Program

June 21, 2024

Welcome (Co-chairs) 

Keynote Talk:  Modeling and Security Analysis of Attacks on Machine Learning Systems

(Anoop Singhal)  

Coffee Break along with CODASPY 2024 

Session 1: Privacy I

Transformer-based Language Models and Homomorphic Encryption: An Intersection with BERT-tiny  

(Lorenzo Rovida and Alberto Leporati) 

Legally Binding but Unfair? Towards Assessing Fairness of Privacy Policies   

(Vincent Freiberger and Erik Buchmann) 

1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy     

(Stephen Meisenbacher, Maulik Chevli and Florian Matthes) 

Lunch Break

Session 2: Fake Audio (Tutorial)

Review of Existing Methods for Generating and Detecting Fake and Partially Fake Audio    

(Abdulazeez Alali and George Theodorakopoulos) 

Session 3: Attacks and Vulnerabilities

LLMs for Explainable Few-shot Deception Detection

(Dainis Boumber, Bryan Tuck, Rakesh M. Verma and Fatima Zahra Qachfar) 

Evaluating Large Language Models for Real-World Vulnerability Repair in C/C++ Code  

(Lan Zhang, Qingtian Zou, Anoop Singhal, Xiaoyan Sun and Peng Liu) 

Domain Independent Deception Detection: Feature Sets, LIWC Efficacy, and Synthetic Data Challenges   

(Casey Hanks, Shanina Ko, Emily Nguyen and Rakesh Verma) 

Coffee Break

Session 4: Privacy II

Privacy-Enhancing Technologies for AI Systems: A Tutorial

(Liv D'Aliberti, Evan Gronberg and Joseph Kovba)

Machine Learning Training on Encrypted Data with TFHE

(Luis Montero, Jordan Frery, Celia Kherfallah, Roman Bredehoft and Andrei Stoian)

Closing Remarks (Cochairs)