11 citations · 19 across the 6 of their papers we have counts for
6 papers · 1 filter
What Makes and Breaks Safety Fine-tuning? A Mechanistic Study
Samyak Jain, Ekdeep Singh Lubana, Kemal Oksuz +4
Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via…
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
Samyak Jain, Robert Kirk, Ekdeep Singh Lubana +5
Fine-tuning large pre-trained models has become the de facto strategy for developing both task-specific and general-purpose machine learning systems, including developing models th…
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…
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…