Visiting Researcher talk: Dr Fazl Barez 05 May2025

Dr. Fazl Barez’ recent talk at NTU, “Open Problems in Machine Unlearning for AI Safety” delved into the challenges and limitations of machine unlearning as a tool for ensuring AI safety. While machine unlearning is often employed to selectively suppress specific types of knowledge to align AI models with particular use cases, Dr. Barez cautioned against several limitations of this approach. One concern highlighted during the talk is associated with the “pluralistic nature” of knowledge. AI models, even after unlearning specific data, may inadvertently recombine pieces of information to generate dangerous insights. This raises ethical and practical questions, as suppressing such knowledge might also hinder valuable applications. Dr. Barez described the unintended side effects of unlearning, which could degrade a model’s ability to perform useful tasks. Additionally, he noted that assessing the effectiveness of machine unlearning remains a significant challenge, as AI models may retain traces of removed knowledge or relearn it through indirect means. During the Q&A session, Dr. Barez emphasised that unlearning alone cannot serve as a “silver bullet” for AI safety. He encouraged NTU researchers to reflect on this open problem, pursue further research into alternative approaches, and explore how the concepts presented could be integrated into practical applications within the broader frameworks of their own studies.