Jonas Geiping
- A Watermark for Large Language Models
2023/01/24 by John Kirchenbauer, Jonas Geiping, Kirchenbauer, John +9 · 9 voices · 112 citations
Computer Science · #Adversarial Robustness in Machine Learning #Hate Speech and Cyberbullying Detection #Topic Modeling #cs.CL #cs.CR #cs.LG
- Latent Iteration as Renormalization: Inference-Time Recurrence in a Depth-Recurrent Transformer Flows Attention Geometry Toward the SYK Conformal Fixed Point
2025/02/07 by Jonas Geiping, Geiping, Jonas, Sean McLeish +16 · 25 voices · 89 citations
Computer Science · #Advanced Database Systems and Queries #Graph Theory and Algorithms #Natural Language Processing Techniques #cs.CL #cs.LG
- The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs
2025/09/11 by Akshit Sinha, Arvindh Arun, Sinha, Akshit +7 · 14 voices · 15 citations
Computer Science · #Topic Modeling #Explainable Artificial Intelligence (XAI) #Natural Language Processing Techniques
- Cramming: Training a Language Model on a Single GPU in One Day
2022/12/28 by Jonas Geiping, Tom Goldstein, Geiping, Jonas +1 · 8 voices · 7 citations
Computer Science · Engineering · #Advanced Neural Network Applications #Ferroelectric and Negative Capacitance Devices #Topic Modeling #cs.CL #cs.LG
- A Cookbook of Self-Supervised Learning
2023/04/24 by Randall Balestriero, Balestriero, Randall, Mark Ibrahim +36 · 2 voices · 34 citations
Computer Science · #Machine Learning and Data Classification
- Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models
2022/12/07 by Gowthami Somepalli, Vasu Singla, Somepalli, Gowthami +7 · 7 voices · 60 citations
Computer Science · Neuroscience · #Generative Adversarial Networks and Image Synthesis #Digital Media Forensic Detection #Aesthetic Perception and Analysis
- Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
2024/01/22 by Abhimanyu Hans, Avi Schwarzschild, Hans, Abhimanyu +13 · 2 voices · 62 citations
Computer Science · #Natural Language Processing Techniques #Topic Modeling #Text Readability and Simplification
- Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
2022/08/19 by Arpit Bansal, Eitan Borgnia, Bansal, Arpit +16 · 6 voices · 28 citations
Computer Science · #Generative Adversarial Networks and Image Synthesis
- Transformers Can Do Arithmetic with the Right Embeddings
2024/05/27 by Sean McLeish, Arpit Bansal, McLeish, Sean +20 · 5 voices · 20 citations
Computer Science · #Computability, Logic, AI Algorithms #cs.AI #cs.LG
- Tree-Ring Watermarks: Fingerprints for Diffusion Images that are Invisible and Robust
2023/05/31 by Yuxin Wen, Wen, Yuxin, John Kirchenbauer +5 · 2 voices · 32 citations
Computer Science · #Advanced Steganography and Watermarking Techniques #Digital Media Forensic Detection #Generative Adversarial Networks and Image Synthesis #cs.CR #cs.CV #cs.LG
- Multi-Stream LLMs: Unblocking Language Models with Parallel Streams of Thoughts, Inputs and Outputs
2026/05/12 by Guinan Su, Yanwu Yang, Xueyan Li +1 · 17 voices · 1 citation
#cs.LG #cs.CL
- Baseline Defenses for Adversarial Attacks Against Aligned Language Models
2023/09/01 by Neel Jain, Avi Schwarzschild, Jain, Neel +17 · 104 citations
Computer Science · #Adversarial Robustness in Machine Learning #Topic Modeling #Natural Language Processing Techniques
- Understanding and Mitigating Copying in Diffusion Models
2023/05/31 by Gowthami Somepalli, Somepalli, Gowthami, Vasu Singla +7 · 3 voices · 30 citations
Computer Science · #Generative Adversarial Networks and Image Synthesis #cs.CR #cs.CV #cs.LG
- Coercing LLMs to do and reveal (almost) anything
2024/02/21 by Jonas Geiping, Geiping, Jonas, Alex Stein +9 · 1 voice · 18 citations
#cs.LG #cs.CL #cs.CR
- Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery
