Modern cryptographic tools such as multi-party computation (MPC) and zero-knowledge proofs (ZKPs) offer strong, provable security guarantees—but these generic protocols remain impractical for production-scale machine learning (ML), especially in the era of large language models (LLMs). This thesis proposal advances the central claim that cryptographic protocols co-designed with the structure of specific ML subtasks can achieve practical efficiency without compromising privacy or verifiability. To validate this vision, this proposal develops three interconnected research thrusts: (1) Confidential Outsourced Training. Customized MPC protocols shift expensive cryptographic steps to local computations, enabling secure training of large models in untrusted clouds by resource-constrained data owners. (2) Scalable MPC Primitives for Large Datasets. Provably secure building blocks—such as oblivious shuffles, private joins, and sparse linear algebra routines—bridge the performance gap in privacy-preserving data pipelines at scale. (3) Verifiable ML without Retraining. Rather than proving each training step, a new proof-of-optimality framework certifies that a trained or fine-tuned model (e.g., LoRA adapters) satisfies desired properties, enabling efficient, auditable deployment without re-executing training. Together, these efforts aim to close the long-standing gap between privacy and efficiency, demonstrating that strong cryptographic guarantees and modern ML workflows can be reconciled through principled, application-aware design.

Zero-knowledge proofs of training (zkPoT) allow a party to prove that a model is trained correctly on a committed dataset without revealing any additional information about the model or the dataset. Existing zkPoT protocols prove the entire training process in zero knowledge; i.e., they prove that the final model was obtained in an iterative fashion starting from the training data and a random seed (and potentially other parameters) and applying the correct algorithm at each iteration. This approach inherently requires the prover to perform work linear to the number of iterations.

Diffusion models are increasingly deployed in real-world text-to-image services. These models, however, encode implicit assumptions about the world based on web-scraped image-caption pairs used during training. Over time, such assumptions may become outdated, incorrect, or socially biased--leading to failures where the generated images misalign with users' expectations or evolving societal norms. Identifying and fixing such failures is challenging and, thus, a valuable asset for service providers, as failures often emerge post-deployment and demand specialized expertise and resources to resolve them. In this work, we introduce $\textit{SURE}$, the first end‑to‑end framework that $\textbf{S}$ec$\textbf{U}$rely $\textbf{RE}$pairs failures flagged by users of diffusion-based services. $\textit{SURE}$ enables the service provider to securely collaborate with an external third-party specialized in model repairing (i.e., Model Repair Institute) without compromising the confidentiality of user feedback, the service provider’s proprietary model, or the Model Repair Institute’s proprietary repairing knowledge. To achieve the best possible efficiency, we propose a co-design of a model editing algorithm with a customized two-party cryptographic protocol. Our experiments show that $\textit{SURE}$ is highly practical: $\textit{SURE}$ securely and effectively repairs all 32 layers of {Stable Diffusion v1.4} in under 17 seconds (four orders of magnitude more efficient than a general baseline). Our results demonstrate that practical, secure model repair is attainable for large-scale, modern diffusion services.

Post hoc privacy auditing techniques can be used to test the privacy guarantees of a model, but come with several limitations: (i) they can only establish lower bounds on the privacy loss, (ii) the intermediate model updates and some data must be shared with the auditor to get a better approximation of the privacy loss, and (iii) the auditor typically faces a steep computational cost to run a large number of attacks. In this paper, we propose to proactively generate a cryptographic certificate of privacy during training to forego such auditing limitations. We introduce Confidential-DPproof , a framework for Confidential Proof of Differentially Private Training, which enhances training with a certificate of the $(\varepsilon,\delta)$-DP guarantee achieved. To obtain this certificate without revealing information about the training data or model, we design a customized zero-knowledge proof protocol tailored to the requirements introduced by differentially private training, including random noise addition and privacy amplification by subsampling. In experiments on CIFAR-10, Confidential-DPproof trains a model achieving state-of-the-art $91$% test accuracy with a certified privacy guarantee of $(\varepsilon=0.55,\delta=10^{-5})$-DP in approximately 100 hours.

Cloud service providers offer robust infrastructure for rent to organizations of all kinds. High stakes applications, such as the ones in defense and healthcare, are turning to the public cloud for a cost-effective, geographically distributed, always available solution to their hosting needs. Many such users are unwilling or unable to delegate their data to this third-party infrastructure. In this demonstration, we introduce RESCU-SQL, a zero-trust platform for resilient and secure SQL querying outsourced to one or more cloud service providers. RESCU-SQL users can query their DBMS using cloud infrastructure alone without revealing their private records to anyone. It does so by executing the query over secure multiparty computation. We call this system zero trust because it can tolerate any number of malicious servers provided one of them remains honest. Our demo will offer an interactive dashboard with which attendees can observe the performance of RESCU-SQL deployed on several in-cloud nodes for the TPC-H benchmark. Attendees can select a computing party and inject messages from it to explore how quickly it detects and reacts to a malicious party. This is the first SQL system to support all-but-one maliciously secure querying over a semi-honest coordinator for efficiency.