Alptekin Küpçü

Aqsa Shabbir, Halil İbrahim Kanpak, Alptekin Küpçü et al.

Split Learning (SL) has emerged as a promising paradigm for distributed deep learning, allowing resource-constrained clients to offload portions of their model computation to servers while maintaining collaborative learning. However, recent research has demonstrated that SL remains vulnerable to a range of privacy and security threats, including information leakage, model inversion, and adversarial attacks. While various defense mechanisms have been proposed, a systematic understanding of the attack landscape and corresponding countermeasures is still lacking. In this study, we present a comprehensive taxonomy of attacks and defenses in SL, categorizing them along three key dimensions: employed strategies, constraints, and effectiveness. Furthermore, we identify key open challenges and research gaps in SL based on our systematization, highlighting potential future directions.

Halil Ibrahim Kanpak, Aqsa Shabbir, Esra Genç et al.

Training deep neural networks often requires large-scale datasets, necessitating storage and processing on cloud servers due to computational constraints. The procedures must follow strict privacy regulations in domains like healthcare. Split Learning (SL), a framework that divides model layers between client(s) and server(s), is widely adopted for distributed model training. While Split Learning reduces privacy risks by limiting server access to the full parameter set, previous research has identified that intermediate outputs exchanged between server and client can compromise client's data privacy. Homomorphic encryption (HE)-based solutions exist for this scenario but often impose prohibitive computational burdens. To address these challenges, we propose CURE, a novel system based on HE, that encrypts only the server side of the model and optionally the data. CURE enables secure SL while substantially improving communication and parallelization through advanced packing techniques. We propose two packing schemes that consume one HE level for one-layer networks and generalize our solutions to n-layer neural networks. We demonstrate that CURE can achieve similar accuracy to plaintext SL while being 16x more efficient in terms of the runtime compared to the state-of-the-art privacy-preserving alternatives.

Yahya Hassanzadeh-Nazarabadi, Alptekin Küpçü, Öznur Özkasap

As an append-only distributed database, blockchain is utilized in a vast variety of applications including the cryptocurrency and Internet-of-Things (IoT). The existing blockchain solutions show downsides in communication and storage scalability, as well as decentralization. In this article, we propose LightChain , which is the first blockchain architecture that operates over a Distributed Hash Table (DHT) of participating peers. LightChain is a permissionless blockchain that provides addressable blocks and transactions within the network, which makes them efficiently accessible by all peers. Each block and transaction is replicated within the DHT of peers and is retrieved in an on-demand manner. Hence, peers in LightChain are not required to retrieve or keep the entire ledger. LightChain is fair as all of the participating peers have a uniform chance of being involved in the consensus regardless of their influence such as hashing power or stake. We provide formal mathematical analysis and experimental results (simulations and cloud deployment) to demonstrate the security, efficiency, and fairness of LightChain , and show that LightChain is the only existing blockchain that can provide integrity under the corrupted majority power of peers. As we experimentally demonstrate, compared to the mainstream blockchains such as Bitcoin and Ethereum, LightChain requires around 66 times smaller per node storage, and is around 380 times faster on bootstrapping a new node to the system, and each LightChain node is rewarded equally likely for participating in the protocol.

Günther Eibl, Sanaz Taheri-Boshrooyeh, Alptekin Küpçü

Smart meter data aggregation protocols have been developed to address rising privacy threats against customers' consumption data. However, these protocols do not work satisfactorily in the presence of failures of smart meters or network communication links. In this paper, we propose a lightweight and fault-tolerant aggregation algorithm that can serve as a solid foundation for further research. We revisit an existing error-resilient privacy-preserving aggregation protocol based on masking and improve it by: (i) performing changes in the cryptographic parts that lead to a reduction of computational costs, (ii) simplifying the behaviour of the protocol in the presence of faults, and showing a proof of proper termination under a well-defined failure model, (iii) decoupling the computation part from the data flow so that the algorithm can also be used with homomorphic encryption as a basis for privacy-preservation. To best of our knowledge, this is the first algorithm that is formulated for both, masking and homomorphic encryption. (iv) Finally, we provide a formal proof of the privacy guarantee under failure. The systematic treatment with strict proofs and the established connection to graph theory may also serve as a starting point for possible generalizations and improvements with respect to increased resilience.

Nandini Agrawal, R Prashanthi, Osman Biçer et al.

Since its proposal by Eyal and Sirer (CACM '13), selfish mining attack on proof-of-work blockchains has been studied extensively in terms of both improving its impact and defending against it. Before any defense is deployed in a real world blockchain system, it needs to be tested for security and dependability. However, real blockchain systems are too complex to conduct any test on or benchmark the developed protocols. Some simulation environments have been proposed recently, such as BlockSim (Maher et al., '20). However, BlockSim is developed for the simulation of an entire network on a single CPU. Therefore, it is insufficient to capture the essence of a real blockchain network, as it is not distributed and the complications such as propagation delays that occur in reality cannot be simulated realistically enough. In this work, we propose BlockSim-Net, a simple, efficient, high performance, network-based blockchain simulator, to better reflect reality.

Mohammad Etemad, Alptekin Küpçü, Charalampos Papamanthou et al.

Searchable symmetric encryption (SSE) enables a client to perform searches over its outsourced encrypted files while preserving privacy of the files and queries. Dynamic schemes, where files can be added or removed, leak more information than static schemes. For dynamic schemes, forward privacy requires that a newly added file cannot be linked to previous searches. We present a new dynamic SSE scheme that achieves forward privacy by replacing the keys revealed to the server on each search. Our scheme is efficient and parallelizable and outperforms the best previous schemes providing forward privacy, and achieves competitive performance with dynamic schemes without forward privacy. We provide a full security proof in the random oracle model. In our experiments on the Wikipedia archive of about four million pages, the server takes one second to perform a search with 100,000 results.