Filters








6 Hits in 2.3 sec

Poisoning Online Learning Filters: DDoS Attacks and Countermeasures [article]

Wesley Joon-Wie Tann, Ee-Chien Chang
2022 arXiv   pre-print
In one of the most recent online deep learning filtering methods presented in Tann et al.  ...  Tann et al. [29] presented one of the only approaches that employ powerful online deep learning models, which does not use data labels for training.  ... 
arXiv:2107.12612v2 fatcat:yutkbircdngylajkjerbblltne

Mitigating Adversarial Attacks by Distributing Different Copies to Different Users [article]

Jiyi Zhang, Wesley Joon-Wie Tann, Ee-Chien Chang
2022 arXiv   pre-print
Machine learning models are vulnerable to adversarial attacks. In this paper, we consider the scenario where a model is to be distributed to many users, among which a malicious user attempts to attack another user. The malicious user probes its unique copy of the model to search for adversarial samples, presenting found samples to the victim's model in order to replicate the attack. By distributing different copies of the model to different users, we can mitigate such attacks wherein
more » ... samples found on one copy would not work on another copy. We propose a flexible parameter rewriting method that directly modifies the model's parameters. This method does not require training and is able to generate a large number of copies, where each copy induces different sets of adversarial samples. Experimentation studies show that our approach can significantly mitigate the attacks while retaining high accuracy.
arXiv:2111.15160v2 fatcat:cxz5mzgkojddbkzc5mbzm27v7y

SHADOWCAST: Controllable Graph Generation [article]

Wesley Joon-Wie Tann, Ee-Chien Chang, Bryan Hooi
2021 arXiv   pre-print
Correspondence to: Wesley Tann <wesleyj-tann@u.nus.edu>.  ... 
arXiv:2006.03774v4 fatcat:55xir2qiofgm7f3rvbo7rupvj4

Towards Safer Smart Contracts: A Sequence Learning Approach to Detecting Security Threats [article]

Wesley Joon-Wie Tann, Xing Jie Han, Sourav Sen Gupta, Yew-Soon Ong
2019 arXiv   pre-print
Symbolic analysis of security exploits in smart contracts has demonstrated to be valuable for analyzing predefined vulnerability properties. While some symbolic tools perform complex analysis steps, they require a predetermined invocation depth to search vulnerable execution paths, and the search time increases with depth. The number of contracts on blockchains like Ethereum has increased 176 fold since December 2015. If these symbolic tools fail to analyze the increasingly large number of
more » ... acts in time, entire classes of exploits could cause irrevocable damage. In this paper, we aim to have safer smart contracts against emerging threats. We propose the approach of sequential learning of smart contract weaknesses using machine learning—long-short term memory (LSTM)—that allows us to be able to detect new attack trends relatively quickly, leading to safer smart contracts. Our experimental studies on 620,000 smart contracts prove that our model can easily scale to analyze a massive amount of contracts; that is, the LSTM maintains near constant analysis time as contracts increase in complexity. In addition, our approach achieves 99% test accuracy and correctly analyzes contracts that were false positive (FP) errors made by a symbolic tool.
arXiv:1811.06632v3 fatcat:4zs2m5uprvcsbmjbvyn7f3bbx4

Quantum Remote Entanglement for Medium-Free Secure Communication? [article]

Wesley Joon-Wie Tann
2022
Qubit |𝝍⟩ Measurement bit (𝐵) Results (%) |0⟩ 0 91.1 1 8.9 |1⟩ 0 5.6 1 94.4 Conference '22, November 2022, Wesley Joon-Wie Tann  ... 
doi:10.48550/arxiv.2202.00830 fatcat:dd5e6iaavjb33nxwjmwpj4ms6y

Multi-Class classification of vulnerabilities in Smart Contracts using AWD-LSTM, with pre-trained encoder inspired from natural language processing [article]

Ajay K. Gogineni, S. Swayamjyoti, Devadatta Sahoo, Kisor K. Sahu, Raj kishore
2020 arXiv   pre-print
Acknowledgement We thank Sourav Sen Gupta, Wesley Joon-Wie Tann, Xing Jie Han and, Yew-Soon Ong for sharing the preprocessed SC data with us, which was used for this study.  ...  METHODS Data pre-processing The SC data that is analyzed in this article is obtained from the Tann et al. work [25] .  ...  Tann et al. [25] used a standard LSTM model [34, 35] , where the embeddings are initialized randomly at the beginning of training and are updated during training.  ... 
arXiv:2004.00362v1 fatcat:umuq6qxzmzc3xhtccuwdbky7be