English
Related papers

Related papers: Fluently Lying: Adversarial Robustness Can Be Subs…

200 papers

Despite many proposed algorithms to provide robustness to deep learning (DL) models, DL models remain susceptible to adversarial attacks. We hypothesize that the adversarial vulnerability of DL models stems from two factors. The first…

Artificial Intelligence · Computer Science 2022-02-21 Mahsa Paknezhad , Cuong Phuc Ngo , Amadeus Aristo Winarto , Alistair Cheong , Chuen Yang Beh , Jiayang Wu , Hwee Kuan Lee

Localized adversarial patches aim to induce misclassification in machine learning models by arbitrarily modifying pixels within a restricted region of an image. Such attacks can be realized in the physical world by attaching the adversarial…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Chong Xiang , Arjun Nitin Bhagoji , Vikash Sehwag , Prateek Mittal

Machine learning models have demonstrated vulnerability to adversarial attacks, more specifically misclassification of adversarial examples. In this paper, we propose a one-off and attack-agnostic Feature Manipulation (FM)-Defense to detect…

Machine Learning · Computer Science 2020-04-23 Shuo Wang , Tianle Chen , Surya Nepal , Carsten Rudolph , Marthie Grobler , Shangyu Chen

Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data. Although there has been remarkable recent progress, the scope of demonstration in SSL has mainly been on…

Computer Vision and Pattern Recognition · Computer Science 2020-12-04 Kihyuk Sohn , Zizhao Zhang , Chun-Liang Li , Han Zhang , Chen-Yu Lee , Tomas Pfister

Detecting out-of-distribution (OOD) inputs is critical for safely deploying deep learning models in real-world scenarios. In recent years, many OOD detectors have been developed, and even the benchmarking has been standardized, i.e.…

Cryptography and Security · Computer Science 2025-01-30 Peter Lorenz , Mario Fernandez , Jens Müller , Ullrich Köthe

Our research aims to unify existing works' diverging opinions on how architectural components affect the adversarial robustness of CNNs. To accomplish our goal, we synthesize a suite of three generalizable robust architectural design…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 ShengYun Peng , Weilin Xu , Cory Cornelius , Matthew Hull , Kevin Li , Rahul Duggal , Mansi Phute , Jason Martin , Duen Horng Chau

When instructed to underperform on multiple-choice evaluations, do language models engage with question content or fall back on positional shortcuts? We map the boundary between these regimes using a six-condition adversarial…

Computation and Language · Computer Science 2026-05-01 Jon-Paul Cacioli

Deep learning methods have shown state of the art performance in a range of tasks from computer vision to natural language processing. However, it is well known that such systems are vulnerable to attackers who craft inputs in order to…

Machine Learning · Computer Science 2020-09-29 Giulio Zizzo , Chris Hankin , Sergio Maffeis , Kevin Jones

Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a…

Machine Learning · Computer Science 2019-06-11 Puyudi Yang , Jianbo Chen , Cho-Jui Hsieh , Jane-Ling Wang , Michael I. Jordan

Many Machine Learning models are vulnerable to adversarial attacks: There exist methodologies that add a small (imperceptible) perturbation to an input such that the model comes up with a wrong prediction. Better understanding of such…

Cryptography and Security · Computer Science 2023-06-13 Paul Stahlhofen , André Artelt , Luca Hermes , Barbara Hammer

An adversary can fool deep neural network object detectors by generating adversarial noises. Most of the existing works focus on learning local visible noises in an adversarial "patch" fashion. However, the 2D patch attached to a 3D object…

Computer Vision and Pattern Recognition · Computer Science 2022-05-17 Yexin Duan , Jialin Chen , Xingyu Zhou , Junhua Zou , Zhengyun He , Jin Zhang , Wu Zhang , Zhisong Pan

Deep neural networks remain vulnerable to adversarial examples despite advances in architectures and training paradigms. We investigate how training data characteristics affect adversarial robustness across 36 state-of-the-art vision models…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Marco Zimmerli , Andreas Plesner , Till Aczel , Roger Wattenhofer

To combat adversarial spelling mistakes, we propose placing a word recognition model in front of the downstream classifier. Our word recognition models build upon the RNN semi-character architecture, introducing several new backoff…

Computation and Language · Computer Science 2019-08-30 Danish Pruthi , Bhuwan Dhingra , Zachary C. Lipton

We study the extent to which standard machine learning algorithms rely on exchangeability and independence of data by introducing a monotone adversarial corruption model. In this model, an adversary, upon looking at a "clean" i.i.d.…

Machine Learning · Computer Science 2026-01-06 Kasper Green Larsen , Chirag Pabbaraju , Abhishek Shetty

Carefully crafted, often imperceptible, adversarial perturbations have been shown to cause state-of-the-art models to yield extremely inaccurate outputs, rendering them unsuitable for safety-critical application domains. In addition, recent…

Computer Vision and Pattern Recognition · Computer Science 2019-06-04 Yash Sharma , Gavin Weiguang Ding , Marcus Brubaker

Stochastic neural networks (SNNs) are random functions whose predictions are gained by averaging over multiple realizations. Consequently, a gradient-based adversarial example is calculated based on one set of samples and its classification…

Machine Learning · Computer Science 2023-03-07 Sina Däubener , Asja Fischer

Reliable evaluation of adversarial defenses is a challenging task, currently limited to an expert who manually crafts attacks that exploit the defense's inner workings or approaches based on an ensemble of fixed attacks, none of which may…

Machine Learning · Computer Science 2021-10-28 Chengyuan Yao , Pavol Bielik , Petar Tsankov , Martin Vechev

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees on network robustness. Small perturbations to sensor inputs…

Machine Learning · Computer Science 2022-02-03 Michael Everett , Bjorn Lutjens , Jonathan P. How

Deep neural networks for classification are vulnerable to adversarial attacks, where small perturbations to input samples lead to incorrect predictions. This susceptibility, combined with the black-box nature of such networks, limits their…

Cryptography and Security · Computer Science 2024-08-28 Dipkamal Bhusal , Md Tanvirul Alam , Monish K. Veerabhadran , Michael Clifford , Sara Rampazzi , Nidhi Rastogi

By leveraging the principles of quantum mechanics, QML opens doors to novel approaches in machine learning and offers potential speedup. However, machine learning models are well-documented to be vulnerable to malicious manipulations, and…

Machine Learning · Computer Science 2024-11-12 Bacui Li , Tansu Alpcan , Chandra Thapa , Udaya Parampalli