AI Security
New research reveals how adversarial attacks can manipulate AI explanation systems to mislead human decision-makers, with critical implications for content authenticity verification.
LLM Interpretability
New research presents evidence that LLM self-explanations can help predict model behavior, offering a positive case for faithfulness in AI interpretability.
Explainable AI
New research combines deep neural networks with Answer Set Programming to generate human-readable explanations for AI decisions, advancing interpretability crucial for detection systems.
Explainable AI
Researchers introduce prompt-counterfactual explanations, a new method for understanding generative AI behavior by identifying minimal prompt changes that alter outputs.
AI alignment
New research proposes a cognitive architecture framework to address the 'black box' problem in AI systems, focusing on transparency, alignment, and interpretability through structured reasoning pathways.
neural networks
Researchers develop breakthrough verification method that accelerates neural network explanation validation by an order of magnitude, enabling more reliable AI systems for content authentication and deepfake detection applications.
AI transparency
Researchers propose comprehensive workflow for tracking AI decision-making processes from data input to final output, addressing transparency and accountability challenges in modern AI systems through systematic documentation and verification methods.