What's in Your "Safe" Data?: Identifying Benign Data that Breaks Safety

Current Large Language Models (LLMs), even those tuned for safety and alignment, are susceptible to jailbreaking. Some have found that just further fine-tuning an aligned model with benign data (i.e., data without harmful content) surprisingly leads to substantial degradation in safety. We delve into the data-centric aspects of why benign fine-tuning inadvertently contributes to jailbreaking. First, we represent fine-tuning data through two lenses: representation and gradient spaces. Furthermore, we propose a bi-directional anchoring method that prioritizes data points that are close to harmful examples and distant from benign ones. By doing so, our approach effectively identifies subsets of benign data that are more likely to degrade the model's safety after fine-tuning. Training on just 100 of these seemingly benign datapoints can lead to the fine-tuned model affirmatively responding to > 70% of tested harmful requests, compared to < 20% after fine-tuning on randomly selected data. We further find that selected data are often in the form of lists and bullet points, or math questions.

Aleatoric and Epistemic Discrimination in Classification

Machine learning (ML) models can underperform on certain population groups due to choices made during model development and bias inherent in the data. We categorize sources of discrimination in the ML pipeline into two classes: aleatoric discrimination, which is inherent in the data distribution, and epistemic discrimination, which is due to decisions during model development. We quantify aleatoric discrimination by determining the performance limits of a model under fairness constraints, assuming perfect knowledge of the data distribution. We demonstrate how to characterize aleatoric discrimination by applying Blackwell's results on comparing statistical experiments. We then quantify epistemic discrimination as the gap between a model's accuracy given fairness constraints and the limit posed by aleatoric discrimination. We apply this approach to benchmark existing interventions and investigate fairness risks in data with missing values. Our results indicate that state-of-the-art fairness interventions are effective at removing epistemic discrimination. However, when data has missing values, there is still significant room for improvement in handling aleatoric discrimination.