adversarial robustness
Adversarial robustness refers to the ability of an AI model to maintain its performance in the presence of adversarial attacks or modifications aimed at misleading its predictions.
- Adversarial Robustness of Nonparametric Regression
- Adversarial generalization of unfolding (model-based) networks
- Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks
- Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks
- Enhancing Graph Classification Robustness with Singular Pooling
- Erasing Conceptual Knowledge from Language Models
- Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs
- Learning Robust Vision-Language Models from Natural Latent Spaces
- Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference
- ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search
- Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models
- Semi-infinite Nonconvex Constrained Min-Max Optimization
- Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers
- Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits
- VMDT: Decoding the Trustworthiness of Video Foundation Models
- Vulnerable Data-Aware Adversarial Training
- Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers