Related papers: Proteus: A Practical Framework for Privacy-Preserv…
A central issue in machine learning is how to train models on sensitive user data. Industry has widely adopted a simple algorithm: Stochastic Gradient Descent with noise (a.k.a. Stochastic Gradient Langevin Dynamics). However, foundational…
Chain-of-Thought (CoT) prompting improves LLM reasoning but can increase privacy risk by resurfacing personally identifiable information (PII) from the prompt into reasoning traces and outputs, even under policies that instruct the model…
We describe SAFIUS, a secure accountable file system that resides over an untrusted storage. SAFIUS provides strong security guarantees like confidentiality, integrity, prevention from rollback attacks, and accountability. SAFIUS also…
Many reconfigurable platforms require that applications be written specifically to take advantage of the reconfigurable hardware. In a PC-based environment, this presents an undesirable constraint in that the many already available…
We address the problem of secure data deletion on log-structured file systems. We focus on the YAFFS file system, widely used on Android smartphones. We show that these systems provide no temporal guarantees on data deletion and that…
End users face a choice between privacy and efficiency in current Large Language Model (LLM) service paradigms. In cloud-based paradigms, users are forced to compromise data locality for generation quality and processing speed. Conversely,…
The Deep Leakage from Gradient (DLG) attack has emerged as a prevalent and highly effective method for extracting sensitive training data by inspecting exchanged gradients. This approach poses a substantial threat to the privacy of…
With the wide adoption of handheld devices (e.g. smartphones, tablets) a large number of location-based services (also called LBSs) have flourished providing mobile users with real-time and contextual information on the move. Accounting for…
The mean time between failures (MTBF) of HPC systems is rapidly reducing, and that current failure recovery mechanisms e.g., checkpoint-restart, will no longer be able to recover the systems from failures. Early failure detection is a new…
We present the design, implementation and evaluation of a system, called MATRIX, developed to protect the privacy of mobile device users from location inference and sensor side-channel attacks. MATRIX gives users control and visibility over…
For the modeling, design and planning of future energy transmission networks, it is vital for stakeholders to access faithful and useful power flow data, while provably maintaining the privacy of business confidentiality of service…
Preserving privacy in sensitive data while pretraining large language models on small, domain-specific corpora presents a significant challenge. In this work, we take an exploratory step toward privacy-preserving continual pretraining by…
As mobile devices become ubiquitous, people around the world have enjoyed the convenience they have brought to our lives. At the same time, the increasing security threats that rise from using mobile devices not only have caught attention…
Protecting integrated circuits (ICs) from piracy and theft throughout their lifecycle is a persistent and complex challenge. In order to safeguard against illicit piracy attacks, this work proposes a novel framework utilizing Non-Fungible…
There are many approaches in mobile data ecosystem that inspect network traffic generated by applications running on user's device to detect personal data exfiltration from the user's device. State-of-the-art methods rely on features…
In this paper, we propose a new biometric verification and template protection system which we call the THRIVE system. The system includes novel enrollment and authentication protocols based on threshold homomorphic cryptosystem where the…
With the increasing use of conversational AI systems, there is growing concern over privacy leaks, especially when users share sensitive personal data in interactions with Large Language Models (LLMs). Conversations shared with these models…
Mobile computing devices have been used broadly to store, manage and process sensitive or even mission critical data. To protect confidentiality of data stored in mobile devices, major mobile operating systems use full disk encryption,…
We present the forensic analysis of the artifacts generated on Android smartphones by ChatSecure, a secure Instant Messaging application that provides strong encryption for transmitted and locally-stored data to ensure the privacy of its…
Membership Inference Attacks exploit the vulnerabilities of exposing models trained on customer data to queries by an adversary. In a recently proposed implementation of an auditing tool for measuring privacy leakage from sensitive…