Christian Schlarmann
@chs20.bsky.social
ML PhD Student at Tübingen AI Center
📜Paper: arxiv.org/abs/2502.11725
Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics
Measuring perceptual similarity is a key tool in computer vision. In recent years perceptual metrics based on features extracted from neural networks with large and diverse training sets, e.g. CLIP, h...
arxiv.org
April 1, 2025 at 11:36 AM
📜Paper: arxiv.org/abs/2502.11725
In line with previous works, this shows that it is important to develop adaptive attacks against new defenses in order to claim robustness.
📜 arxiv.org/abs/2411.14834
📜 arxiv.org/abs/2411.14834
Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense
Ensemble everything everywhere is a defense to adversarial examples that was recently proposed to make image classifiers robust. This defense works by ensembling a model's intermediate representations...
arxiv.org
February 11, 2025 at 2:24 PM
In line with previous works, this shows that it is important to develop adaptive attacks against new defenses in order to claim robustness.
📜 arxiv.org/abs/2411.14834
📜 arxiv.org/abs/2411.14834