Sravanti Addepalli

Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?

Sravanti Addepalli, Yerram Varun, Arun Sai Suggala, Prateek Jain

Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While the large dimensionality of input token space makes …

Time-Reversal Provides Unsupervised Feedback to LLMs

Yerram Varun, Rahul Madhavan, Sravanti Addepalli, Arun Sai Suggala et autres

Large Language Models (LLMs) are typically trained to predict in the forward direction of time. However, recent works have shown that prompting these models to look back and critique their own generations can produce useful feedback. Motivated by this, we explore the …

Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification

Sravanti Addepalli, Ashish Ramayee Asokan, Lakshay Sharma, R. Venkatesh Babu

Vision-Language Models (VLMs) such as CLIP are trained on large amounts of image-text pairs, resulting in remarkable generalization across several data distributions. However, in several cases, their expensive training and data collection/curation costs do not justify the end application. This motivates a …

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 application of existing SSL methods to adversarial training has been sub-optimal due to the increased training complexity …

Time-Reversal Provides Unsupervised Feedback to LLMs

Varun Yerram, Rahul Madhavan, Sravanti Addepalli, Karthikeyan Shanmugam et autres

Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification

Sravanti Addepalli, Ashish Ramayee Asokan, Lakshay Sharma, R. Venkatesh Babu

Vision-Language Models (VLMs) such as CLIP are trained on large amounts of image-text pairs, resulting in remarkable generalization across several data distributions. However, in several cases, their expensive training and data collection/curation costs do not justify the end application. This motivates a …

Boosting Adversarial Robustness using Feature Level Stochastic Smoothing

Sravanti Addepalli, Samyak Jain, Gaurang Sriramanan, R. Venkatesh Babu

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 is far from the requirements in critical applications such as robotics and autonomous navigation systems. Further, in …

Certified Adversarial Robustness Within Multiple Perturbation Bounds

Soumalya Nandi, Sravanti Addepalli, Harsh Rangwani, R. Venkatesh Babu

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 perturbations of inputs during inference. While initial work focused on robustness to ℓ2norm perturbations using noise …

in (code pays fourni par la source)

RMLVQA: A Margin Loss Approach For Visual Question Answering with Language Biases

Abhipsa Basu, Sravanti Addepalli, R. Venkatesh Babu

Visual Question Answering models have been shown to suffer from language biases, where the model learns a correlation between the question and the answer, ignoring the image. While early works attempted to use question-only models or data augmentations to reduce this bias, …

in (code pays fourni par la source)

DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks

Samyak Jain, Sravanti Addepalli, Pawan Kumar Sahu, Priyam Dey et autres

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, ensembling and model averaging. In this work, we first establish a surprisingly simple but strong benchmark …

in (code pays fourni par la source)

Certified Adversarial Robustness Within Multiple Perturbation Bounds

Soumalya Nandi, Sravanti Addepalli, Harsh Rangwani, R. Venkatesh Babu

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 perturbations of inputs during inference. While initial work focused on robustness to $\ell_2$ norm perturbations using …

DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks

Samyak Jain, Sravanti Addepalli, Pawan Kumar Sahu, Priyam Dey et autres

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, ensembling and model averaging. In this work, we first establish a surprisingly simple but strong benchmark …