{"total":14,"rows":[{"id":"2502.00840","title":"Activation Approximations Can Incur Safety Vulnerabilities Even in Aligned LLMs: Comprehensive Analysis and Defense","created":"2025-02-02","cited_by_count":7,"area":null},{"id":"2506.06579","title":"Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2512.11269","title":"A Scalable Multi-GPU Framework for Encrypted Large-Model Inference","created":"2025-12-12","cited_by_count":3,"area":null},{"id":"2509.09424","title":"ENSI: Efficient Non-Interactive Secure Inference for Large Language Models","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2607.23478","title":"ATLAS: Automated Approximation of Transformers for Efficient Homomorphic Inference in One Hour","created":"2026-07-26","cited_by_count":2,"area":null},{"id":"2506.15307","title":"SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPC","created":"2025-06-18","cited_by_count":1,"area":null},{"id":"2510.12343","title":"Traveling Salesman-Based Token Ordering Improves Stability in Homomorphically Encrypted Language Models","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2602.01621","title":"CGF-Softmax: A Cumulant-Based Softmax Reformulation for Efficient Inference under Homomorphic Encryption","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2603.02214","title":"Federated Inference: Toward Privacy-Preserving Collaborative and Incentivized Model Serving","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2606.16801","title":"The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Models","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2512.04580","title":"CryptoTensors: A Light-Weight Large Language Model File Format for Highly-Secure Model Distribution","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2606.03399","title":"Selective Token-Level Cryptographic Redaction for Privacy-Preserving Clinical Deployment of Large Language Models","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2609.01730","title":"HEAT: Faster Fully Homomorphic Inference via Approximations-Weights Co-Adaptation","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2610.19607","title":"A Graph-Based Analysis of Comparability, Scale, and Attribution in Private Transformer Inference","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}