18 November 2022 in Science
The mixtures of cations and anions used in hybrid halide perovskites for high-performance solar cells often undergo element and phase segregation, which limits device lifetime. We adapted Schelling’s model of segregation to study individual cation migration and found that the initial film inhomogeneity accelerates materials degradation. We fabricated perovskite films (FA
1–x
Cs
x
PbI 3 ; where FA is formamidinium) through the addition of selenophene, which led to homogeneous cation distribution that retarded cation aggregation during materials processing and device operation. The resultant devices achieved enhanced efficiency and retained >91% of their initial efficiency after 3190 hours at the maximum power point under 1 sun illumination. We also observe prolonged operational lifetime in devices with initially homogeneous FACsPb(Br 0.13 I 0.87 ) 3 absorbers.
7 September 2022 in Pattern Recognition
28 June 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
The privacy and security of face data on social media are facing unprecedented challenges as it is vulnerable to unauthorized access and identification. A common practice for solving this problem is to modify the original data so that it could be protected from being recognized by malicious face recognition (FR) systems. However, such “adversarial examples” obtained by existing methods usually suffer from low transferability and poor image quality, which severely limits the application of these methods in real-world scenarios. In this paper, we propose a 3D-Aware Adversarial Makeup Generation GAN (3DAM-GAN). which aims to improve the quality and transferability of synthetic makeup for identity information concealing. Specifically, a UV-based generator consisting of a novel Makeup Adjustment Module (MAM) and Makeup Transfer Module (MTM) is designed to render realistic and robust makeup with the aid of symmetric characteristics of human faces. Moreover, a makeup attack mechanism with an ensemble training strategy is proposed to boost the transferability of black-box models. Extensive experiment results on several benchmark datasets demonstrate that 3DAM-GAN could effectively protect faces against various FR models, including both publicly available state-of-the-art models and commercial face verification APIs, such as Face++, Baidu and Aliyun.
12 July 2024 in IEEE Transactions on Circuits and Systems for Video Technology
Recently, the asymmetric cost-based steganographic method using generative adversarial networks has achieved significant success. This highlights the substantial potential of deep learning-based asymmetric cost generation methods over traditional methods reliant on cost enhancement. However, the current frameworks for asymmetric cost learning ignore the correlation between positive and negative embedding costs, resulting in an imbalance asymmetric embedding costs. This can cause scattered modified pixels or even anomalous modified pixels in the stego image, thereby reducing steganographic security. In this paper, we propose a novel asymmetric steganographic cost learning framework, termed Steganographic embedding Cost Generation and Modulation (SCGM), to ensure a balance between asymmetric embedding costs by maintaining the correlation and therefore improve steganographic security. In our framework, we initially train a policy network to produce symmetric costs and subsequently use an adaptive modulation module we designed to achieve asymmetry. The modulation module facilitates the adaptive transformation of learned symmetric costs into asymmetric costs by autonomously learning modulation proportions during adversarial training with steganalysis. Moreover, we develop distinct adversarial loss functions for both the symmetric cost generation and the asymmetric cost modulation phases to further enhance steganographic security. Extensive experimental results have demonstrated that SCGM attains state-of-the-art performance in steganographic security, with an average error rate across steganalyzers that exceeds the existing best asymmetric cost-based steganography method by 2.77%.
29 May 2025 in IEEE Transactions on Information Forensics and Security
With the rapid development of image generation technologies, especially the advancement of Diffusion Models, the quality of synthesized images has significantly improved, raising concerns among researchers about information security. To mitigate the malicious abuse of diffusion models, diffusion-generated image detection has proven to be an effective countermeasure. However, a key challenge for forgery detection is generalising to diffusion models not seen during training. In this paper, we address this problem by focusing on image noise. We observe that images from different diffusion models share similar noise patterns, distinct from genuine images. Building upon this insight, we introduce a novel Noise-Aware Self-Attention (NASA) module that focuses on noise regions to capture anomalous patterns. To implement a SOTA detection model, we incorporate NASA into Swin Transformer, forming an novel detection architecture NASA-Swin. Additionally, we employ a cross-modality fusion embedding to combine RGB and noise images, along with a channel mask strategy to enhance feature learning from both modalities. Extensive experiments demonstrate the effectiveness of our approach in enhancing detection capabilities for diffusion-generated images. When encountering unseen generation methods, our approach achieves the state-of-the-art performance.