Rui Zhang

Rui Zhang, Ka-Ho Chow, Ping Li

The growing concern over data privacy, the benefits of utilizing data from diverse sources for model training, and the proliferation of networked devices with enhanced computational capabilities have all contributed to the rise of federated learning (FL). The clients in FL collaborate to train a global model by uploading gradients computed on their private datasets without collecting raw data. However, a new attack surface has emerged from gradient sharing, where adversaries can restore the label distribution of a victim's private data by analyzing the obtained gradients. To mitigate this privacy leakage, existing lightweight defenses restrict the sharing of gradients, such as encrypting the final-layer gradients or locally updating the parameters within. In this paper, we introduce a novel attack called Gradient Bridge (GDBR) that recovers the label distribution of training data from the limited gradient information shared in FL. GDBR explores the relationship between the layer-wise gradients, tracks the flow of gradients, and analytically derives the batch training labels. Extensive experiments show that GDBR can accurately recover more than 80% of labels in various FL settings. GDBR highlights the inadequacy of restricted gradient sharing-based defenses and calls for the design of effective defense schemes in FL.

Linyong Nan, Chiachun Hsieh, Ziming Mao et al.

Existing table question answering datasets contain abundant factual questions that primarily evaluate the query and schema comprehension capability of a system, but they fail to include questions that require complex reasoning and integration of information due to the constraint of the associated short-form answers. To address these issues and to demonstrate the full challenge of table question answering, we introduce FeTaQA, a new dataset with 10K Wikipedia-based {table, question, free-form answer, supporting table cells} pairs. FeTaQA yields a more challenging table question answering setting because it requires generating free-form text answers after retrieval, inference, and integration of multiple discontinuous facts from a structured knowledge source. Unlike datasets of generative QA over text in which answers are prevalent with copies of short text spans from the source, answers in our dataset are human-generated explanations involving entities and their high-level relations. We provide two benchmark methods for the proposed task: a pipeline method based on semantic-parsing-based QA systems and an end-to-end method based on large pretrained text generation models, and show that FeTaQA poses a challenge for both methods.

Ehsan Meamari, Hao Guo, Chien-Chung Shen et al.

Attribute-Based Encryption (ABE) has emerged as an information-centric public-key cryptographic system which allows a data owner to share data, according to access policy, with multiple data users based on the attributes they possess, without knowing their identities. In the original ABE schemes, a central authority administrates the system and issues secret keys to data users based on their attributes and both the owner and users need to trust a specific CA. However, in certain real-world applications, the data users would not trust anyone but themselves. For such situations, we introduce a new decentralization model of ABE, termed Data User-based ABE (DU-ABE), which is managed jointly by the data users. DU-ABE is the first decentralized ABE scheme that replaces the authorities with the data users without employing any other extra entities.