Rethinking Label Flipping Attack: From Sample Masking to Sample Thresholding.

Nowadays, machine learning (ML) and deep learning (DL) methods have become fundamental building blocks for a wide range of AI applications. The popularity of these methods also makes them widely exposed to malicious attacks, which may cause severe security concerns. To understand the security properties of the ML/DL methods, researchers have recently started to turn their focus to adversarial attack algorithms that could successfully corrupt the model or clean data owned by the victim with imperceptible perturbations. In this paper, we study the Label Flipping Attack (LFA) problem, where the attacker expects to corrupt an ML/DL model's performance by flipping a small fraction of the labels in the training data. Prior art along this direction adopts combinatorial optimization problems, leading to limited scalability toward deep learning models. To this end, we propose a novel minimax problem which provides an efficient reformulation of the sample selection process in LFA. In the new optimization problem, the sample selection operation could be implemented with a single thresholding parameter. This leads to a novel training algorithm called Sample Thresholding. Since the objective function is differentiable and the model complexity does not depend on the sample size, we can apply Sample Thresholding to attack deep learning models. Moreover, since the victim's behavior is not predictable in a poisonous attack setting, we have to employ surrogate models to simulate the true model employed by the victim model. Seeing the problem, we provide a theoretical analysis of such a surrogate paradigm. Specifically, we show that the performance gap between the true model employed by the victim and the surrogate model is small under mild conditions. On top of this paradigm, we extend Sample Thresholding to the crowdsourced ranking task, where labels collected from the annotators are vulnerable to adversarial attacks. Finally, experimental analyses on three real-world datasets speak to the efficacy of our method.

Positive-Unlabeled Learning With Label Distribution Alignment.

Positive-Unlabeled (PU) data arise frequently in a wide range of fields such as medical diagnosis, anomaly analysis and personalized advertising. The absence of any known negative labels makes it very challenging to learn binary classifiers from such data. Many state-of-the-art methods reformulate the original classification risk with individual risks over positive and unlabeled data, and explicitly minimize the risk of classifying unlabeled data as negative. This, however, usually leads to classifiers with a bias toward negative predictions, i.e., they tend to recognize most unlabeled data as negative. In this paper, we propose a label distribution alignment formulation for PU learning to alleviate this issue. Specifically, we align the distribution of predicted labels with the ground-truth, which is constant for a given class prior. In this way, the proportion of samples predicted as negative is explicitly controlled from a global perspective, and thus the bias toward negative predictions could be intrinsically eliminated. On top of this, we further introduce the idea of functional margins to enhance the model's discriminability, and derive a margin-based learning framework named Positive-Unlabeled learning with Label Distribution Alignment (PULDA). This framework is also combined with the class prior estimation process for practical scenarios, and theoretically supported by a generalization analysis. Moreover, a stochastic mini-batch optimization algorithm based on the exponential moving average strategy is tailored for this problem with a convergence guarantee. Finally, comprehensive empirical results demonstrate the effectiveness of the proposed method.

Synergy of Au-Pt for Enhancing Ethylene Photodegradation Performance of Flower-like TiO2.

Efficient and low-cost degradation of ethylene has always been a difficult problem in the storage and transportation of fruits and vegetables. Although photocatalysis is considered to be a feasible and efficient solution for ethylene degradation, the low degradation ability of conventional catalysts for small non-polar molecules limits its application. TiO2 has the advantage of tunable microstructure, but it also has the defects of wide band gap and low utilization of sunlight. The surface plasmon resonance (SPR) effect of noble metals can effectively improve the visible light absorption range of catalysts, and the synergy of noble metals further enhances the photocatalytic ability. Herein, we developed a series of AuPt catalysts through the photo-deposition method. Benefited from the SPR effect and the synergy of Au and Pt, the efficiency of AuPt-TiO2 was 19.9, 4.64 and 2.42 times that of TiO2, Au-TiO2 and Pt-TiO2, and the photocatalytic degradation ability of AuPt-TiO2 was maintained in five cyclic stability tests. Meanwhile, the transient photocurrent spectra and PL spectra proved that the light absorption capacity and carrier separation efficiency of AuPt-TiO2 were enhanced. This work provides a new direction for enhancing non-polar small-molecule photodegradation of semiconductors.