22 citations · 44 across the 18 of their papers we have counts for
10 papers · 1 filter
Robust Reward Modeling via Causal Rubrics
Pragya Srivastava, Harman Singh, Rahul Madhavan +9
Reward models (RMs) are fundamental to aligning Large Language Models (LLMs) via human feedback, yet they often suffer from reward hacking. They tend to latch on to superficial or…
ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representations
Sravanti Addepalli, Priyam Dey, R. Venkatesh Babu
The need for abundant labelled data in supervised Adversarial Training (AT) has prompted the use of Self-Supervised Learning (SSL) techniques with AT. However, the direct applicati…
Boosting Adversarial Robustness using Feature Level Stochastic Smoothing
Sravanti Addepalli, Samyak Jain, Gaurang Sriramanan +1
Advances in adversarial defenses have led to a significant improvement in the robustness of Deep Neural Networks. However, the robust accuracy of present state-ofthe-art defenses i…
Certified Adversarial Robustness Within Multiple Perturbation Bounds
Soumalya Nandi, Sravanti Addepalli, Harsh Rangwani +1
Randomized smoothing (RS) is a well known certified defense against adversarial attacks, which creates a smoothed classifier by predicting the most likely class under random noise…
DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks
Samyak Jain, Sravanti Addepalli, Pawan Sahu +2
Generalization of neural networks is crucial for deploying them safely in the real world. Common training strategies to improve generalization involve the use of data augmentations…
Efficient and Effective Augmentation Strategy for Adversarial Training
Sravanti Addepalli, Samyak Jain, R. Venkatesh Babu
Adversarial training of Deep Neural Networks is known to be significantly more data-hungry when compared to standard training. Furthermore, complex data augmentations such as AutoA…
Scaling Adversarial Training to Large Perturbation Bounds
Sravanti Addepalli, Samyak Jain, Gaurang Sriramanan +1
The vulnerability of Deep Neural Networks to Adversarial Attacks has fuelled research towards building robust models. While most Adversarial Training algorithms aim at defending at…
Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networks
Sravanti Addepalli, Anshul Nasery, R. Venkatesh Babu +2
Deep Neural Networks are known to be brittle to even minor distribution shifts compared to the training distribution. While one line of work has demonstrated that Simplicity Bias (…
DAFT: Distilling Adversarially Fine-tuned Models for Better OOD Generalization
Anshul Nasery, Sravanti Addepalli, Praneeth Netrapalli +1
We consider the problem of OOD generalization, where the goal is to train a model that performs well on test distributions that are different from the training distribution. Deep l…
DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier
Sravanti Addepalli, Gaurav Kumar Nayak, Anirban Chakraborty +1
In this era of digital information explosion, an abundance of data from numerous modalities is being generated as well as archived everyday. However, most problems associated with…