7 citations · 19 across the 9 of their papers we have counts for
10 papers
Improving Membership Inference in ASR Model Auditing with Perturbed Loss Features
Francisco Teixeira, Karla Pizzi, Raphael Olivier +3
Membership Inference (MI) poses a substantial privacy threat to the training data of Automatic Speech Recognition (ASR) systems, while also offering an opportunity to audit these m…
LoFT: Local Proxy Fine-tuning For Improving Transferability Of Adversarial Attacks Against Large Language Model
Muhammad Ahmed Shah, Roshan Sharma, Hira Dhamyal +10
It has been shown that Large Language Model (LLM) alignments can be circumvented by appending specially crafted attack suffixes with harmful queries to elicit harmful responses. To…
There is more than one kind of robustness: Fooling Whisper with adversarial examples
Raphael Olivier, Bhiksha Raj
Whisper is a recent Automatic Speech Recognition (ASR) model displaying impressive robustness to both out-of-distribution inputs and random noise. In this work, we show that this r…
Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition models
Raphael Olivier, Hadi Abdullah, Bhiksha Raj
A targeted adversarial attack produces audio samples that can force an Automatic Speech Recognition (ASR) system to output attacker-chosen text. To exploit ASR models in real-world…
How many perturbations break this model? Evaluating robustness beyond adversarial accuracy
Raphael Olivier, Bhiksha Raj
Robustness to adversarial attacks is typically evaluated with adversarial accuracy. While essential, this metric does not capture all aspects of robustness and in particular leaves…
Recent improvements of ASR models in the face of adversarial attacks
Raphael Olivier, Bhiksha Raj
Like many other tasks involving neural networks, Speech Recognition models are vulnerable to adversarial attacks. However recent research has pointed out differences between attack…
Sequential Randomized Smoothing for Adversarially Robust Speech Recognition
Raphael Olivier, Bhiksha Raj
While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partial…
Exploiting Non-Linear Redundancy for Neural Model Compression
Muhammad A. Shah, Raphael Olivier, Bhiksha Raj
Deploying deep learning models, comprising of non-linear combination of millions, even billions, of parameters is challenging given the memory, power and compute constraints of the…
In-training Matrix Factorization for Parameter-frugal Neural Machine Translation
Zachary Kaden, Teven Le Scao, Raphael Olivier
In this paper, we propose the use of in-training matrix factorization to reduce the model size for neural machine translation. Using in-training matrix factorization, parameter mat…
Retrieval-Based Neural Code Generation
Shirley Anugrah Hayati, Raphael Olivier, Pravalika Avvaru +3
In models to generate program source code from natural language, representing this code in a tree structure has been a common approach. However, existing methods often fail to gene…