GTSRB
PulseAugur coverage of GTSRB — every cluster mentioning GTSRB across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New backdoor attack exploits Vision MoE capacity overflow
Researchers have identified a new vulnerability in Mixture-of-Experts (MoE) architectures for Vision Transformers, termed 'Capacity Overflow'. This vulnerability stems from the batch-dependent token dispatch mechanism u…
-
New SaBRe framework enhances neural network verification for AI safety
Researchers have developed a new framework called SaBRe that uses a branch-and-bound approach to verify neural networks against relational specifications. This method is crucial for ensuring the safety of AI components …
-
New LAMDA framework boosts AI traffic sign recognition robustness
Researchers have developed a new training framework called LAMDA (Language-Anchored Model for Direction Alignment) to enhance the robustness of traffic sign recognition models in autonomous vehicles. This method uses la…
-
New research tackles adversarial robustness in deep neural networks
Several recent research papers explore novel methods for enhancing the adversarial robustness of deep neural networks. These studies introduce techniques such as ensemble-based approaches combining empirical and certifi…
-
New AI backdoor attack evades defenses by targeting data density
Researchers have developed a new backdoor attack method for AI models that is more resilient to post-training defenses like fine-tuning and pruning. The technique involves strategically placing triggered samples in low-…