More Like this

1. Provably Confidential Language Modelling

   https://doi.org/10.18653/v1/2022.naacl-main.69  

   Zhao, Xuandong; Li, Lei; Wang, Yu-Xiang (July 2022, Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies)

   Large language models are shown to memorize privacy information such as social security numbers in training data. Given the sheer scale of the training corpus, it is challenging to screen and filter these privacy data, either manually or automatically. In this paper, we propose Confidentially Redacted Training (CRT), a method to train language generation models while protecting the confidential segments. We borrow ideas from differential privacy (which solves a related but distinct problem) and show that our method is able to provably prevent unintended memorization by randomizing parts of the training process. Moreover, we show that redaction with an approximately correct screening policy amplifies the confidentiality guarantee. We implement the method for both LSTM and GPT language models. Our experimental results show that the models trained by CRT obtain almost the same perplexity while preserving strong confidentiality. 

   more » « less
2. Topological Interference Management With Confidential Messages

   https://doi.org/10.1109/TIT.2022.3186238  

   de Dieu Mutangana, Jean; Tandon, Ravi (November 2022, IEEE Transactions on Information Theory)
3. Two-Multicast Channel With Confidential Messages

   https://doi.org/10.1109/TIFS.2021.3055031  

   Zivarifard, Hassan; Bloch, Matthieu R.; Nosratinia, Aria (January 2021, IEEE Transactions on Information Forensics and Security)

   null (Ed.)
4. Reusable Enclaves for Confidential Serverless Computing

   Zhao, Shixuan; Xu, Pinshen; Chen, Guoxing; Zhang, Mengya; Zhang, Yinqian; Lin, Zhiqiang (August 2023, Proceedings of the 32nd USENIX Security Symposium)

   The recent development of Trusted Execution Environment has brought unprecedented opportunities for confidential computing within cloud-based systems. Among various popular cloud business models, serverless computing has gained dominance since its emergence, leading to a high demand for confidential serverless computing services based on trusted enclaves. However, the issue of cold start overhead significantly hinders its performance, as new enclaves need to be created to ensure a clean and verifiable execution environment. In this paper, we propose a novel approach for constructing reusable enclaves that enable rapid enclave reset and robust security with three key enabling techniques: enclave snapshot and rewinding, nested attestation, and multi-layer intra-enclave compartmentalisation. We have built a prototype system for confidential serverless computing, integrating OpenWhisk and a WebAssembly runtime, which significantly reduces the cold start overhead in an end-to-end serverless setting while imposing a reasonable performance impact on standard execution. 

   more » « less
5. Nimble: Rollback Protection for Confidential Cloud Services

   Angel, Sebastian; Basu, Aditya; Cui, Weidong; Jaeger, Trent; Lau, Stella; Setty, Srinath; Singanamalla, Sudheesh (July 2023, 17th USENIX Symposium on Operating Systems Design and Implementation)