Results 91 to 100 of about 14,798 (256)

MedRDF: A Robust and Retrain-Less Diagnostic Framework for Medical Pretrained Models Against Adversarial Attack [PDF]

, 2021
Mengting Xu, Tao Zhang, Daoqiang Zhang
openalex   +1 more source

Self‐Driving Microscopes: AI Meets Super‐Resolution Microscopy

Small Methods, EarlyView.
This review examines the use of machine learning to automate super‐resolution optical microscopy, enabling the microscope to autonomously make decisions on what, when, and how to image. By eliminating the need for human intervention, this approach has the potential to enhance the versatility and accessibility of super‐resolution microscopy.
Edward N. Ward, Anna Scheeder, Max Barysevich, Clemens F. Kaminski   +3 more
wiley   +1 more source

Certified Accuracy and Robustness: How different architectures stand up to adversarial attacks

Intelligent Systems with Applications
Adversarial attacks are a concern for image classification using neural networks. Numerous methods have been created to minimize the effects of attacks, where the best defense against such attacks is through adversarial training, which has proven to be ...
Azryl Elmy Sarih, Nagender Aneja, Ong Wee Hong   +2 more
doaj   +1 more source

Generative AI for Requirements Engineering: A Systematic Literature Review

Software: Practice and Experience, EarlyView.
ABSTRACT Introduction Requirements engineering (RE) faces challenges due to the handling of increasingly complex software systems. These challenges can be addressed using generative artificial intelligence (GenAI). Given that GenAI‐based RE has not been systematically analyzed in detail, this review examines the related research, focusing on trends ...
Haowei Cheng, Jati H. Husen, Yijun Lu, Teeradaj Racharak, Nobukazu Yoshioka, Naoyasu Ubayashi, Hironori Washizaki   +6 more
wiley   +1 more source

Towards Transferable Targeted 3D Adversarial Attack in the Physical World [PDF]

, 2023
Yao Huang, Yinpeng Dong, Shouwei Ruan, Yang Xiao, Hang Su, Xingxing Wei   +5 more
openalex   +1 more source

Fail‐Controlled Classifiers: A Swiss‐Army Knife Toward Trustworthy Systems

Software: Practice and Experience, EarlyView.
ABSTRACT Background Modern critical systems often require to take decisions and classify data and scenarios autonomously without having detrimental effects on people, infrastructures or the environment, ensuring desired dependability attributes. Researchers typically strive to craft classifiers with perfect accuracy, which should be always correct and ...
Fahad Ahmed Khokhar, Tommaso Zoppi, Andrea Ceccarelli, Leonardo Montecchi, Andrea Bondavalli   +4 more
wiley   +1 more source

Adversarial Attacks on Medical Image Classification. [PDF]

Cancers (Basel), 2023
Tsai MJ, Lin PY, Lee ME.
europepmc   +1 more source

Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis [PDF]

, 2022
Yi Chang, Zhao Ren, Thành Tâm Nguyên, Wolfgang Nejdl, Björn W. Schuller   +4 more
openalex   +1 more source

Multiscale analysis of oxidative damage in hair fibers: From AFM nanomechanics to AI‐based degradation modeling

VIEW, EarlyView.
We investigated oxidative damage in human hair fibers using SEM and AFM‐based nanomechanical mapping, revealing progressive cuticle degradation and localized mechanical softening. cGAN was employed to model time‐dependent degradation, offering a predictive framework for assessing chemical damage in soft biomaterials.
Seungwon Choi, Jaehoon Sah, Sooyeon Ra, Chanuk Yang, Jae‐Hyun Lee, Taegeun Song, Myunglae Jo, Hyung Kook Choi, Sangmin An   +8 more
wiley   +1 more source

Investigating the Transferability of TOG Adversarial Attacks in YOLO Models in the Maritime Domain

IEEE Access
In recent years, CNN-based object detectors have been widely adopted in autonomous systems. Although their capabilities are employed across various industries, these detectors are inherently susceptible to adversarial attacks.
Phornphawit Manasut, Md Saleh Ibtasham, Zeynep Yaradanakul, Sepinoud Azimi, Sebastien Lafond, Bogdan Iancu   +5 more
doaj   +1 more source