Results 21 to 30 of about 7,756 (262)
CoRR, 2022 Recent advances in machine learning show that neural models are vulnerable to minimally perturbed inputs, or adversarial examples. Adversarial algorithms are optimization problems that minimize the accuracy of ML models by perturbing inputs, often using a model's loss function to craft such perturbations.
Thomas Cilloni +2 more
openaire +2 more sources
CoRR, 2021 Adversarial attacks expose important vulnerabilities of deep learning models, yet little attention has been paid to settings where data arrives as a stream. In this paper, we formalize the online adversarial attack problem, emphasizing two key elements found in real-world use-cases: attackers must operate under partial knowledge of the target model ...
Andjela Mladenovic +6 more
openaire +3 more sources
Deflecting Adversarial Attacks
CoRR, 2020 There has been an ongoing cycle where stronger defenses against adversarial attacks are subsequently broken by a more advanced defense-aware attack. We present a new approach towards ending this cycle where we "deflect'' adversarial attacks by causing the attacker to produce an input that semantically resembles the attack's target class.
Yao Qin 0001 +4 more
openaire +2 more sources
Augmented Lagrangian Adversarial Attacks [PDF]
2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 ICCV 2021 (Poster).
Jérôme Rony +3 more
openaire +2 more sources
Meta Gradient Adversarial Attack [PDF]
2021 IEEE/CVF International Conference on Computer Vision (ICCV), 2021 In recent years, research on adversarial attacks has become a hot spot. Although current literature on the transfer-based adversarial attack has achieved promising results for improving the transferability to unseen black-box models, it still leaves a long way to go. Inspired by the idea of meta-learning, this paper proposes a novel architecture called
Zheng Yuan 0005 +5 more
openaire +2 more sources
Textual Adversarial Training Method Based on Distributed Perturbation [PDF]
Jisuanji gongcheng, 2023 Text adversarial defense aims to enhance the resilience of neural network models against different adversarial attacks. The current text confrontation defense methods are usually only effective against certain specific confrontation attacks and have ...
Zhidong SHEN, Hengxian YUE
doaj +1 more source
IEEE Access, 2022 The internet-of-Vehicle (IoV) can facilitate seamless connectivity between connected vehicles (CV), autonomous vehicles (AV), and other IoV entities. Intrusion Detection Systems (IDSs) for IoV networks can rely on machine learning (ML) to protect the in ...
Ibrahim Aliyu +4 more
doaj +1 more source
Detection of Adversarial Attacks and Characterization of Adversarial Subspace [PDF]
ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020 Adversarial attacks have always been a serious threat for any data-driven model. In this paper, we explore subspaces of adversarial examples in unitary vector domain, and we propose a novel detector for defending our models trained for environmental sound classification.
Mohammad Esmaeilpour +2 more
openaire +2 more sources
Probabilistic Categorical Adversarial Attack & Adversarial Training
CoRR, 2022 The existence of adversarial examples brings huge concern for people to apply Deep Neural Networks (DNNs) in safety-critical tasks. However, how to generate adversarial examples with categorical data is an important problem but lack of extensive exploration.
Xu, Han +6 more
openaire +2 more sources