Tag: adversarial robustness
Browse our exclusive articles!
AGFT: Boost Zero-Shot Adversarial Robustness in VLMs
Enhance zero-shot adversarial robustness of vision-language models with AGFT's alignment-guided fine-tuning preserving cross-modal integrity.
Max Second Derivative of Activations & Adversarial Robustness
Explore how the max second derivative of activation functions impacts neural network adversarial robustness and model resilience.
Key Concrete Problems in AI Safety Research
Explore key concrete problems in AI safety, focusing on robustness, interpretability, value alignment, and scalable solutions for secure AI systems.
Transfer of Adversarial Robustness Across Perturbation Types
Explore how adversarial robustness transfers between perturbation types to enhance AI model resilience and improve training strategies.
Boost AI Security by Trading Inference Compute for Robustness
Enhance AI adversarial robustness by optimizing inference-time compute. Learn how increased compute improves security against attacks in AI models.