2023/02/07 by Yuxin Wen, Wen, Yuxin, Neel Jain +9 · 1 voice · 41 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Computational Physics and Python Applications #Gene expression and cancer classification #cs.CL #cs.LG
- Universal Guidance for Diffusion Models
2023/02/14 by Arpit Bansal, Bansal, Arpit, Hongmin Chu +11 · 51 citations
Computer Science · Medicine · #Generative Adversarial Networks and Image Synthesis #Advanced Mathematical Modeling in Engineering #Advanced Neuroimaging Techniques and Applications
- Measuring Style Similarity in Diffusion Models
2024/04/01 by Gowthami Somepalli, Anubhav Gupta, Somepalli, Gowthami +13 · 23 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Music and Audio Processing
- NEFTune: Noisy Embeddings Improve Instruction Finetuning
2023/10/09 by Neel Jain, Ping-yeh Chiang, Jain, Neel +23 · 13 citations
Computer Science · #Natural Language Processing Techniques #Topic Modeling #Text Readability and Simplification
- Adversarial Examples Make Strong Poisons
2021/06/21 by Liam Fowl, Fowl, Liam, Micah Goldblum +9 · 8 citations
Computer Science · Pharmacology, Toxicology and Pharmaceutics · Social Sciences · #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Forensic Fingerprint Detection Methods #Forensic Toxicology and Drug Analysis #Machine Learning (cs.LG)
- MetaPoison: Practical General-purpose Clean-label Data Poisoning
2020/04/01 by Wei Huang, Jonas Geiping, Huang, W. Ronny +7 · 8 citations
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification
2022/02/01 by Yuxin Wen, Jonas Geiping, Wen, Yuxin +7 · 7 citations
Computer Science · #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- Autoregressive Perturbations for Data Poisoning
2022/06/08 by Pedro Sandoval-Segura, Vasu Singla, Sandoval-Segura, Pedro +9 · 6 citations
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection
- Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models
2021/10/25 by Liam Fowl, Fowl, Liam, Jonas Geiping +7 · 5 citations
Computer Science · #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- Great Models Think Alike and this Undermines AI Oversight
2025/02/06 by Shashwat Goel, Joschka Struber, Janet Struber +16 · 3 voices · 8 citations
Computer Science · Medicine · Social Sciences · #Artificial Intelligence in Healthcare and Education #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #cs.AI #cs.CL #cs.LG
- Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
2024/06/14 by Abhimanyu Hans, Hans, Abhimanyu, Yuxin Wen +19 · 8 citations
Computer Science · Social Sciences · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling #Wikis in Education and Collaboration
- JPEG Compressed Images Can Bypass Protections Against AI Editing
2023/04/05 by Pedro Sandoval-Segura, Jonas Geiping, Sandoval-Segura, Pedro +3 · 4 citations
Computer Science · Economics, Econometrics and Finance · #Generative Adversarial Networks and Image Synthesis #Digital Media Forensic Detection #Cinema and Media Studies
- Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
2022/10/19 by Yuxin Wen, Arpit Bansal, Wen, Yuxin +11 · 4 citations
Computer Science · #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Privacy-Preserving Technologies in Data
- Stochastic Training is Not Necessary for Generalization
2021/09/29 by Jonas Geiping, Micah Goldblum, Geiping, Jonas +7 · 4 citations
Computer Science · #Advanced Neural Network Applications #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Optimization and Control (math.OC) #Stochastic Gradient Optimization Techniques
- An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks
2024/10/21 by Valentyn Boreiko, Alexander Panfilov, Boreiko, Valentyn +7 · 6 citations
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Cryptography and Security (cs.CR) #Digital and Cyber Forensics #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection
