← Search

Naman D. Singh

2 accepted papers

2024

Towards Reliable Evaluation and Fast Training of Robust Semantic Segmentation Models

ECCV 2024poster

"Adversarial robustness has been studied extensively in image classification, especially for the ℓ∞ -threat model, but significantly less so for related tasks such as object detection and semantic segmentation, where attacks turn out to be a much harder optimization problem than for image classifica…

2022

Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks

AAAI 2022technical

We propose a versatile framework based on random search, Sparse-RS, for score-based sparse targeted and untargeted attacks in the black-box setting. Sparse-RS does not rely on substitute models and achieves state-of-the-art success rate and query efficiency for multiple sparse attack models: L0-boun…