Xiaojin Zhang

Yan Kang, Jiahuan Luo, Yuanqin He et al.

Federated learning (FL) has emerged as a practical solution to tackle data silo issues without compromising user privacy. One of its variants, vertical federated learning (VFL), has recently gained increasing attention as the VFL matches the enterprises' demands of leveraging more valuable features to build better machine learning models while preserving user privacy. Current works in VFL concentrate on developing a specific protection or attack mechanism for a particular VFL algorithm. In this work, we propose an evaluation framework that formulates the privacy-utility evaluation problem. We then use this framework as a guide to comprehensively evaluate a broad range of protection mechanisms against most of the state-of-the-art privacy attacks for three widely deployed VFL algorithms. These evaluations may help FL practitioners select appropriate protection mechanisms given specific requirements. Our evaluation results demonstrate that: the model inversion and most of the label inference attacks can be thwarted by existing protection mechanisms; the model completion (MC) attack is difficult to be prevented, which calls for more advanced MC-targeted protection mechanisms. Based on our evaluation results, we offer concrete advice on improving the privacy-preserving capability of VFL systems. The code is available at https://github.com/yankang18/Attack-Defense-VFL

Xiaojin Zhang, Yan Kang, Kai Chen et al.

Federated learning (FL) enables participating parties to collaboratively build a global model with boosted utility without disclosing private data information. Appropriate protection mechanisms have to be adopted to fulfill the opposing requirements in preserving \textit{privacy} and maintaining high model \textit{utility}. In addition, it is a mandate for a federated learning system to achieve high \textit{efficiency} in order to enable large-scale model training and deployment. We propose a unified federated learning framework that reconciles horizontal and vertical federated learning. Based on this framework, we formulate and quantify the trade-offs between privacy leakage, utility loss, and efficiency reduction, which leads us to the No-Free-Lunch (NFL) theorem for the federated learning system. NFL indicates that it is unrealistic to expect an FL algorithm to simultaneously provide excellent privacy, utility, and efficiency in certain scenarios. We then analyze the lower bounds for the privacy leakage, utility loss and efficiency reduction for several widely-adopted protection mechanisms including \textit{Randomization}, \textit{Homomorphic Encryption}, \textit{Secret Sharing} and \textit{Compression}. Our analysis could serve as a guide for selecting protection parameters to meet particular requirements.

Xiaojin Zhang, Hanlin Gu, Lixin Fan et al.

In a federated learning scenario where multiple parties jointly learn a model from their respective data, there exist two conflicting goals for the choice of appropriate algorithms. On one hand, private and sensitive training data must be kept secure as much as possible in the presence of \textit{semi-honest} partners, while on the other hand, a certain amount of information has to be exchanged among different parties for the sake of learning utility. Such a challenge calls for the privacy-preserving federated learning solution, which maximizes the utility of the learned model and maintains a provable privacy guarantee of participating parties' private data. This article illustrates a general framework that a) formulates the trade-off between privacy loss and utility loss from a unified information-theoretic point of view, and b) delineates quantitative bounds of privacy-utility trade-off when different protection mechanisms including Randomization, Sparsity, and Homomorphic Encryption are used. It was shown that in general \textit{there is no free lunch for the privacy-utility trade-off} and one has to trade the preserving of privacy with a certain degree of degraded utility. The quantitative analysis illustrated in this article may serve as the guidance for the design of practical federated learning algorithms.

Haoran Li, Yulin Chen, Jinglong Luo et al.

The advancement of large language models (LLMs) has significantly enhanced the ability to effectively tackle various downstream NLP tasks and unify these tasks into generative pipelines. On the one hand, powerful language models, trained on massive textual data, have brought unparalleled accessibility and usability for both models and users. On the other hand, unrestricted access to these models can also introduce potential malicious and unintentional privacy risks. Despite ongoing efforts to address the safety and privacy concerns associated with LLMs, the problem remains unresolved. In this paper, we provide a comprehensive analysis of the current privacy attacks targeting LLMs and categorize them according to the adversary's assumed capabilities to shed light on the potential vulnerabilities present in LLMs. Then, we present a detailed overview of prominent defense strategies that have been developed to counter these privacy attacks. Beyond existing works, we identify upcoming privacy concerns as LLMs evolve. Lastly, we point out several potential avenues for future exploration.

Kangkang Sun, Xiaojin Zhang, Xi Lin et al.

Federated Learning (FL) is a novel privacy-protection distributed machine learning paradigm that guarantees user privacy and prevents the risk of data leakage due to the advantage of the client's local training. Researchers have struggled to design fair FL systems that ensure fairness of results. However, the interplay between fairness and privacy has been less studied. Increasing the fairness of FL systems can have an impact on user privacy, while an increase in user privacy can affect fairness. In this work, on the client side, we use fairness metrics, such as Demographic Parity (DemP), Equalized Odds (EOs), and Disparate Impact (DI), to construct the local fair model. To protect the privacy of the client model, we propose a privacy-protection fairness FL method. The results show that the accuracy of the fair model with privacy increases because privacy breaks the constraints of the fairness metrics. In our experiments, we conclude the relationship between privacy, fairness and utility, and there is a tradeoff between these.

Xiaojin Zhang, Lixin Fan, Siwei Wang et al.

In federated learning, benign participants aim to optimize a global model collaboratively. However, the risk of \textit{privacy leakage} cannot be ignored in the presence of \textit{semi-honest} adversaries. Existing research has focused either on designing protection mechanisms or on inventing attacking mechanisms. While the battle between defenders and attackers seems never-ending, we are concerned with one critical question: is it possible to prevent potential attacks in advance? To address this, we propose the first game-theoretic framework that considers both FL defenders and attackers in terms of their respective payoffs, which include computational costs, FL model utilities, and privacy leakage risks. We name this game the federated learning privacy game (FLPG), in which neither defenders nor attackers are aware of all participants' payoffs. To handle the \textit{incomplete information} inherent in this situation, we propose associating the FLPG with an \textit{oracle} that has two primary responsibilities. First, the oracle provides lower and upper bounds of the payoffs for the players. Second, the oracle acts as a correlation device, privately providing suggested actions to each player. With this novel framework, we analyze the optimal strategies of defenders and attackers. Furthermore, we derive and demonstrate conditions under which the attacker, as a rational decision-maker, should always follow the oracle's suggestion \textit{not to attack}.

Xiaojin Zhang, Anbu Huang, Lixin Fan et al.

Federated learning (FL) is a new distributed learning paradigm, with privacy, utility, and efficiency as its primary pillars. Existing research indicates that it is unlikely to simultaneously attain infinitesimal privacy leakage, utility loss, and efficiency. Therefore, how to find an optimal trade-off solution is the key consideration when designing the FL algorithm. One common way is to cast the trade-off problem as a multi-objective optimization problem, i.e., the goal is to minimize the utility loss and efficiency reduction while constraining the privacy leakage not exceeding a predefined value. However, existing multi-objective optimization frameworks are very time-consuming, and do not guarantee the existence of the Pareto frontier, this motivates us to seek a solution to transform the multi-objective problem into a single-objective problem because it is more efficient and easier to be solved. To this end, we propose FedPAC, a unified framework that leverages PAC learning to quantify multiple objectives in terms of sample complexity, such quantification allows us to constrain the solution space of multiple objectives to a shared dimension, so that it can be solved with the help of a single-objective optimization algorithm. Specifically, we provide the results and detailed analyses of how to quantify the utility loss, privacy leakage, privacy-utility-efficiency trade-off, as well as the cost of the attacker from the PAC learning perspective.

Yu Liu, Lang Gao, Mingxin Yang et al.

Large Language Models (LLMs) have training corpora containing large amounts of program code, greatly improving the model's code comprehension and generation capabilities. However, sound comprehensive research on detecting program vulnerabilities, a more specific task related to code, and evaluating the performance of LLMs in this more specialized scenario is still lacking. To address common challenges in vulnerability analysis, our study introduces a new benchmark, VulDetectBench, specifically designed to assess the vulnerability detection capabilities of LLMs. The benchmark comprehensively evaluates LLM's ability to identify, classify, and locate vulnerabilities through five tasks of increasing difficulty. We evaluate the performance of 17 models (both open- and closed-source) and find that while existing models can achieve over 80% accuracy on tasks related to vulnerability identification and classification, they still fall short on specific, more detailed vulnerability analysis tasks, with less than 30% accuracy, making it difficult to provide valuable auxiliary information for professional vulnerability mining. Our benchmark effectively evaluates the capabilities of various LLMs at different levels in the specific task of vulnerability detection, providing a foundation for future research and improvements in this critical area of code security. VulDetectBench is publicly available at https://github.com/Sweetaroo/VulDetectBench.

Xiaojin Zhang, Mingcong Xu, Wei Chen

In this paper, we first give an introduction to the theoretical basis of the privacy-utility equilibrium in federated learning based on Bayesian privacy definitions and total variation distance privacy definitions. We then present the \textit{Learn-to-Distort-Data} framework, which provides a principled approach to navigate the privacy-utility equilibrium by explicitly modeling the distortion introduced by the privacy-preserving mechanism as a learnable variable and optimizing it jointly with the model parameters. We demonstrate the applicability of our framework to a variety of privacy-preserving mechanisms on the basis of data distortion and highlight its connections to related areas such as adversarial training, input robustness, and unlearnable examples. These connections enable leveraging techniques from these areas to design effective algorithms for privacy-utility equilibrium in federated learning under the \textit{Learn-to-Distort-Data} framework.

Wei Chen, Hengxu Lin, Qun Zhang et al.

Emotional Support Conversation aims at reducing the seeker's emotional distress through supportive response. Existing approaches have two limitations: (1) They ignore the emotion causes of the distress, which is important for fine-grained emotion understanding; (2) They focus on the seeker's own mental state rather than the emotional dynamics during interaction between speakers. To address these issues, we propose a novel framework CauESC, which firstly recognizes the emotion causes of the distress, as well as the emotion effects triggered by the causes, and then understands each strategy of verbal grooming independently and integrates them skillfully. Experimental results on the benchmark dataset demonstrate the effectiveness of our approach and show the benefits of emotion understanding from cause to effect and independent-integrated strategy modeling.

Xiaojin Zhang, Wei Chen

The widespread adoption of machine learning necessitates robust privacy protection alongside algorithmic resilience. While Local Differential Privacy (LDP) provides foundational guarantees, sophisticated adversaries with prior knowledge demand more nuanced Bayesian privacy notions, such as Maximum Bayesian Privacy (MBP) and Average Bayesian Privacy (ABP), first introduced by \cite{zhang2022no}. Concurrently, machine learning systems require inherent robustness against data perturbations and adversarial manipulations. This paper systematically investigates the intricate theoretical relationships among LDP, MBP, and ABP. Crucially, we bridge these privacy concepts with algorithmic robustness, particularly within the Probably Approximately Correct (PAC) learning framework. Our work demonstrates that privacy-preserving mechanisms inherently confer PAC robustness. We present key theoretical results, including the formalization of the established LDP-MBP relationship, novel bounds between MBP and ABP, and a proof demonstrating PAC robustness from MBP. Furthermore, we establish a novel theoretical relationship quantifying how privacy leakage directly influences an algorithm's input robustness. These results provide a unified theoretical framework for understanding and optimizing the privacy-robustness trade-off, paving the way for the development of more secure, trustworthy, and resilient machine learning systems.

Zhi Yin, Xiaoran Li, Shengyu Zhang et al.

Given the inherent limitations of traditional Variational Quantum Eigensolver(VQE) algorithms, the integration of deep generative models into hybrid quantum-classical frameworks, specifically the Generative Quantum Eigensolver(GQE), represents a promising innovative approach. However, taking the Unitary Coupled Cluster with Singles and Doubles(UCCSD) ansatz which is widely used in quantum chemistry as an example, different molecular systems require constructions of distinct quantum operators. Considering the similarity of different molecules, the construction of quantum operators utilizing the similarity can reduce the computational cost significantly. Inspired by the SMILES representation method in computational chemistry, we developed a text-based representation approach for UCCSD quantum operators by leveraging the inherent representational similarities between different molecular systems. This framework explores text pattern similarities in quantum operators and employs text similarity metrics to establish a transfer learning framework. Our approach with a naive baseline setting demonstrates knowledge transfer between different molecular systems for ground-state energy calculations within the GQE paradigm. This discovery offers significant benefits for hybrid quantum-classical computation of molecular ground-state energies, substantially reducing computational resource requirements.

Xiaojin Zhang, Mingcong Xu, Yiming Li et al.

Federated learning (FL) offers a promising paradigm for collaborative model training while preserving data privacy. However, its susceptibility to gradient inversion attacks poses a significant challenge, necessitating robust privacy protection mechanisms. This paper introduces a novel theoretical framework to decipher the intricate interplay between attack and protection complexities in privacy-preserving FL. We formally define "Attack Complexity" as the minimum computational and data resources an adversary requires to reconstruct private data below a given error threshold, and "Protection Complexity" as the expected distortion introduced by privacy mechanisms. Leveraging Maximum Bayesian Privacy (MBP), we derive tight theoretical bounds for protection complexity, demonstrating its scaling with model dimensionality and privacy budget. Furthermore, we establish comprehensive bounds for attack complexity, revealing its dependence on privacy leakage, gradient distortion, model dimension, and the chosen privacy level. Our findings quantitatively illuminate the fundamental trade-offs between privacy guarantees, system utility, and the effort required for both attacking and defending. This framework provides critical insights for designing more secure and efficient federated learning systems.

Xiaojin Zhang, Yan Kang, Lixin Fan et al.

Trustworthy Federated Learning (TFL) typically leverages protection mechanisms to guarantee privacy. However, protection mechanisms inevitably introduce utility loss or efficiency reduction while protecting data privacy. Therefore, protection mechanisms and their parameters should be carefully chosen to strike an optimal tradeoff between \textit{privacy leakage}, \textit{utility loss}, and \textit{efficiency reduction}. To this end, federated learning practitioners need tools to measure the three factors and optimize the tradeoff between them to choose the protection mechanism that is most appropriate to the application at hand. Motivated by this requirement, we propose a framework that (1) formulates TFL as a problem of finding a protection mechanism to optimize the tradeoff between privacy leakage, utility loss, and efficiency reduction and (2) formally defines bounded measurements of the three factors. We then propose a meta-learning algorithm to approximate this optimization problem and find optimal protection parameters for representative protection mechanisms, including Randomization, Homomorphic Encryption, Secret Sharing, and Compression. We further design estimation algorithms to quantify these found optimal protection parameters in a practical horizontal federated learning setting and provide a theoretical analysis of the estimation error.

Xiaojin Zhang, Wenjie Li, Kai Chen et al.

We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility. The algorithm is applicable to arbitrary privacy measurements that maps from the distortion to a real value. It can achieve personalized utility-privacy trade-off for each model parameter, on each client, at each communication round in federated learning. Such adaptive and fine-grained protection can improve the effectiveness of privacy-preserved federated learning. Theoretically, we show that gap between the utility loss of the protection hyperparameter output by our algorithm and that of the optimal protection hyperparameter is sub-linear in the total number of iterations. The sublinearity of our algorithm indicates that the average gap between the performance of our algorithm and that of the optimal performance goes to zero when the number of iterations goes to infinity. Further, we provide the convergence rate of our proposed algorithm. We conduct empirical results on benchmark datasets to verify that our method achieves better utility than the baseline methods under the same privacy budget.

Xiaojin Zhang, Kai Chen, Qiang Yang

Federated learning (FL) enables participating parties to collaboratively build a global model with boosted utility without disclosing private data information. Appropriate protection mechanisms have to be adopted to fulfill the requirements in preserving \textit{privacy} and maintaining high model \textit{utility}. The nature of the widely-adopted protection mechanisms including \textit{Randomization Mechanism} and \textit{Compression Mechanism} is to protect privacy via distorting model parameter. We measure the utility via the gap between the original model parameter and the distorted model parameter. We want to identify under what general conditions privacy-preserving federated learning can achieve near-optimal utility via data generation and parameter distortion. To provide an avenue for achieving near-optimal utility, we present an upper bound for utility loss, which is measured using two main terms called variance-reduction and model parameter discrepancy separately. Our analysis inspires the design of appropriate protection parameters for the protection mechanisms to achieve near-optimal utility and meet the privacy requirements simultaneously. The main techniques for the protection mechanism include parameter distortion and data generation, which are generic and can be applied extensively. Furthermore, we provide an upper bound for the trade-off between privacy and utility, \blue{which together with the lower bound provided by no free lunch theorem in federated learning (\cite{zhang2022no}) form the conditions for achieving optimal trade-off.

