2024 Proceeding- Program Chairs:
- Hongxin Hu,
- Andrew Sung,
- Rakesh M. Verma
It is our great pleasure to welcome you to the 2024 ACM International Workshop on Security and Privacy Analytics - IWSPA 2024. This year's workshop is the tenth in the series and co-hosted with the Fourteenth ACM Annual Conference on Data and Applications Security and Privacy (CODASPY 2024).
IWSPA addresses important research topics associated with the application of data analytics tools and techniques (including statistical, machine/deep learning, data mining, and natural language processing) to challenges that arise with security and privacy preservation. IWSPA provides a forum for the interaction between researchers in these areas, identifying and pursuing new topics that arise in the intersection between the fields of Artificial Intelligence and Cybersecurity.
Proceeding Downloads
Modeling and Security Analysis of Attacks on Machine Learning Systems
The past several years have witnessed rapidly increasing use of machine learning (ML) systems in multiple industry sectors. Since security analysis is one of the most essential parts of the real-world ML system protection practice, there is an urgent ...
Transformer-based Language Models and Homomorphic Encryption: An Intersection with BERT-tiny
In recent years, emerging and improved Natural Language Processing (NLP) models, such as Bidirectional Encoder Representations from Transformers (BERT), have gained significant attention due to their performance on several natural language tasks. However,...
Legally Binding but Unfair? Towards Assessing Fairness of Privacy Policies
Privacy policies are expected to inform data subjects about their data protection rights and should explain the data controller's data management practices. Privacy policies only fulfill their purpose, if they are correctly interpreted, understood, and ...
1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy
The study of privacy-preserving Natural Language Processing (NLP) has gained rising attention in recent years. One promising avenue studies the integration of Differential Privacy in NLP, which has brought about innovative methods in a variety of ...
Review of Existing Methods for Generating and Detecting Fake and Partially Fake Audio
Using deep-learning technologies, both text-to-speech (TTS) and voice conversion (VC) methods can generate fake speech effectively, making it challenging to differentiate between real and fake speech. Accordingly, researchers have employed deepfake ...
LLMs for Explainable Few-shot Deception Detection
This study investigates the effectiveness of Large Language Models (LLMs) in detecting deception using a Retrieval Augmented Generation (RAG) framework for few-shot learning in domain-agnostic settings. Our approach combines the sophisticated reasoning ...
Evaluating Large Language Models for Real-World Vulnerability Repair in C/C++ Code
The advent of Large Language Models (LLMs) has enabled advancement in automated code generation, translation, and summarization. Despite their promise, evaluating the use of LLMs in repairing real-world code vulnerabilities remains underexplored. In this ...
Domain Independent Deception Detection: Feature Sets, LIWC Efficacy, and Synthetic Data Challenges
Deception is increasingly prevalent in the modern world, appearing in many different forms (domains) from phishing emails to fictitious product reviews, or even false political statements. Many researchers are looking for ways to identify deception ...
Privacy-Enhancing Technologies for AI Systems: A Tutorial
This tutorial presents privacy threats to artificially intelligent (AI) systems and proposes the use of several privacy-enhancing technologies (PETs) to address them. Such threats can affect both model owners and system users, be internal or external to ...
Machine Learning Training on Encrypted Data with TFHE
We present an approach for outsourcing the training of machine learning (ML) models while preserving data confidentiality from malicious parties. We use fully homomorphic encryption (FHE) to build a unified training framework that works on encrypted data ...