Search Results for author:
Found 7 papers, 2 papers with code
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
We address this research gap and propose the embedding space attack, which directly attacks the continuous embedding representation of input tokens.
In-Context Learning Can Re-learn Forbidden Tasks
Specifically, we investigate whether in-context learning (ICL) can be used to re-learn forbidden tasks despite the explicit fine-tuning of the model to refuse them.
Adversarial Attacks and Defenses in Large Language Models: Old and New Threats
Here, one major impediment has been the overestimation of the robustness of new defense approaches due to faulty defense evaluations.
Raising the Bar for Certified Adversarial Robustness with Diffusion Models
In this work, we demonstrate that a similar approach can substantially improve deterministic certified defenses.
Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features
Moreover, our second approach does not require either large batches or full deterministic gradients, which is a typical weakness of many techniques for finite-sum problems.
Dissecting adaptive methods in GANs
By considering an update rule with the magnitude of the Adam update and the normalized direction of SGD, we empirically show that the adaptive magnitude of Adam is key for GAN training.
Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise
In this work, we prove the first high-probability complexity results with logarithmic dependence on the confidence level for stochastic methods for solving monotone and structured non-monotone VIPs with non-sub-Gaussian (heavy-tailed) noise and unbounded domains.
