SafeMERGE: Preserving Safety Alignment in Fine-Tuned Large Language Models via Selective Layer-Wise Model MergingAladin DjuheraSwanand Ravindra Kadheet al.2025ICLR 2025
Workshop on Data Integrity and Secure Cloud Computing (DISCC)Pradip BoseAugusto Vegaet al.2025HPCA 2025
Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented GenerationMaya AndersonGuy Amitet al.2025ICISSP 2025
Polynomial Adaptation of Large-Scale CNNs for Homomorphic Encryption-Based Secure InferenceMoran BaruchNir Druckeret al.2024CSCML 2024
Mezzo TLS 1.3 Protocol, Suitable for Transmitting Already-Encrypted DataNir DruckerShai Gueron2024CSCML 2024
A Secure Multiparty Computation Platform for Squeaky-Clean Data RoomsPankaj DayamaVinayaka Panditet al.2024CCS 2024
Exploring Vulnerabilities in LLMs: A Red Teaming Approach to Evaluate Social BiasYuya Jeremy OngJay Pankaj Galaet al.2024IEEE CISOSE 2024
Securing AI Inference in the Cloud: Is CPU-GPU Confidential Computing Ready ?Apoorve MohanMengmei Yeet al.2024CLOUD 2024