Search Results for author:
Found 5 papers, 3 papers with code
Defending LLMs against Jailbreaking Attacks via Backtranslation
The inferred prompt is called the backtranslated prompt which tends to reveal the actual intent of the original prompt, since it is generated based on the LLM's response and is not directly manipulated by the attacker.
Which Pretrain Samples to Rehearse when Finetuning Pretrained Models?
We propose a novel sampling scheme, mix-cd, that identifies and prioritizes samples that actually face forgetting, which we call collateral damage.
Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation
Data attribution methods trace model behavior back to its training dataset, offering an effective approach to better understand ''black-box'' neural networks.
Reducing Training Sample Memorization in GANs by Training with Memorization Rejection
In this paper, we propose memorization rejection, a training scheme that rejects generated samples that are near-duplicates of training samples during training.
Concept Gradient: Concept-based Interpretation Without Linear Assumption
We showed that for a general (potentially non-linear) concept, we can mathematically evaluate how a small change of concept affecting the model's prediction, which leads to an extension of gradient-based interpretation to the concept space.