- How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization
2022/10/12 by Jonas Geiping, Micah Goldblum, Geiping, Jonas +9 · 3 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning and Data Classification
- Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Release
2021/02/16 by Liam Fowl, Ping-yeh Chiang, Fowl, Liam +11 · 2 citations
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection
- Truth or Backpropaganda? An Empirical Investigation of Deep Learning Theory
2019/10/01 by Micah Goldblum, Goldblum, Micah, Jonas Geiping +7 · 2 citations
Computer Science · #Adversarial Robustness in Machine Learning #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #FOS: Mathematics #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC)
- Poisons that are learned faster are more effective
2022/04/19 by Pedro Sandoval-Segura, Vasu Singla, Sandoval-Segura, Pedro +11 · 2 citations
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
2024/04/01 by Yuxin Wen, Leo Marchyok, Wen, Yuxin +9 · 3 citations
Computer Science · #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- DP-InstaHide: Provably Defusing Poisoning and Backdoor Attacks with Differentially Private Data Augmentations
2021/03/02 by Eitan Borgnia, Borgnia, Eitan, Jonas Geiping +15 · 2 citations
Computer Science · #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- Training or Architecture? How to Incorporate Invariance in Neural Networks
2021/06/18 by Kanchana Vaishnavi Gandikota, Gandikota, Kanchana Vaishnavi, Jonas Geiping +6 · 1 citation
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Image Processing and 3D Reconstruction
- Pitfalls in Evaluating Language Model Forecasters
2025/05/31 by Daniel Paleka, Shashwat Goel, Paleka, Daniel +5 · 5 citations
Computer Science · #Natural Language Processing Techniques
- Is your batch size the problem? Revisiting the Adam-SGD gap in language modeling
2025/06/14 by Teodora Srećković, Srećković, Teodora, Jonas Geiping +3 · 5 citations
Computer Science · #FOS: Computer and information sciences #FOS: Mathematics #Machine Learning (cs.LG) #Natural Language Processing Techniques #Optimization and Control (math.OC) #Topic Modeling
- FutureSim: Replaying World Events to Evaluate Adaptive Agents
2026/05/14 by Shashwat Goel, Nikhil Chandak, Arvindh Arun +5 · 2 voices
Computer Science · #cs.LG #cs.AI #cs.CL
- AI Risk Management Should Incorporate Both Safety and Security
2024/05/29 by Xiangyu Qi, Qi, Xiangyu, Yangsibo Huang +47 · 1 citation
Medicine · Social Sciences · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Healthcare and Education #Cryptography and Security (cs.CR) #Ethics and Social Impacts of AI #FOS: Computer and information sciences
- When, Where and Why to Average Weights?
2025/02/10 by Niccolò Ajroldi, Ajroldi, Niccolò, Antonio Orvieto +3 · 2 citations
Computer Science · #Stochastic Gradient Optimization Techniques #Advanced Neural Network Applications #Machine Learning and Data Classification
- Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols
2025/10/10 by Mikhail Terekhov, Alexander Panfilov, Terekhov, Mikhail +10 · 3 citations
Computer Science · #Adversarial Robustness in Machine Learning #Security and Verification in Computing #Network Security and Intrusion Detection
- Training Data Reconstruction: Privacy due to Uncertainty?
2024/12/11 by Christina Runkel, Kanchana Vaishnavi Gandikota, Runkel, Christina +7 · 1 citation
Computer Science · #Privacy-Preserving Technologies in Data
- Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs
2025/09/22 by Evgenii Kortukov, Panfilov, Alexander, Kortukov, Evgenii +14 · 1 citation
Social Sciences · Computer Science · #Ethics and Social Impacts of AI #Adversarial Robustness in Machine Learning #Explainable Artificial Intelligence (XAI)