Farinaz Koushanfar — accepted AI-conference papers

2024

SelfVC: Voice Conversion With Iterative Refinement using Self Transformations

Paarth Neekhara, Shehzeen Samarah Hussain, Rafael Valle, Boris Ginsburg, Rishabh Ranjan, Shlomo Dubnov +2

ICML 2024poster

We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that separately encode speaker characteristics and linguistic content.…

Cited by 7 Source ↗PDF ↗Scholar ↗

2024

Token-Specific Watermarking with Enhanced Detectability and Semantic Coherence for Large Language Models

Mingjia Huo, Sai Ashish Somayajula, Youwei Liang, Ruisi Zhang, Farinaz Koushanfar, Pengtao Xie

ICML 2024poster

Large language models generate high-quality responses with potential misinformation, underscoring the need for regulation by distinguishing AI-generated and human-written texts. Watermarking is pivotal in this context, which involves embedding hidden markers in texts during the LLM inference phase,…

Cited by 19 Source ↗PDF ↗code ↗Scholar ↗

2023

zPROBE: Zero Peek Robustness Checks for Federated Learning

Zahra Ghodsi, Mojan Javaheripi, Nojan Sheybani, Xinqiao Zhang, Ke Huang, Farinaz Koushanfar

ICCV 2023poster

Privacy-preserving federated learning allows multiple users to jointly train a model with coordination of a central server. The server only learns the final aggregation result, thereby preventing leakage of the users' (private) training data from the individual model updates. However, keeping the in…

Cited by 19 PDF ↗Scholar ↗

2022

LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models

Mojan Javaheripi, Gustavo Henrique de Rosa, Subhabrata Mukherjee, Shital Shah, Tomasz Lukasz Religa, Caio Cesar Teodoro Mendes +3

NeurIPS 2022accept

The Transformer architecture is ubiquitously used as the building block of largescale autoregressive language models. However, finding architectures with the optimal trade-off between task performance (perplexity) and hardware constraints like peak memory utilization and latency is non-trivial. This…

Cited by 20 Source ↗PDF ↗code ↗Scholar ↗

2021

ProFlip: Targeted Trojan Attack With Progressive Bit Flips

Huili Chen, Cheng Fu, Jishen Zhao, Farinaz Koushanfar

ICCV 2021poster

The security of Deep Neural Networks (DNNs) is of great importance due to their employment in various safety-critical applications. DNNs are shown to be vulnerable against the Trojan attack that manipulates the model parameters via poisoned training and gets activated by the pre-defined trigger in i…

Cited by 97 PDF ↗Scholar ↗

2019

Coda: An End-to-End Neural Program Decompiler

Cheng Fu, Huili Chen, Haolan Liu, Xinyun Chen, Yuandong Tian, Farinaz Koushanfar +1

NeurIPS 2019poster

Reverse engineering of binary executables is a critical problem in the computer security domain. On the one hand, malicious parties may recover interpretable source codes from the software products to gain commercial advantages. On the other hand, binary decompilation can be leveraged for code vulne…

Cited by 87 Source ↗PDF ↗code ↗Scholar ↗