no code implementations • 18 Nov 2023 • Tao Wang, Zijian Ying, Qianmu Li, Zhichao Lian
To address these challenges, we propose a framework called Uniform Scale and Mix Mask Method (US-MM) for adversarial example generation.
no code implementations • 15 May 2022 • Ruiqi Zha, Zhichao Lian, Qianmu Li, Siqi Gu
Essentially, the target of deepfake detection problem is to represent natural faces and fake faces at the representation space discriminatively, and it reminds us whether we could optimize the feature extraction procedure at the representation space through constraining intra-class consistence and inter-class inconsistence to bring the intra-class representations close and push the inter-class representations apart?
no code implementations • 2 May 2022 • Zijian Ying, Qianmu Li, Zhichao Lian, Jun Hou, Tong Lin, Tao Wang
To organize these excitations into final saliency maps, we introduce a double-chain backpropagation procedure.
1 code implementation • 20 Sep 2021 • Deqiang Li, Tian Qiu, Shuo Chen, Qianmu Li, Shouhuai Xu
Our main findings are: (i) predictive uncertainty indeed helps achieve reliable malware detection in the presence of dataset shift, but cannot cope with adversarial evasion attacks; (ii) approximate Bayesian methods are promising to calibrate and generalize malware detectors to deal with dataset shift, but cannot cope with adversarial evasion attacks; (iii) adversarial evasion attacks can render calibration methods useless, and it is an open problem to quantify the uncertainty associated with the predicted labels of adversarial examples (i. e., it is not effective to use predictive uncertainty to detect adversarial examples).
1 code implementation • 30 Jun 2020 • Deqiang Li, Qianmu Li
This motivates us to investigate which kind of robustness the ensemble defense or effectiveness the ensemble attack can achieve, particularly when they combat with each other.
no code implementations • 24 May 2020 • Deqiang Li, Qianmu Li, Yanfang Ye, Shouhuai Xu
In this paper, we survey and systematize the field of Adversarial Malware Detection (AMD) through the lens of a unified conceptual framework of assumptions, attacks, defenses, and security properties.
1 code implementation • 15 Apr 2020 • Deqiang Li, Qianmu Li, Yanfang Ye, Shouhuai Xu
By conducting experiments with the Drebin Android malware dataset, we show that the framework can achieve a 98. 49\% accuracy (on average) against grey-box attacks, where the attacker knows some information about the defense and the defender knows some information about the attack, and an 89. 14% accuracy (on average) against the more capable white-box attacks, where the attacker knows everything about the defense and the defender knows some information about the attack.
no code implementations • 26 Jan 2020 • Milad Taleby Ahvanooey, Qianmu Li
Age estimation is defined to label a facial image automatically with the age group (year range) or the exact age (year) of the person's face.
no code implementations • 1 Nov 2019 • Ziyuan Pu, Zhiyong Cui, Shuo Wang, Qianmu Li, Yinhai Wang
The findings can help improve the prediction accuracy and efficiency of forecasting road surface friction using historical data sets with missing values, therefore mitigating the impact of wet or icy road conditions on traffic safety.
1 code implementation • 19 Dec 2018 • Deqiang Li, Qianmu Li, Yanfang Ye, Shouhuai Xu
However, machine learning is known to be vulnerable to adversarial evasion attacks that manipulate a small number of features to make classifiers wrongly recognize a malware sample as a benign one.
Cryptography and Security 68-06
no code implementations • 18 Sep 2018 • Deqiang Li, Ramesh Baral, Tao Li, Han Wang, Qianmu Li, Shouhuai Xu
Adversarial machine learning in the context of image processing and related applications has received a large amount of attention.