Tag: AI model robustness
Browse our exclusive articles!
Adversarial Influence on LLM Latent Spaces Using Persistent Homology
Explore how persistent homology reveals adversarial impacts on LLM latent spaces, enhancing AI interpretability and security across model architectures.
Enhancing LLM Security with Sparse Autoencoders
Discover how integrating Sparse Autoencoders boosts Large Language Models' robustness, reducing jailbreak attacks by up to 5x without altering weights.
ROVA Boosts Video Reasoning Models for Real-World Use
Discover how ROVA improves video reasoning models' robustness and accuracy under real-world disturbances like weather and motion.
Efficient Adversarial Training with Criticality-Aware Fine-Tuning
Discover Criticality-Aware Adversarial Training (CAAT) for efficient, scalable robustness in Vision Transformers with minimal parameter fine-tuning.
Robust Data-Free Meta-Learning Against Task Shifts
Explore a robust framework for data-free meta-learning that tackles task-distribution shifts and model corruption for reliable few-shot learning.