robustness

A unified evaluation framework for large language models

Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

Raising the Cost of Malicious AI-Powered Image Editing

Fiddler Auditor is a tool to evaluate language models.

Contains code for the paper "Vision Transformers are Robust Learners" (AAAI 2022).

The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now". This work introduces one fast and effective attack method to evaluate the harmful-content generation ability of safety-driven unlearned diffusion models.

OOD Generalization and Detection (ACL 2020)

[CVPR 2024] The official implementation of paper "synthesize, diagnose, and optimize: towards fine-grained vision-language understanding"

This repository contains the code for our upcoming paper An Investigation of End-to-End Models for Robust Speech Recognition at ICASSP 2021.

[CVPR 2024 Highlight] ImageNet-D

Biologically-grounded adversarial training platform: cyclic Wake/Dream/Nightmare/Compress phases that accumulate model robustness without catastrophic forgetting. Dockerized, EU AI Act compliance reporting.

[ICML 2025] Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning