← Authors

Jonas Geiping

40 papers · 2019–2026 · 9 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge 🌍 Conference Polyglot (8) πŸƒ Academic Marathon (6) 🐝 Cross-Pollinator (12) πŸ—ΊοΈ Taxonomy Completionist (60) 🧭 Keyword Pioneer 🀝 Dynamic Duo (32) πŸ† Grand Slam πŸ‘‘ Triple Crown πŸ”¬ Deep Specialist (10) πŸ’Ž Century Club (39) ⚑ Prolific Year (17) πŸ”₯ Unstoppable (7) ❓ The Questioner (6) πŸ—ƒοΈ Keyword Collector (129)

Conferences

NIPS (15) ICLR (12) ICML (6) CVPR (2) AAAI (1) ACL (1) ICCV (1) NAACL (1) SEMEVAL (1)

Top co-authors

Tom Goldstein (32) Micah Goldblum (21) Yuxin Wen (9) John Kirchenbauer (7) Gowthami Somepalli (7) Arpit Bansal (5) Avi Schwarzschild (5) Michael Moeller (5) Hong-Min Chu (4) Aniruddha Saha (4)

Research topics

Privacy (3)

Keywords

large language model (4) data poisoning (4) generative model (3) neural network (3) diffusion model (3) vision-language model (3) prompt augmentation (2) training datum (2) visual word sense disambiguation (2) in-context learning (2) privacy attack (2) privacy protection (2) text-to-image diffusion (2) adversarial attack (2) text generation (2) zero-shot learning (2) instruction tuning (2) poisoning attack (2) copyright protection (2) data replication (2)

Papers

MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation AAAI 2026
LLM-Generated Passphrases That Are Secure and Easy to Remember NAACL 2025
An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks ICML 2025
When, Where and Why to Average Weights? ICML 2025
Great Models Think Alike and this Undermines AI Oversight ICML 2025
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text ICML 2024
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs NIPS 2024
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models NIPS 2024
CALVIN: Improved Contextual Video Captioning via Instruction Tuning NIPS 2024
Transformers Can Do Arithmetic with the Right Embeddings NIPS 2024
Object Recognition as Next Token Prediction CVPR 2024
NEFTune: Noisy Embeddings Improve Instruction Finetuning ICLR 2024
Universal Guidance for Diffusion Models ICLR 2024
On the Reliability of Watermarks for Large Language Models ICLR 2024
Cramming: Training a Language Model on a single GPU in one day. ICML 2023
Augmenters at SemEval-2023 Task 1: Enhancing CLIP in Handling Compositionality and Ambiguity for Zero-Shot Visual WSD through Prompt Augmentation and Text-To-Image Diffusion ACL 2023
Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models CVPR 2023
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries ICLR 2023
Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent ICLR 2023
A Watermark for Large Language Models ICML 2023
Augmenters at SemEval-2023 Task 1: Enhancing CLIP in Handling Compositionality and Ambiguity for Zero-Shot Visual WSD through Prompt Augmentation and Text-To-Image Diffusion SEMEVAL 2023
A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning NIPS 2023
Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise NIPS 2023
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models ICLR 2023
How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization ICLR 2023
Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation ICLR 2023
Understanding and Mitigating Copying in Diffusion Models NIPS 2023
Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery NIPS 2023
Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images NIPS 2023
On the Exploitability of Instruction Tuning NIPS 2023
What Can We Learn from Unlearnable Datasets? NIPS 2023
Autoregressive Perturbations for Data Poisoning NIPS 2022
Stochastic Training is Not Necessary for Generalization ICLR 2022
Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models ICLR 2022
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching ICLR 2021
Adversarial Examples Make Strong Poisons NIPS 2021
MetaPoison: Practical General-purpose Clean-label Data Poisoning NIPS 2020
Truth or backpropaganda? An empirical investigation of deep learning theory ICLR 2020
Inverting Gradients - How easy is it to break privacy in federated learning? NIPS 2020
Parametric Majorization for Data-Driven Energy Minimization Methods ICCV 2019