4 citations · 4 across the 4 of their papers we have counts for
4 papers
Revisiting Acoustic Features for Robust ASR
Muhammad A. Shah, Bhiksha Raj
Automatic Speech Recognition (ASR) systems must be robust to the myriad types of noises present in real-world environments including environmental noise, room impulse response, spe…
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…
Fixed Inter-Neuron Covariability Induces Adversarial Robustness
Muhammad Ahmed Shah, Bhiksha Raj
The vulnerability to adversarial perturbations is a major flaw of Deep Neural Networks (DNNs) that raises question about their reliability when in real-world scenarios. On the othe…
Training on Foveated Images Improves Robustness to Adversarial Attacks
Muhammad A. Shah, Bhiksha Raj
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks -- subtle, perceptually indistinguishable perturbations of inputs that change the response of th…