Furong's Lab

ARMA-Networks

Dynamics-Aware-Robust-Training

ICLR 2023 paper "Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness" by Yuancheng Xu, Yanchao Sun, Micah Goldblum, Tom Goldstein and Furong Huang

Mementos

paad_adv_rl

Code for ICLR 2022 publication: Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL. https://openreview.net/forum?id=JM2kFbJvvI

perceptionCLIP

Code for our ICLR 2024 paper "PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts"

SWIFT

SWIFT: Shared WaIt Free Transmission

tuformer

VLM-Poisoning

Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"

WAVES

Code for our paper "Benchmarking the Robustness of Image Watermarks"

WocaR-RL

Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning

umd-huang-lab/WAVES

Code for our paper "Benchmarking the Robustness of Image Watermarks"

umd-huang-lab/perceptionCLIP

Code for our ICLR 2024 paper "PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts"

umd-huang-lab/tracevla

umd-huang-lab/VLM-Poisoning

Code for Neurips 2024 paper "Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models"

umd-huang-lab/Mementos

umd-huang-lab/Dynamics-Aware-Robust-Training

ICLR 2023 paper "Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness" by Yuancheng Xu, Yanchao Sun, Micah Goldblum, Tom Goldstein and Furong Huang

umd-huang-lab/WocaR-RL

Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning

umd-huang-lab/SWIFT

SWIFT: Shared WaIt Free Transmission

umd-huang-lab/ARMA-Networks

umd-huang-lab/paad_adv_rl

Code for ICLR 2022 publication: Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL. https://openreview.net/forum?id=JM2kFbJvvI

umd-huang-lab/SIMA

umd-huang-lab/tuformer

umd-huang-lab/private-topic-model-tensor-methods

We provide an end-to-end differentially pri- vate spectral algorithm for learning LDA, based on matrix/tensor decompositions, and establish theoretical guarantees on util- ity/consistency of the estimated model pa- rameters. The spectral algorithm consists of multiple algorithmic steps, named as “edges”, to which noise could be injected to obtain differential privacy. We identify subsets of edges, named as “configurations”, such that adding noise to all edges in such a subset guarantees differential privacy of the end-to-end spectral algorithm. We character- ize the sensitivity of the edges with respect to the input and thus estimate the amount of noise to be added to each edge for any required privacy level. We then character- ize the utility loss for each configuration as a function of injected noise. Overall, by com- bining the sensitivity and utility characteri- zation, we obtain an end-to-end differentially private spectral algorithm for LDA and iden- tify the corresponding configuration that out- performs others in any specific regime. We are the first to achieve utility guarantees un- der the required level of differential privacy for learning in LDA. Overall our method sys- tematically outperforms differentially private variational inference.

umd-huang-lab/cmarl_ame

Implementation of ICLR'23 publication "Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication".

umd-huang-lab/Tensorial-Neural-Networks

We implement tensorial neural networks (TNNs), a generalization of existing neural networks by extending tensor operations on low order operands to those on high order operands.

umd-huang-lab/transfer-fairness

A self-training method for transferring fairness under distribution shifts.

umd-huang-lab/Transfer-Q

Official repository of the paper "Transfer Q Star: Principled Decoding for LLM Alignment"

umd-huang-lab/transfer_across_obs

Code for paper "Transfer RL across Observation Feature Spaces via Model-Based Regularization". https://openreview.net/forum?id=7KdAoOsI81C

umd-huang-lab/Easy2Hard-Bench

Official repository of the paper "Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization" in NeurIPS 2024 Track Datasets and Benchmarks

umd-huang-lab/PROTECTED

Code for paper "Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies" by Xiangyu Liu, Chenghao Deng, Yanchao Sun, Yongyuan Liang, Furong Huang

umd-huang-lab/RealFM

Repository for RealFM: A Realistic Mechanism to Incentivize Federated Participation and Contribution

umd-huang-lab/COPlanner

umd-huang-lab/FalseRefusal

Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models

umd-huang-lab/ortho-conv

umd-huang-lab/poison-rl

Code for paper Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics. https://arxiv.org/abs/2009.00774

umd-huang-lab/ELBERT

Official Implementation of the paper "Equal Long-term Benefit Rate: Adapting Static Fairness Notions to Sequential Decision Making" by Yuancheng Xu, Chenghao Deng, Yanchao Sun, Ruijie Zheng, Xiyao Wang, Jieyu Zhao and Furong Huang.

umd-huang-lab/evasion-rl

umd-huang-lab/PDML

umd-huang-lab/PRISE

umd-huang-lab/TACO

Code for "TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning"