Search

Completely Automated Public Turing Test To Tell Computers and Humans Apart (CAPTCHA) is a type of challenge-response test widely used in authentication systems. A well-known challenge it faces is the CAPTCHA farm, where workers are hired to solve CAPTCHAs manually. In this work, we propose to tackle this challenge from a novel perspective, converting CAPTCHA farm detection to identity inconsistency detection, which essentially becomes an authentication process. Specifically, we develop a novel embedding model, which measures the similarity between mouse trajectories collected during the session and when registering/solving CAPTCHA, to authenticate and detect identity inconsistency. Moreover, unlike most existing works that employ a separate mouse movement classifier for each individual user, which brings in considerable costs when serving a large number of users, our model performs detection tasks using only one classifier for all users, significantly reducing the cost. Experiment results validate the superiority of our method over the state-of-the-art time series classification methods, achieving 94.3% and 97.7% of AUC in identity and authentication inconsistency detection, respectively.

Leveraging federated learning (FL) to enable cross-domain privacy-sensitive data mining represents a vital breakthrough to accomplish privacy-preserving learning. However, attackers can infer the original user data by analyzing the uploaded intermediate parameters during the aggregation process. Therefore, secure aggregation has become a critical issue in the field of FL. Many secure aggregation protocols face the problem of high computation costs, which severely limits their applicability. To this end, we propose AHSecAgg, a lightweight secure aggregation protocol using additive homomorphic masks. AHSecAgg significantly reduces computation overhead without compromising the dropout handling capability or model accuracy. We prove the security of AHSecAgg in semi-honest and active adversary settings. In addition, in cross-silo scenarios where the group of participants is relatively fixed during each round, we propose TSKG, a lightweight Threshold Signature based masking key generation method. TSKG can generate different temporary secrets and shares for different aggregation rounds using the initial key and thus effectively eliminates the cost of secret sharing and key agreement. We prove TSKG does not sacrifice security. Extensive experiments show that AHSecAgg significantly outperforms state-of-the-art mask-based secure aggregation protocols in terms of computational efficiency, and TSKG effectively reduces the computation and communication costs for existing secure aggregation protocols.

Secure aggregation of user vectors has become a critical issue in the field of federated learning. Many Secure Aggregation Protocols (SAP) face exorbitant computation costs, which severely limit their applicability. We uncover that current endeavors to reduce computation costs tend to overlook a crucial fact: a considerable portion of SAP's computation burden stems from processing each entry in the private vectors. Given this observation, we propose PVF, a portable module for compressing computation costs. PVF is able to ``freeze'' a substantial portion of the private vector through specific linear transformations, only requiring $\frac{1}{\lambda}$ of the original vector to participate in SAP. Eventually, users can ``thaw'' the public sum of the ``frozen entries" by the result of SAP. To enhance functionality, we introduce extensions that can enforce consistency constraints on users' original vectors, verify aggregated results, and enhance security when a portion of the private vector is known to the server. We demonstrate that PVF can seamlessly integrate with various SAP and prove that it poses no threat to user privacy in the semi-honest and active adversary settings. We select $8$ baselines, encompassing $6$ distinct types of SAP, and explore the acceleration effects of PVF on these SAP. Empirical investigations indicate that when $\lambda=100$, PVF yields up to $99.5\times$ speedup and up to $32.3\times$ communication reduction, with the potential to approach nearly $1000\times$ acceleration as $\lambda$ increases.

Completely Automated Public Turing Test To Tell Computers and Humans Apart (CAPTCHA) has been implemented on many websites to identify between harmful automated bots and legitimate users. However, the revenue generated by the bots has turned circumventing CAPTCHAs into a lucrative business. Although earlier studies provided information about text-based CAPTCHAs and the associated CAPTCHA-solving services, a lot has changed in the past decade regarding content, suppliers, and solvers of CAPTCHA. We have conducted a comprehensive investigation of the latest third-party CAPTCHA providers and CAPTCHA-solving services' attacks. We dug into the details of CAPTCHA-As-a-Service and the latest CAPTCHA-solving services and carried out adversarial experiments on CAPTCHAs and CAPTCHA solvers. The experiment results show a worrying fact: most latest CAPTCHAs are vulnerable to both human solvers and automated solvers. New CAPTCHAs based on hard AI problems and behavior analysis are needed to stop CAPTCHA solvers.

Federated learning allows clients to collaboratively train a global model without uploading raw data for privacy preservation. This feature, i.e., the inability to review participants' datasets, has recently been found responsible for federated learning's vulnerability in the face of backdoor attacks. Existing defense methods fall short from two perspectives: 1) they consider only very specific and limited attacker models and unable to cope with advanced backdoor attacks, such as distributed backdoor attacks, which break down the global trigger into multiple distributed triggers. 2) they conduct detection based on model granularity thus the performance gets impacted by the model dimension. To address these challenges, we propose Federated Layer Detection (FLD), a novel model filtering approach for effectively defending against backdoor attacks. FLD examines the models based on layer granularity to capture the complete model details and effectively detect potential backdoor models regardless of model dimension. We provide theoretical analysis and proof for the convergence of FLD. Extensive experiments demonstrate that FLD effectively mitigates state-of-the-art backdoor attacks with negligible impact on the accuracy of the primary task.

Mobile devices and the immense amount and variety of data they generate are key enablers of machine learning (ML)-based applications. Traditional ML techniques have shifted toward new paradigms such as federated (FL) and split learning (SL) to improve the protection of user's data privacy. However, these paradigms often rely on server(s) located in the edge or cloud to train computationally-heavy parts of a ML model to avoid draining the limited resource on client devices, resulting in exposing device data to such third parties. This work proposes an alternative approach to train computationally-heavy ML models in user's devices themselves, where corresponding device data resides. Specifically, we focus on GANs (generative adversarial networks) and leverage their inherent privacy-preserving attribute. We train the discriminative part of a GAN with raw data on user's devices, whereas the generative model is trained remotely (e.g., server) for which there is no need to access sensor true data. Moreover, our approach ensures that the computational load of training the discriminative model is shared among user's devices-proportional to their computation capabilities-by means of SL. We implement our proposed collaborative training scheme of a computationally-heavy GAN model in real resource-constrained devices. The results show that our system preserves data privacy, keeps a short training time, and yields same accuracy of model training in unconstrained devices (e.g., cloud). Our code can be found on https://github.com/YukariSonz/FSL-GAN