Related papers: SnapAudit: Active Auditing of Differentially Priva…

Decentralized Federated Learning (DFL) enables collaborative model training without a central server, but it remains vulnerable to privacy leakage because shared model updates can expose sensitive information through inversion,…

Large language models (LLMs) have exhibited striking in-context learning (ICL) ability to adapt to target tasks with a few input-output demonstrations. For better ICL, different methods are proposed to select representative demonstrations…

Empirical auditing has emerged as a means of catching some of the flaws in the implementation of privacy-preserving algorithms. Existing auditing mechanisms, however, are either computationally inefficient requiring multiple runs of the…

To protect privacy for data-collection-based services, local differential privacy (LDP) is widely adopted due to its rigorous theoretical bound on privacy loss. However, mistakes in complex theoretical analysis or subtle implementation…

The industry increasingly relies on deep learning (DL) technology for manufacturing inspections, which are challenging to automate with rule-based machine vision algorithms. DL-powered inspection systems derive defect patterns from labeled…

We present new auditors to assess Differential Privacy (DP) of an algorithm based on output samples. Such empirical auditors are common to check for algorithmic correctness and implementation bugs. Most existing auditors are batch-based or…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing but also pose significant privacy risks by memorizing and leaking Personally Identifiable Information (PII). Existing mitigation…

Users of modern Machine Learning (ML) cloud services face a privacy conundrum -- on one hand, they may have concerns about sending private data to the service for inference, but on the other hand, for specialized models, there may be no…

Log-based insider threat detection (ITD) detects malicious user activities by auditing log entries. Recently, large language models (LLMs) with strong common sense knowledge have emerged in the domain of ITD. Nevertheless, diverse activity…

The pretraining and fine-tuning approach has become the leading technique for various NLP applications. However, recent studies reveal that fine-tuning data, due to their sensitive nature, domain-specific characteristics, and…

Logic locking is a prominent technique to protect the integrity of hardware designs throughout the integrated circuit design and fabrication flow. However, in recent years, the security of locking schemes has been thoroughly challenged by…

Differential privacy (DP) is a widely used approach for mitigating privacy risks when training machine learning models on sensitive data. DP mechanisms add noise during training to limit the risk of information leakage. The scale of the…

In-Context Learning (ICL) empowers Large Language Models (LLMs) to tackle diverse tasks by incorporating multiple input-output examples, known as demonstrations, into the input of LLMs. More recently, advancements in the expanded context…

Split learning (SL) aims to protect user data privacy by distributing deep models between client-server and keeping private data locally. Only processed or `smashed' data can be transmitted from the clients to the server during the SL…

Smart meter devices enable a better understanding of the demand at the potential risk of private information leakage. One promising solution to mitigating such risk is to inject noises into the meter data to achieve a certain level of…

Differential privacy (DP) is widely employed to provide privacy protection for individuals by limiting information leakage from the aggregated data. Two well-known models of DP are the central model and the local model. The former requires…

Differentially private synthetic data generation (DP-SDG) algorithms are used to release datasets that are structurally and statistically similar to sensitive data while providing formal bounds on the information they leak. However, bugs in…

In-context learning (ICL) is an emerging capability of large autoregressive language models where a few input-label demonstrations are appended to the input to enhance the model's understanding of downstream NLP tasks, without directly…

The growing trend of legal disputes over the unauthorized use of data in machine learning (ML) systems highlights the urgent need for reliable data-use auditing mechanisms to ensure accountability and transparency in ML. We present the…

Recent developments have underscored the critical role of \textit{differential privacy} (DP) in safeguarding individual data for training machine learning models. However, integrating DP oftentimes incurs significant model performance…