dedeswim
PhD Student @ethz-spylab | ETH Zürich | ML security & privacy | Maintainer of @robustbench
ETH ZürichSwitzerland
Pinned Repositories
AP_Libs
Advanced Programming course libraries
com-402-hw
Homework for the COM-402 Information Security and Privacy class @ EPFL
dedeswim.github.io
My personal website, hosted on GitHub Pages, built with Hugo
ee-556-hw
Homework for the EE-556 Mathematics of Data class @ EPFL
pytorch_influence_functions
This is a PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence Functions by Pang Wei Koh and Percy Liang.
vits-robustness-torch
Code for the paper "A Light Recipe to Train Robust Vision Transformers" [SaTML 2023]
realistic-adv-examples
Code for the paper "Evading Black-box Classifiers Without Breaking Eggs" [SaTML 2024]
satml-llm-ctf
Code used to run the platform for the LLM CTF colocated with SaTML 2024
jailbreakbench
An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]
robustbench
RobustBench: a standardized adversarial robustness benchmark [NeurIPS'21 Benchmarks and Datasets Track]
dedeswim's Repositories
dedeswim/vits-robustness-torch
Code for the paper "A Light Recipe to Train Robust Vision Transformers" [SaTML 2023]
dedeswim/com-402-hw
Homework for the COM-402 Information Security and Privacy class @ EPFL
dedeswim/dedeswim.github.io
My personal website, hosted on GitHub Pages, built with Hugo
dedeswim/ee-556-hw
Homework for the EE-556 Mathematics of Data class @ EPFL
dedeswim/pytorch_influence_functions
This is a PyTorch reimplementation of Influence Functions from the ICML2017 best paper: Understanding Black-box Predictions via Influence Functions by Pang Wei Koh and Percy Liang.
dedeswim/AP_Libs
Advanced Programming course libraries
dedeswim/db-spark-projects
EPFL Database Systems Project 2
dedeswim/ml_project_1
Project 1 of the Machine Learning course at EPFL.
dedeswim/auto-attack
Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
dedeswim/cv
My personal CV
dedeswim/dedeswim
Personal README
dedeswim/dotfiles
My dotfiles (mainly Nix-related)
dedeswim/go
Gitlinks repository (uses https://github.com/lengstrom/gitlinks)
dedeswim/hugo-personal-website
Hugo website content repository. Built with Hugo.
dedeswim/litellm
Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)
dedeswim/pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
dedeswim/robustbench
RobustBench: a standardized adversarial robustness benchmark [arXiv, Oct 2020]
dedeswim/ViTs-vs-CNNs
[NeurIPS 2021]: Are Transformers More Robust Than CNNs? (Pytorch implementation & checkpoints)