Search Results for author:
Found 13 papers, 12 papers with code
Merging Improves Self-Critique Against Jailbreak Attacks
The robustness of large language models (LLMs) against adversarial manipulations, such as jailbreak attacks, remains a significant challenge.
Configurable Safety Tuning of Language Models with Synthetic Preference Data
State-of-the-art language model fine-tuning techniques, such as Direct Preference Optimization (DPO), restrict user control by hard-coding predefined behaviors into the model.
Distilled Self-Critique of LLMs with Synthetic Data: a Bayesian Perspective
This paper proposes an interpretation of RLAIF as Bayesian inference by introducing distilled Self-Critique (dSC), which refines the outputs of a LLM through a Gibbs sampler that is later distilled into a fine-tuned model.
Fast Adaptation with Bradley-Terry Preference Models in Text-To-Image Classification and Generation
Recently, large multimodal models, such as CLIP and Stable Diffusion have experimented tremendous successes in both foundations and applications.
Personalizing Text-to-Image Generation via Aesthetic Gradients
This work proposes aesthetic gradients, a method to personalize a CLIP-conditioned diffusion model by guiding the generative process towards custom aesthetics defined by the user from a set of images.
Protecting Classifiers From Attacks. A Bayesian Approach
Classification problems in security settings are usually modeled as confrontations in which an adversary tries to fool a classifier manipulating the covariates of instances to obtain a benefit.
Adversarial Machine Learning: Bayesian Perspectives
Adversarial Machine Learning (AML) is emerging as a major field aimed at protecting machine learning (ML) systems against security threats: in certain scenarios there may be adversaries that actively manipulate input data to fool learning systems.
Variationally Inferred Sampling Through a Refined Bound
A framework for efficient Bayesian inference in probabilistic programs is introduced by embedding a sampler inside a variational posterior approximation.
Variationally Inferred Sampling Through a Refined Bound for Probabilistic Programs
A framework to boost the efficiency of Bayesian inference in probabilistic programs is introduced by embedding a sampler inside a variational posterior approximation.
Opponent Aware Reinforcement Learning
We introduce Threatened Markov Decision Processes (TMDPs) as an extension of the classical Markov Decision Process framework for Reinforcement Learning (RL).
Stochastic Gradient MCMC with Repulsive Forces
We propose a unifying view of two different Bayesian inference algorithms, Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) and Stein Variational Gradient Descent (SVGD), leading to improved and efficient novel sampling schemes.
Reinforcement Learning under Threats
In several reinforcement learning (RL) scenarios, mainly in security settings, there may be adversaries trying to interfere with the reward generating process.
