Knowledge distillation (KD) enables efficient deployment of deep learning models. However, it can increase privacy risks by making the student more vulnerable to membership inference attacks (MIAs), as the student may inherit patterns specific to the teacher’s private training data. Existing KD-based methods against MI...
Hyeon-Jin Jeong, Seok-Won Hong, Jae-Hwan Jeong et al.· International Conference on...· 0 citations
Streamlined Knowledge Distillation is proposed, a simple yet effective logit-based method that transfers only two essential forms of knowledge without requiring additional alignment or relational modeling and introduces a Mahalanobis distance-based direction-wise loss stabilized through Tikhonov regularization and Chol...
Current safety guard models for Large Language Models (LLMs) often fail to block complex Jailbreaking attacks because they focus on the structure of a prompt rather than its true intent. To evaluate this problem, we introduce the Role-Goal-Format (RGF) framework, which analyzes how the combination of a user’s persona,...
Jin-Seong Kim, Han-Ju Lee, Hyeon-Jin Jeong et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
