Results 11 to 20 of about 503,159 (305)
Attack Tree Analysis for Adversarial Evasion Attacks [PDF]
2023 IEEE 28th Pacific Rim International Symposium on Dependable Computing (PRDC), 2023 10 ...
Yuki Yamaguchi, Toshiaki Aoki
openaire +4 more sources
Attackability Characterization of Adversarial Evasion Attack on Discrete Data [PDF]
Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020 Evasion attack on discrete data is a challenging, while practically interesting research topic. It is intrinsically an NP-hard combinatorial optimization problem. Characterizing the conditions guaranteeing the solvability of an evasion attack task thus becomes the key to understand the adversarial threat. Our study is inspired by the weak submodularity
Yutong Wang +6 more
openaire +3 more sources
Malware Evasion Attack and Defense [PDF]
2019 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W), 2019 Machine learning (ML) classifiers are vulnerable to adversarial examples. An adversarial example is an input sample which is slightly modified to induce misclassification in an ML classifier. In this work, we investigate white-box and grey-box evasion attacks to an ML-based malware detector and conduct performance evaluations in a real-world setting ...
Yonghong Huang +5 more
openaire +3 more sources
Universal Evasion Attacks on Summarization Scoring
Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, 2022 The automatic scoring of summaries is important as it guides the development of summarizers. Scoring is also complex, as it involves multiple aspects such as fluency, grammar, and even textual entailment with the source text. However, summary scoring has not been considered a machine learning task to study its accuracy and robustness. In this study, we
Wenchuan Mu, Kwan Hui Lim 0001
openaire +4 more sources
Projective Ranking-based GNN Evasion Attacks
IEEE Transactions on Knowledge and Data Engineering, 2022 Graph neural networks (GNNs) offer promising learning methods for graph-related tasks. However, GNNs are at risk of adversarial attacks. Two primary limitations of the current evasion attack methods are highlighted: (1) The current GradArgmax ignores the "long-term" benefit of the perturbation.
He Zhang 0012 +3 more
openaire +4 more sources
Malware Collusion Attack against SVM: Issues and Countermeasures
Applied Sciences, 2018 Android has become the most popular mobile platform, and a hot target for malware developers. At the same time, researchers have come up with numerous ways to deal with malware.
Hongyi Chen +3 more
doaj +1 more source
Research on game strategy of underwater attack and defense process in typical situation
Xibei Gongye Daxue Xuebao, 2023 Aiming at the problem of underwater attack and defense in typical situations, a mathematical model of three-party attack and defense problem composed of torpedo, submarines and anti-torpedo torpedo is established. Under the condition of considering three-
WANG Zhong +3 more
doaj +1 more source
OMG-Attack: Self-Supervised On-Manifold Generation of Transferable Evasion Attacks
2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), 2023 ICCV 2023, AROW ...
Ofir Bar Tal, Adi Haviv, Amit H. Bermano
openaire +2 more sources
On the Feasibility of Adversarial Sample Creation Using the Android System API
Information, 2020 Due to its popularity, the Android operating system is a critical target for malware attacks. Multiple security efforts have been made on the design of malware detection systems to identify potentially harmful applications.
Fabrizio Cara +3 more
doaj +1 more source
Dual-Targeted Textfooler Attack on Text Classification Systems
IEEE Access, 2023 Deep neural networks provide good performance on classification tasks such as those for image, audio, and text classification. However, such neural networks are vulnerable to adversarial examples.
Hyun Kwon
doaj +1 more source