arXiv subjects

Sheila Zingg

Publications and source records attributed to Sheila Zingg.

4 recordsLinked to original sources

arXiv2026

MOSAIC: Masked Outsourcing of Secure AI Computations

We address the challenge of securely and efficiently outsourcing AI computations from a trusted but computationally weak client to an untrusted but powerful server, in the setting where the client holds both the input and the model, and the server must learn neither. We present MOSAIC, whose core is a novel matrix-multiplication masking protocol that scales to far larger matrices than prior work, enabling the safe outsourcing of modern workloads such as large transformer inference. By introducing small amounts of noise to the multiplication result and thereby relaxing correctness, MOSAIC achieves optimal asymptotic client overhead and concrete runtimes orders of magnitude faster than prior work. Its security reduces to the decisional LWE and LPN assumptions. Because this noise accumulates across the many layers of a transformer, a key technical challenge is bounding error growth; MOSAIC addresses this with an error-scaling mechanism based on random Hadamard rotations. On large 70B transformer models, MOSAIC's perplexity is comparable to popular quantization approaches and even matches full-precision BF16 inference on HumanEval. Finally, we present an end-to-end implementation showing how ideas like MOSAIC can promise a path towards large-scale confidential AI in modern data centers. Non-confidential inference is already distributed across phase (prefill/decode), layer, and time to maximize utilization of heterogeneous hardware, using RDMA-like networking to move activations, cached KV values, and weights across nodes. MOSAIC enables scaling of confidential compute by keeping the trusted computing base (TCB) small and outsourcing the bulk of the AI computation to untrusted accelerators.

cs.CR↗

arXiv2026

Credential Disclosure in (EU) Digital Identity Wallets: Privacy Risks and Practical Mitigations

The European Union will introduce the EUDI Wallet by late 2026, which allows users to hold digital credentials (i.e., representations of physical official identity documents) on their devices. This will allow users to securely and privately disclose identity attributes to websites. Although such a system has many benefits, it also introduces risks caused by poor credential disclosure decisions. In this paper, we (i) conduct a large-scale survey on credential disclosure with users and experts and (ii) evaluate the effectiveness and feasibility of our Credential Assistant that displays expert recommendations and user opinions. Our results show that users are likely to overshare (e.g., ~20% of users disclosed their official ID to news websites). This indicates that users struggle to protect their privacy, which will impact the usability of the EUDI Wallet and lead to privacy violations, identity theft, and other abuses of leaked credentials. Finally, we show that our Credential Assistant significantly reduces users' credential disclosure mistakes from ~15% to ~7%. However, it does not fully eliminate poor credential disclosure decisions, indicating that stronger interventions may be necessary, especially for sensitive attributes.

cs.CR↗

arXiv2024

PayOff: A Regulated Central Bank Digital Currency with Private Offline Payments

The European Central Bank is preparing for the potential issuance of a central bank digital currency (CBDC), called the digital euro. A recent regulatory proposal by the European Commission defines several requirements for the digital euro, such as support for both online and offline payments. Offline payments are expected to enable cash-like privacy, local payment settlement, and the enforcement of holding limits. While other central banks have expressed similar desired functionality, achieving such offline payments poses a novel technical challenge. We observe that none of the existing research solutions, including offline E-cash schemes, are fully compliant. Proposed solutions based on secure elements offer no guarantees in case of compromise and can therefore lead to significant payment fraud. The main contribution of this paper is PayOff, a novel CBDC design motivated by the digital euro regulation, which focuses on offline payments. We analyze the security implications of local payment settlement and identify new security objectives. PayOff protects user privacy, supports complex regulations such as holding limits, and implements safeguards to increase robustness against secure element failure. Our analysis shows that PayOff provides strong privacy and identifies residual leakages that may arise in real-world deployments. Our evaluation shows that offline payments can be fast and that the central bank can handle high payment loads with moderate computing resources. However, the main limitation of PayOff is that offline payment messages and storage requirements grow in the number of payments that the sender makes or receives without going online in between.

cs.CR↗

arXiv2021

Learning Numeric Optimal Differentially Private Truncated Additive Mechanisms

Differentially private (DP) mechanisms face the challenge of providing accurate results while protecting their inputs: the privacy-utility trade-off. A simple but powerful technique for DP adds noise to sensitivity-bounded query outputs to blur the exact query output: additive mechanisms. While a vast body of work considers infinitely wide noise distributions, some applications (e.g., real-time operating systems) require hard bounds on the deviations from the real query, and only limited work on such mechanisms exist. An additive mechanism with truncated noise (i.e., with bounded range) can offer such hard bounds. We introduce a gradient-descent-based tool to learn truncated noise for additive mechanisms with strong utility bounds while simultaneously optimizing for differential privacy under sequential composition, i.e., scenarios where multiple noisy queries on the same data are revealed. Our method can learn discrete noise patterns and not only hyper-parameters of a predefined probability distribution. For sensitivity bounded mechanisms, we show that it is sufficient to consider symmetric and that\new{, for from the mean monotonically falling noise,} ensuring privacy for a pair of representative query outputs guarantees privacy for all pairs of inputs (that differ in one element). We find that the utility-privacy trade-off curves of our generated noise are remarkably close to truncated Gaussians and even replicate their shape for $l_2$ utility-loss. For a low number of compositions, we also improved DP-SGD (sub-sampling). Moreover, we extend Moments Accountant to truncated distributions, allowing to incorporate mechanism output events with varying input-dependent zero occurrence probability.

cs.CR↗