Search Results for author:
Found 7 papers, 5 papers with code
Fast Adversarial Attacks on Language Models In One GPU Minute
Through human evaluations, we find that our untargeted attack causes Vicuna-7B-v1. 5 to produce ~15% more incorrect outputs when compared to LM outputs in the absence of our attack.
Boosting Adversarial Robustness using Feature Level Stochastic Smoothing
Advances in adversarial defenses have led to a significant improvement in the robustness of Deep Neural Networks.
Scaling Adversarial Training to Large Perturbation Bounds
The presence of images that flip Oracle predictions and those that do not makes this a challenging setting for adversarial robustness.
Towards Efficient and Effective Adversarial Training
The vulnerability of Deep Neural Networks to adversarial attacks has spurred immense interest towards improving their robustness.
Towards Achieving Adversarial Robustness Beyond Perceptual Limits
The presence of images that flip Oracle predictions and those that do not, makes this a challenging setting for adversarial robustness.
Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses
Further, we propose Guided Adversarial Training (GAT), which achieves state-of-the-art performance amongst single-step defenses by utilizing the proposed relaxation term for both attack generation and training.
Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes
In this work, we attempt to address this problem by training networks to form coarse impressions based on the information in higher bit planes, and use the lower bit planes only to refine their prediction.
