Results 161 to 170 of about 5,389,393 (319)
AI‐Driven Cancer Multi‐Omics: A Review From the Data Pipeline Perspective
Advanced Intelligent Discovery, EarlyView.The exponential growth of cancer multi‐omics data brings opportunities and challenges for precision oncology. This review systematically examines AI's role in addressing these challenges, covering generative models, integration architectures, Explainable AI for clinical trust, clinical applications, and key directions for clinical translation.
Shilong Liu, Shunxiang Li, Kun Qian
wiley +1 more source
Friend-Guard Textfooler Attack on Text Classification System
IEEE AccessDeep neural networks provide good performance for image classification, text classification, speech classification, and pattern analysis. However, such neural networks are vulnerable to adversarial examples.
Hyun Kwon
doaj +1 more source
Uncertainty‐Guided Selective Adaptation Enables Cross‐Platform Predictive Fluorescence Microscopy
Advanced Intelligent Discovery, EarlyView.Deep learning models often fail when transferred to new microscopes. A novel framework overcomes this by selectively adapting the early layers governing low‐level image statistics, while freezing deep layers that encode morphology. This uncertainty‐guided approach enables robust, label‐free virtual staining across diverse systems, democratizing ...
Kai‐Wen K. Yang +9 more
wiley +1 more source
Generating Watermarked Adversarial Texts
, 2021 Adversarial example generation has been a hot spot in recent years because it can cause deep neural networks (DNNs) to misclassify the generated adversarial examples, which reveals the vulnerability of DNNs, motivating us to find good solutions to ...
Wu, Hanzhou, Li, Mingjie, Zhang, Xinpeng
core
Advanced Intelligent Discovery, EarlyView.Materials informatics and autonomous experimentation are transforming the discovery of organic molecular crystals. This review presents an integrated molecule–crystal–function–optimization workflow combining machine learning, crystal structure prediction, and Bayesian optimization with robotic platforms.
Takuya Taniguchi +2 more
wiley +1 more source
Yoda: Comparison Evaluation of Adversarial Example Attacks
, 2021 최근 딥러닝 모델이 발전하면서 보안성 검증 평가에 대한 요구가 많아지고, 특히 적대적 예제(Adversarial Example) 생성 공격에 대한 연구가 증가하고 있다. 하지만, 많은 연구들이 독자적인 플랫폼에서 진행되고, 통합 환경이 부족한 상황이다. 따라서 우리는 이 논문에서 적대적 공격 통합 도구 프레임 워크인 Yoda를 제안한다.
송원호, 손수엘
core
Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.This article reviews the current state of bioinspired soft robotics. The article discusses soft actuators, soft sensors, materials selection, and control methods used in bioinspired soft robotics. It also highlights the challenges and future prospects of this field.
Abhirup Sarker +2 more
wiley +1 more source
A New Type of Adversarial Examples
CoRRMost machine learning models are vulnerable to adversarial examples, which poses security concerns on these models. Adversarial examples are crafted by applying subtle but intentionally worst-case modifications to examples from the dataset, leading the model to output a different answer from the original example. In this paper, adversarial examples are
Xingyang Nie +5 more
openaire +2 more sources
Explaining and Harnessing Adversarial Examples
, 2014 Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed input results in the model outputting an incorrect answer with high confidence.
Ian J. Goodfellow +2 more
openaire +2 more sources
Improving performance of adversarial example attack using model explanation
, 2022 학위논문(석사) -- 서울대학교대학원 : 공과대학 전기·정보공학부, 2022.2. 백윤흥 .본 논문은 악의적으로 AI 모델의 분류 결과를 바꾸기 위해 데이터를 변조하는 adversarial example 공격 방법을 제안한다. 제안된 방법 XAI-W는 AI 모델의 출력 결과의 입력 데이터의 어느 부분이 중점적으로 영향을 미쳤는지 해석할 수 있는 model explanation 기술을 사용하여, 입력 데이터 중 AI 모델의 출력에 큰 영향을 미친 부분에
전소희
core