Privacy Pass is Anamorphic: Practical Consequences and Attacks in the Black-box Model

Migrating to Hybrid Cryptography in Practice: The TutaCrypt Protocol and Its Security

This work presents the hybrid key establishment protocol TutaCrypt in a form that enables rigorous cryptographic analysis and defines two Bellare–Rogaway-style security models that precisely characterize the provided security guarantees.

Transferability of Evasion and Backdoor Attacks in Encrypted Domain

LLMs AND DATA PRIVACY

MOSAIC-FL, a Micro-Service Based Privacy-Preserving Framework with Application to Genomics

The FL framework integrates an efficient gRPC communication layer and a Finite State Machine to ensure robust component synchronization and threat detection, while relying on a fault-tolerant secure aggregation protocol using a Threshold variant of the CKKS homomorphic cryptosystem.

Experimental Evaluation of Fully Homomorphic Encryption for Privacy-Preserving V2X Communication

Vehicle-to-Everything (V2X) communication requires continuous exchange of mobility data, but this information is highly sensitive and must be protected. Fully Homomorphic Encryption (FHE) enables computation directly on encrypted data and has recently been explored for Intelligent Transportation Systems (ITS), yet its practical feasibility for specific V2X tasks remains unclear. This paper experimentally evaluates three lattice-based schemes (BFV, BGV, CKKS) using OpenFHE on SUMO-generated mobility data. Three representative traffic-related tasks are considered: collision-risk detection, average speed estimation, and traffic density. For each scheme, we measure encryption time, homomorphic computation time, decryption time, ciphertext size, and correctness relative to plaintext baselines. The results show that all schemes achieve near-perfect correctness, and that aggregated analytics (average speed, density) complete well within non-safety-critical time budgets. However, all schemes consume a significant portion of the 100 ms safety message threshold. These findings quantify the current performance–privacy trade-offs of FHE in V2X scenarios and indicate that hardware acceleration or lighter cryptographic configurations are needed for real-time safety applications.

Privacy-Preserving Counterfactual Explanations for Federated AI

: As the usage of Artificial Intelligence (AI) for sensitive purposes increases, there is a growing need for privacy-aware explainable AI (XAI) tools. In this paper, we present a privacy-preserving counterfactual explanation algorithm . Our starting point is a decision-support model that is able to operate on vertically partitioned datasets, meaning that each party holds a different subset of datapoint attributes. The goal of a counterfactual algorithm is to find, given an observation , a datapoint from the (virtual) dataset that is closest to the observation but has a different label. Our algorithm fully preserves the privacy of the n datapoints belonging to the different parties by combining the strengths of homomorphic encryption and secret sharing . Through a number of experiments, we demonstrate the added value of combining multiple datasets in a realistic scenario and show that the privacy-preserving solution does not affect the accuracy. We fully implement our solution and demonstrate that it scales as to thousands of datapoints.