Cryptography and Data Security

Neueste Paper

• Learning to Refer: Client-Resolved Generation for Privacy-Aware Language Models

  Jeongho Yoon, Chanhee Park, Yongchan Chun, Duong Tuan Thanh, Sungbin Han, Chanjun Park, Hyeonseok Moon, Heuiseok Lim · 29. September 2026

  Cloud-based large language models (LLMs) require users to disclose plaintext data to service providers, creating privacy risks in sensitive domains. Existing privacy-preserving approaches often trade utility for protection, incur substantial computational or communication overhead, remain vulnerable…

• Ask Without Telling: Local SLMs Consult Cloud LLMs Without Revealing Task Intent

  Yanmeng Wang, Yunxuan Li, Shilong Fan, Yuhan Zheng, Tsung-Hui Chang · 29. September 2026

  As local small language models (SLMs) increasingly collaborate with more capable cloud large language models (LLMs), a natural privacy question arises: Can a local SLM obtain cloud LLM guidance while protecting user privacy? Existing privacy-preserving SLM-LLM frameworks primarily hide sensitive val…

• Encryptability As a Coordinate Choice: Depth-One Homomorphic Federated Learning of Quantum Neural Networks

  Marcel Mordarski, Nathan Mani, Arshad Patel, William Knottenbelt, Roberto Bondesan · 28. September 2026

  Encrypted training relies on keeping server-side updates low-degree. This constraint traditionally excludes models whose weights inhabit a compact Lie group (notably variational quantum circuits, where every trainable weight is an $\mathrm{SU(2)}$ rotation). Expressed in Euler angles or discrete alp…

• HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference

  Byeongseo Min, Yongwoo Lee, Young-Sik Kim, Yongjune Kim · 21. September 2026

  Homomorphic encryption (HE) has emerged as a promising approach to privacy-preserving machine learning (PPML), enabling computation directly over encrypted data. In HE-based PPML, a client submits an encrypted input to the server, which evaluates models such as large language models (LLMs) without a…

• OptiPrime: Optimizing Private Inference through Protocol-Hardware Co-design

  Jiangrui Yu, Ye Yu, Si Chen, Chenqi Lin, Wenxuan Zeng, Junfeng Fan, Mingyu Gao, Meng Li · 16. September 2026

  Private deep neural network (DNN) inference based on hybrid homomorphic encryption (HE) and multi-party computation (MPC) can protect user data with a formal guarantee, but at the cost of significant latency overhead due to HE. Customized HE accelerators have been proposed and have achieved orders-o…

• SpliTEE: Improving LLM Inference on Trusted Hardware with Differentially Private GPU Outsourcing

  Shashie Dilhara Batan Arachchige, Robin Carpentier, Hassan Jameel Asghar, Dali Kaafar · 15. September 2026

  User prompts provided to large language models (LLMs) may contain sensitive or private information that can be misused by remotely deployed models, such as through inadvertent memorization during retraining. One way to protect user prompts is to execute the LLM inside a trusted execution environment…

• CARTS: Contextual Autoregressive Rank Transcoding Steganography for Full-Capacity Keyed Text Encoding

  Wissam Ghantous, Alexander V. Mantzaris · 11. September 2026

  Autoregressive language models can be used to transform a payload text into a stegotext of identical token length by preserving per-position rank information across contexts - a methodology we formalize as Contextual Autoregressive Rank Transcoding Steganography (CARTS). While the Calgacus construct…

• Empirical Evaluation of Membership Inference Attacks on NLP Text Classifiers: A Baseline Study on SST-2

  William Novak (Minot State University), Muhammad Abusaqer (Minot State University) · 11. September 2026

  Membership inference attacks (MIAs) try to determine whether a specific record was used to train a model, a privacy risk that matters in natural language processing (NLP), where training data can contain sensitive user text. This paper presents a controlled benchmark of membership inference vulnerab…

• Maverick: Private and Verifiable LLM Inference Made Practical via Matrix-Vector Multiplication Delegation

  Ben Merbaum, Mohammad Amin Raeisi, Wenhao Wang, Charalampos Papamanthou, Katerina Sotiraki, Fan Zhang · 10. September 2026

  Open-source large language models (LLMs) are increasingly competitive with closed-source models while offering transparency and the ability to run inference without exposing user inputs to a service provider. However, running large-scale models locally requires substantial computational resources. I…

• Encrypt What Matters: When Selective Homomorphic Inference Is Efficient

  Ali Backour, Juan Reyes, Jaime Punyed, Ana Onoprishvili · 10. September 2026

  Fully homomorphic encryption (FHE) enables inference on private data without revealing it to the server, but evaluating an entire input under FHE is expensive. We study \emph{selective homomorphic inference}, where only a sensitive region of interest (ROI) is encrypted, and computations independent …

• PAC-Private Autoregressive Generation: Calibrating Noise to Ensemble Disagreement

  Mina Mirzadehsarcheshmeh, Amir Keyvan Khandani · 9. September 2026

  Language models adapted on private text are often served through APIs, so privacy leakage occurs through generated outputs rather than exposed weights. Private prediction protects these releases. Methods such as PMixED incur privacy cost at each release and increasingly rely on the public model over…

• HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation

  Alessandro Zirilli, Davide Marincione, Evgenios M. Kornaropoulos, Giuseppe Ateniese, Emanuele Rodol\`a · 3. September 2026

  Fully homomorphic encryption (FHE) allows a server to run a language model directly on encrypted user prompts, but current approaches remain prohibitively slow. Ciphertexts natively support only addition, multiplication, and rotation, and multiplications may be composed only to a bounded depth befor…

