Jordan Vice , Tim French , Ajmal Mian

Deep Neural Networks (DNNs) are well-known to be vulnerable to Adversarial Examples (AEs). A large amount of efforts have been spent to launch and heat the arms race between the attackers and defenders. Recently, advanced gradient-based…

Cryptography and Security · Computer Science 2020-05-29 Han Qiu , Yi Zeng , Qinkai Zheng , Tianwei Zhang , Meikang Qiu , Gerard Memmi

Despite the significant advances in deep learning over the past decade, a major challenge that limits the wide-spread adoption of deep learning has been their fragility to adversarial attacks. This sensitivity to making erroneous…

Machine Learning · Computer Science 2021-06-21 Hossein Aboutalebi , Mohammad Javad Shafiee , Michelle Karg , Christian Scharfenberger , Alexander Wong

This paper demonstrates that Non-Maximum Suppression (NMS), which is commonly used in Object Detection (OD) tasks to filter redundant detection results, is no longer secure. Considering that NMS has been an integral part of OD systems,…

Computer Vision and Pattern Recognition · Computer Science 2020-06-02 Derui Wang , Chaoran Li , Sheng Wen , Qing-Long Han , Surya Nepal , Xiangyu Zhang , Yang Xiang

Adversarial machine learning, i.e., increasing the robustness of machine learning algorithms against so-called adversarial examples, is now an established field. Yet, newly proposed methods are evaluated and compared under unrealistic…

Machine Learning · Computer Science 2021-09-28 Maximilian Samsinger , Florian Merkle , Pascal Schöttle , Tomas Pevny

Adversarial examples are vital to expose the vulnerability of machine learning models. Despite the success of the most popular substitution-based methods which substitutes some characters or words in the original examples, only substitution…

Computation and Language · Computer Science 2020-12-21 Zhihong Shao , Zitao Liu , Jiyong Zhang , Zhongqin Wu , Minlie Huang

Despite the efficiency and scalability of machine learning systems, recent studies have demonstrated that many classification methods, especially deep neural networks (DNNs), are vulnerable to adversarial examples; i.e., examples that are…

Cryptography and Security · Computer Science 2021-11-22 Yao Li , Minhao Cheng , Cho-Jui Hsieh , Thomas C. M. Lee

Evading adversarial example detection defenses requires finding adversarial examples that must simultaneously (a) be misclassified by the model and (b) be detected as non-adversarial. We find that existing attacks that attempt to satisfy…

Machine Learning · Computer Science 2021-06-30 Oliver Bryniarski , Nabeel Hingun , Pedro Pachuca , Vincent Wang , Nicholas Carlini

Adversarial attacks on machine learning algorithms have been a key deterrent to the adoption of AI in many real-world use cases. They significantly undermine the ability of high-performance neural networks by forcing misclassifications.…

Machine Learning · Computer Science 2024-04-04 Nandish Chattopadhyay , Atreya Goswami , Anupam Chattopadhyay

Adversarial detection protects models from adversarial attacks by refusing suspicious test samples. However, current detection methods often suffer from weak generalization: their effectiveness tends to degrade significantly when applied to…

Cryptography and Security · Computer Science 2025-06-05 Sicong Han , Chenhao Lin , Zhengyu Zhao , Xiyuan Wang , Xinlei He , Qian Li , Cong Wang , Qian Wang , Chao Shen