Chung-Wei Lee, Haipeng Luo, Chen-Yu Wei et al.

In this work, we develop linear bandit algorithms that automatically adapt to different environments. By plugging a novel loss estimator into the optimization problem that characterizes the instance-optimal strategy, our first algorithm not only achieves nearly instance-optimal regret in stochastic environments, but also works in corrupted environments with additional regret being the amount of corruption, while the state-of-the-art (Li et al., 2019) achieves neither instance-optimality nor the optimal dependence on the corruption amount. Moreover, by equipping this algorithm with an adversarial component and carefully-designed testings, our second algorithm additionally enjoys minimax-optimal regret in completely adversarial environments, which is the first of this kind to our knowledge. Finally, all our guarantees hold with high probability, while existing instance-optimal guarantees only hold in expectation.

Xiaojin Zhang, Honglei Zhuang, Shengyu Zhang et al.

We study a variant of the thresholding bandit problem (TBP) in the context of outlier detection, where the objective is to identify the outliers whose rewards are above a threshold. Distinct from the traditional TBP, the threshold is defined as a function of the rewards of all the arms, which is motivated by the criterion for identifying outliers. The learner needs to explore the rewards of the arms as well as the threshold. We refer to this problem as "double exploration for outlier detection". We construct an adaptively updated confidence interval for the threshold, based on the estimated value of the threshold in the previous rounds. Furthermore, by automatically trading off exploring the individual arms and exploring the outlier threshold, we provide an efficient algorithm in terms of the sample complexity. Experimental results on both synthetic datasets and real-world datasets demonstrate the efficiency of our algorithm.

Xiaojin Zhang, Shuai Li, Weiwen Liu et al.

The problem of multi-armed bandits (MAB) asks to make sequential decisions while balancing between exploitation and exploration, and have been successfully applied to a wide range of practical scenarios. Various algorithms have been designed to achieve a high reward in a long term. However, its short-term performance might be rather low, which is injurious in risk sensitive applications. Building on previous work of conservative bandits, we bring up a framework of contextual combinatorial conservative bandits. An algorithm is presented and a regret bound of $\tilde O(d^2+d\sqrt{T})$ is proven, where $d$ is the dimension of the feature vectors, and $T$ is the total number of time steps. We further provide an algorithm as well as regret analysis for the case when the conservative reward is unknown. Experiments are conducted, and the results validate the effectiveness of our algorithm.

Xiaojin Zhang

We consider the problem of selecting a seed set to maximize the expected number of influenced nodes in the social network, referred to as the \textit{influence maximization} (IM) problem. We assume that the topology of the social network is prescribed while the influence probabilities among edges are unknown. In order to learn the influence probabilities and simultaneously maximize the influence spread, we consider the tradeoff between exploiting the current estimation of the influence probabilities to ensure certain influence spread and exploring more nodes to learn better about the influence probabilities. The exploitation-exploration trade-off is the core issue in the multi-armed bandit (MAB) problem. If we regard the influence spread as the reward, then the IM problem could be reduced to the combinatorial multi-armed bandits. At each round, the learner selects a limited number of seed nodes in the social network, then the influence spreads over the network according to the real influence probabilities. The learner could observe the activation status of the edge if and only if its start node is influenced, which is referred to as the edge-level semi-bandit feedback. Two classical bandit algorithms including Thompson Sampling and Epsilon Greedy are used to solve this combinatorial problem. To ensure the robustness of these two algorithms, we use an automatic ensemble learning strategy, which combines the exploration strategy with exploitation strategy. The ensemble algorithm is self-adaptive regarding that the probability of each algorithm could be adjusted based on the historical performance of the algorithm. Experimental evaluation illustrates the effectiveness of the automatically adjusted hybridization of exploration algorithm with exploitation algorithm.