• Membership Inference in Fine-tuned Diffusion Language Models via Token-level Memorization Asymmetry

  Shengfang Zhai, Leo Marchyok, Yuling Shi, Huanran Chen, Yinpeng Dong, Jiaheng Zhang, Sanghyun Hong · 2. September 2026

  Diffusion language models (DLMs) have recently emerged as an alternative modeling paradigm to autoregressive LMs, offering advantages such as parallel generation and bidirectional context modeling. Despite growing interest in their generative capabilities, the privacy risks of DLMs remain underexplo…

• Memorization Is Not Extraction: Tight Differential-Privacy Bounds and Audit Blind Spots

  Xujun Che, Depeng Xu, Shuhan Yuan · 31. August 2026

  Memorization in large language models is measured through a zoo of definitions whose formal relations are unknown, and differential privacy (DP) is treated as a proxy against all of them at once. We pin down the exact DP constant for the two that carry the practical weight, counterfactual memorizati…

• Beyond Classification: Task-Dependent Learnability under Privacy-Motivated Image Transformations

  Leon Ranke, Wolfgang H\"ubner, Ronny Hug, Michael Arens, J\"urgen Beyerer · 28. August 2026

  Privacy-Enhancing Technologies (PETs) in computer vision often rely on noise or image perturbations to protect visual data while securely processing it, creating a trade-off between task performance and protection. This trade-off is commonly evaluated using image classification, which primarily capt…

• Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at Scale

  Peichun Hua, Danyang Chen, Junan Zhang, Haifeng Sun, Jingyu Wang, Diwen Xue, Mingyu Li, Yunming Xiao · 27. August 2026

  Hosted retrieval-augmented generation (RAG) and semantic search allow users to query valuable provider-held corpora, raising two competing demands: to hide each query and chosen result, yet reveal only the documents that the user is authorized to receive. Existing cryptographic approaches either mak…

• Spectrum-Aware Bounds on Invertibility for Privacy-Enhancing Instance Encoding

  Seokjin Hwang, Yuting Li, Kiwan Maeng · 26. August 2026

  Instance encoding is a popular empirical technique for privacy enhancement when sharing data to an untrusted server. It transforms sensitive data through an encoding process before sharing, with the hope that the encoding process retains utility but makes it hard to reconstruct the original data. Ho…

• Certified but Private: Scalable Zero-Knowledge Proofs for Neural Network Guarantees

  Youwei Zhong, Ben Merbaum, Timos Antonopoulos, Ning Luo, Charalampos Papamanthou, Katerina Sotiraki, Ruzica Piskac · 19. August 2026

  With the growing deployment of machine learning models, formal guarantees of the robustness and fairness of these models have become increasingly important in safety-critical and legal-compliance settings. However, model parameters are often commercial secrets that cannot be disclosed to auditors or…

• P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems

  Myunghoon Ryu, Geunpyo Park, Sungjoon Lee, XinYu Piao, Jong-Kook Kim · 17. August 2026

  Cloud-local LLM inference systems have the potential to use the reasoning capability of large cloud models while protecting sensitive user data on personal devices. Cloud-bound requests must exclude personally identifiable information (PII) to prevent external data leakage. Existing privacy-preservi…

• DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM Agents

  Jong Wook Kim, Byoungjae Min, Kennedy Edemacu, Yoonhyuk Choi, Sae-Hong Cho, Beakcheol Jang · 5. August 2026

  Long-term memory enables persistent personalization in LLM agents, but repeated memory-conditioned responses can cumulatively reveal protected attributes even when they are never stated explicitly. We formalize this threat as adaptive transcript privacy and introduce DP-MemView, a differentially pri…

• Gecko: Fast Private Inference via Secure Public Encoder Offloading

  Cheng'an Wei, Kai Chen, Yue Zhao, Congyi Li, Shenchen Zhu · 4. August 2026

  Private inference protects both user inputs and server models during neural network inference, but existing solutions remain too slow for practical deployment. This motivates recent efforts to run a public encoder, such as a pretrained backbone, outside the protection boundary and evaluate only a sm…

• GoldenRetriever: Non-Interactive Homomorphic Encrypted Retrieval for Privacy-Preserving RAG

  Yang Gao, Gang Quan, Scott Piersall, Qian Lou, Dongdong Wang, Liqiang Wang · 3. August 2026

  Retrieval-Augmented Generation (RAG) enhances large language models by incorporating external knowledge, but existing pipelines typically operate on plaintext data, raising significant privacy concerns. Prior work on privacy-preserving retrieval leverages cryptographic techniques such as homomorphic…

• MOSAIC: Masked Outsourcing of Secure AI Computations

  James Hsin-yu Chiang, Sheila Zingg, Kari Kostiainen, Srdjan Capkun · 3. August 2026

  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…

• Balancing Privacy and Efficiency: Music Information Retrieval via Additive Homomorphic Encryption

  William Zerong Wang, Dongfang Zhao · 30. Juli 2026

  Modern music retrieval runs on vector embeddings, and once these embeddings are shared for search or matching they can be copied, probed, or used to train generative models. Fully homomorphic encryption can compute on them but is impractical at scale because of ciphertext--ciphertext multiplication …

• MOSAIC-FL, a micro-service based privacy-preserving framework with application to genomics

  Paul Largillier, Karl Paygambar, C\'edric Gouy-Pailler, Vincent Meyer, Mallek Mziou, Oana Stan · 29. Juli 2026

  Security and privacy are primordial requirements for Federated Learning (FL), especially in fields such as healthcare and genomics where sensitive information has to be analyzed. Our FL framework is designed to address these challenges while proposing a modular, flexible and micro-service architectu…