Jiayu Zhang

Zhibo Jin, Zhiyu Zhu, Xinyi Wang et al.

While deep neural networks have excellent results in many fields, they are susceptible to interference from attacking samples resulting in erroneous judgments. Feature-level attacks are one of the effective attack types, which targets the learnt features in the hidden layers to improve its transferability across different models. Yet it is observed that the transferability has been largely impacted by the neuron importance estimation results. In this paper, a double adversarial neuron attribution attack method, termed `DANAA', is proposed to obtain more accurate feature importance estimation. In our method, the model outputs are attributed to the middle layer based on an adversarial non-linear path. The goal is to measure the weight of individual neurons and retain the features that are more important towards transferability. We have conducted extensive experiments on the benchmark datasets to demonstrate the state-of-the-art performance of our method. Our code is available at: https://github.com/Davidjinzb/DANAA

Zhiyu Zhu, Jiayu Zhang, Zhibo Jin et al.

Attribution algorithms are essential for enhancing the interpretability and trustworthiness of deep learning models by identifying key features driving model decisions. Existing frameworks, such as InterpretDL and OmniXAI, integrate multiple attribution methods but suffer from scalability limitations, high coupling, theoretical constraints, and lack of user-friendly implementations, hindering neural network transparency and interoperability. To address these challenges, we propose Attribution-Based Explainability (ABE), a unified framework that formalizes Fundamental Attribution Methods and integrates state-of-the-art attribution algorithms while ensuring compliance with attribution axioms. ABE enables researchers to develop novel attribution techniques and enhances interpretability through four customizable modules: Robustness, Interpretability, Validation, and Data & Model. This framework provides a scalable, extensible foundation for advancing attribution-based explainability and fostering transparent AI systems. Our code is available at: https://github.com/LMBTough/ABE-XAI.

Jiayu Zhang, Zhiyu Zhu, Xinyi Wang et al.

Deep neural networks have demonstrated remarkable performance across various domains. However, they are vulnerable to adversarial examples, which can lead to erroneous predictions. Generative Adversarial Networks (GANs) can leverage the generators and discriminators model to quickly produce high-quality adversarial examples. Since both modules train in a competitive and simultaneous manner, GAN-based algorithms like AdvGAN can generate adversarial examples with better transferability compared to traditional methods. However, the generation of perturbations is usually limited to a single iteration, preventing these examples from fully exploiting the potential of the methods. To tackle this issue, we introduce a novel approach named Progressive Auto-Regression AdvGAN (PAR-AdvGAN). It incorporates an auto-regressive iteration mechanism within a progressive generation network to craft adversarial examples with enhanced attack capability. We thoroughly evaluate our PAR-AdvGAN method with a large-scale experiment, demonstrating its superior performance over various state-of-the-art black-box adversarial attacks, as well as the original AdvGAN.Moreover, PAR-AdvGAN significantly accelerates the adversarial example generation, i.e., achieving the speeds of up to 335.5 frames per second on Inception-v3 model, outperforming the gradient-based transferable attack algorithms. Our code is available at: https://github.com/LMBTough/PAR

Zhiyu Zhu, Jiayu Zhang, Zhibo Jin et al.

The interpretability of deep neural networks is crucial for understanding model decisions in various applications, including computer vision. AttEXplore++, an advanced framework built upon AttEXplore, enhances attribution by incorporating transferable adversarial attack methods such as MIG and GRA, significantly improving the accuracy and robustness of model explanations. We conduct extensive experiments on five models, including CNNs (Inception-v3, ResNet-50, VGG16) and vision transformers (MaxViT-T, ViT-B/16), using the ImageNet dataset. Our method achieves an average performance improvement of 7.57\% over AttEXplore and 32.62\% compared to other state-of-the-art interpretability algorithms. Using insertion and deletion scores as evaluation metrics, we show that adversarial transferability plays a vital role in enhancing attribution results. Furthermore, we explore the impact of randomness, perturbation rate, noise amplitude, and diversity probability on attribution performance, demonstrating that AttEXplore++ provides more stable and reliable explanations across various models. We release our code at: https://anonymous.4open.science/r/ATTEXPLOREP-8435/

Jiayu Zhang

In the quantum computation verification problem, a quantum server wants to convince a client that the output of evaluating a quantum circuit $C$ is some result that it claims. This problem is considered very important both theoretically and practically in quantum computation [arXiv:1709.06984], [arXiv:1704.04487], [arXiv:1209.0449]. The client is considered to be limited in computational power, and one desirable property is that the client can be completely classical, which leads to the classical verification of quantum computation (CVQC) problem. In terms of the total time complexity, the fastest single-server CVQC protocol so far has complexity $O(poly(κ)|C|^3)$ where $|C|$ is the size of the circuit to be verified and $κ$ is the security parameter, given by Mahadev [arXiv:1804.01082]. In this work, by developing new techniques, we give a new CVQC protocol with complexity $O(poly(κ)|C|)$, which is significantly faster than existing protocols. Our protocol is secure in the quantum random oracle model [arXiv:1008.0931] assuming the existence of noisy trapdoor claw-free functions [arXiv:1804.00640], which are both extensively used assumptions in quantum cryptography. Along the way, we also give a new classical channel remote state preparation protocol for states in $\{|+_θ\rangle=\frac{1}{\sqrt{2}}(|0\rangle+e^{iθπ/4}|1\rangle):θ\in \{0,1\cdots 7\}\}$, another basic primitive in quantum cryptography. Our protocol allows for parallel verifiable preparation of $L$ independently random states in this form (up to a constant overall error and a possibly unbounded server-side simulator), and runs in only $O(poly(κ)L)$ time and constant rounds; for comparison, existing works (even for possibly simpler state families) all require very large or unestimated time and round complexities [arXiv:1904.06320][arXiv:1904.06303][arXiv:2201.13445][arXiv:2201.13430].

Jiayu Zhang

In the universal blind quantum computation problem, a client wants to make use of a single quantum server to evaluate $C|0\rangle$ where $C$ is an arbitrary quantum circuit while keeping $C$ secret. The client's goal is to use as few resources as possible. This problem, with a representative protocol by Broadbent, Fitzsimons and Kashefi [FOCS09, arXiv:0807.4154], has become fundamental to the study of quantum cryptography, not only because of its own importance, but also because it provides a testbed for new techniques that can be later applied to related problems (for example, quantum computation verification). Known protocols on this problem are mainly either information-theoretically (IT) secure or based on trapdoor assumptions (public key encryptions). In this paper we study how the availability of symmetric-key primitives, modeled by a random oracle, changes the complexity of universal blind quantum computation. We give a new universal blind quantum computation protocol. Similar to previous works on IT-secure protocols (for example, BFK [FOCS09, arXiv:0807.4154]), our protocol can be divided into two phases. In the first phase the client prepares some quantum gadgets with relatively simple quantum gates and sends them to the server, and in the second phase the client is entirely classical -- it does not even need quantum storage. Crucially, the protocol's first phase is succinct, that is, its complexity is independent of the circuit size. Given the security parameter $κ$, its complexity is only a fixed polynomial of $κ$, and can be used to evaluate any circuit (or several circuits) of size up to a subexponential of $κ$. In contrast, known schemes either require the client to perform quantum computations that scale with the size of the circuit [FOCS09, arXiv:0807.4154], or require trapdoor assumptions [Mahadev, FOCS18, arXiv:1708.02130].