Nicholas Carlini
- Large-scale online deanonymization with LLMs
LLMs enable scalable, high-precision deanonymization of pseudonymous online accounts using unstructured text.
2026/02/18 by Simon Lermen, Daniel Paleka, Joshua Swanson +3 · 85 voices · 1 citation
#cs.CR #cs.AI #cs.LG
- Scalable Extraction of Training Data from (Production) Language Models
2023/11/28 by Milad Nasr, Nicholas Carlini, Nasr, Milad +17 · 21 voices · 66 citations
Computer Science · #Adversarial Robustness in Machine Learning #Topic Modeling #Explainable Artificial Intelligence (XAI)
- Defeating Prompt Injections by Design
2025/03/24 by Edoardo Debenedetti, Ilia Shumailov, Debenedetti, Edoardo +17 · 23 voices · 58 citations
#cs.CR #cs.AI
- Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
2024/06/17 by Robert Hönig, Hönig, Robert, Javier Rando +5 · 38 voices · 7 citations
Computer Science · #Adversarial Robustness in Machine Learning #cs.CR
- The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks
2018/02/22 by Nicholas Carlini, Carlini, Nicholas, Chang Liu +7 · 5 voices · 68 citations
#cs.LG #cs.AI #cs.CR
- Audio Adversarial Examples: Targeted Attacks on Speech-to-Text
2018/01/05 by Nicholas Carlini, Carlini, Nicholas, David Wagner +1 · 5 voices · 24 citations
#cs.LG #cs.AI #cs.CR
- Extracting Training Data from Diffusion Models
2023/01/30 by Nicholas Carlini, Carlini, Nicholas, Jamie Hayes +15 · 9 voices · 100 citations
Computer Science · #Generative Adversarial Networks and Image Synthesis
- Poisoning Web-Scale Training Datasets is Practical
2023/02/20 by Nicholas Carlini, Matthew Jagielski, Carlini, Nicholas +16 · 6 voices · 46 citations
Computer Science · Medicine · #Adversarial Robustness in Machine Learning #COVID-19 diagnosis using AI #Topic Modeling #cs.CR #cs.LG
- Extracting Training Data from Large Language Models
2020/12/14 by Nicholas Carlini, Florian Tramèr, Carlini, Nicholas +25 · 8 voices · 235 citations
Computer Science · #Adversarial Robustness in Machine Learning #Privacy-Preserving Technologies in Data #Topic Modeling #cs.CL #cs.CR #cs.LG
- Stealing Part of a Production Language Model
2024/03/11 by Nicholas Carlini, Carlini, Nicholas, Daniel Paleka +26 · 11 voices · 26 citations
Computer Science · #Natural Language Processing Techniques #cs.CR
- Universal and Transferable Adversarial Attacks on Aligned Language Models
2023/07/27 by Andy Zou, Zou, Andy, Zifan Wang +9 · 5 voices · 456 citations
#cs.CL #cs.AI #cs.CR #cs.LG
- Unsolved Problems in ML Safety
2021/09/28 by Dan Hendrycks, Hendrycks, Dan, Nicholas Carlini +5 · 2 voices · 27 citations
#cs.LG #cs.AI #cs.CL #cs.CV
- Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samples
2025/10/08 by Alexandra Souly, Souly, Alexandra, Javier Rando +25 · 34 voices · 18 citations
Medicine · #Medical Imaging and Pathology Studies
- MixMatch: A Holistic Approach to Semi-Supervised Learning
2019/05/06 by David Berthelot, Berthelot, David, Nicholas Carlini +9 · 1 voice · 75 citations
Computer Science · #cs.LG #cs.AI #cs.CV #stat.ML
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
2020/01/21 by Kihyuk Sohn, Sohn, Kihyuk, David Berthelot +15 · 155 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #Multimodal Machine Learning Applications #Advanced Neural Network Applications
- Persistent Pre-Training Poisoning of LLMs
2024/10/17 by Yiming Zhang, Javier Rando, Zhang, Yiming +13 · 3 voices · 20 citations
#cs.CR #cs.AI
- Membership Inference Attacks From First Principles
2021/12/07 by Nicholas Carlini, Carlini, Nicholas, Steve Chien +9 · 94 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)
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
2018/02/01 by Anish Athalye, Nicholas Carlini, Athalye, Anish +4 · 61 citations
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Physical Unclonable Functions (PUFs) and Hardware Security
- Quantifying Memorization Across Neural Language Models
2022/02/15 by Nicholas Carlini, Daphne Ippolito, Carlini, Nicholas +9 · 71 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling
- Deduplicating Training Data Makes Language Models Better
2021/07/14 by Katherine Lee, Daphne Ippolito, Lee, Katherine +11 · 58 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling
- On Evaluating Adversarial Robustness
2019/02/18 by Nicholas Carlini, Anish Athalye, Carlini, Nicholas +15 · 49 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Bacillus and Francisella bacterial research #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Label-Only Membership Inference Attacks
2020/07/28 by Christopher A. Choquette-Choo, Florian Tramèr, Choquette-Choo, Christopher A. +5 · 31 citations
Computer Science · #Adversarial Robustness in Machine Learning #Privacy-Preserving Technologies in Data #Machine Learning and Algorithms
- The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
2025/10/10 by Milad Nasr, Nasr, Milad, Nicholas Carlini +27 · 4 voices · 17 citations
Computer Science · #Adversarial Robustness in Machine Learning #Network Security and Intrusion Detection #Security and Verification in Computing #cs.CR #cs.LG
- Adversary Instantiation: Lower Bounds for Differentially Private Machine\n Learning
2021/01/11 by Milad Nasr, Shuang Song, Nasr, Milad +7 · 16 citations
Computer Science · #Adversarial Robustness in Machine Learning #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- The Privacy Onion Effect: Memorization is Relative
2022/06/21 by Nicholas Carlini, Matthew Jagielski, Carlini, Nicholas +9 · 16 citations
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #Ethics and Social Impacts of AI #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- High Accuracy and High Fidelity Extraction of Neural Networks
2019/09/03 by Matthew Jagielski, Jagielski, Matthew, Nicholas Carlini +7 · 14 citations
Computer Science · #Adversarial Robustness in Machine Learning #Advanced Malware Detection Techniques #Anomaly Detection Techniques and Applications
- Counterfactual Memorization in Neural Language Models
2021/12/24 by Chiyuan Zhang, Daphne Ippolito, Zhang, Chiyuan +9 · 12 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling
- Measuring Forgetting of Memorized Training Examples
2022/06/30 by Matthew Jagielski, Jagielski, Matthew, Om Thakkar +19 · 12 citations
Computer Science · #Adversarial Robustness in Machine Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data #Topic Modeling
- ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
2019/11/21 by David Berthelot, Berthelot, David, Nicholas Carlini +11 · 9 citations
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Multimodal Machine Learning Applications
- Provably Minimally-Distorted Adversarial Examples
2017/09/29 by Nicholas Carlini, Guy Katz, Carlini, Nicholas +5 · 13 citations
Computer Science · #Adversarial Robustness in Machine Learning
- Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
2022/12/13 by Florian Tramèr, Tramèr, Florian, Gautam Kamath +3 · 8 citations
Computer Science · #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Privacy-Preserving Technologies in Data
- ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
2026/05/11 by Zhun Wang, Nico Schiller, Hongwei Li +13 · 8 voices · 1 citation
#cs.CR #cs.AI #cs.LG
- Forcing Diffuse Distributions out of Language Models
2024/04/16 by Yiming Zhang, Zhang, Yiming, Avi Schwarzschild +7 · 1 voice · 9 citations
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling #cs.CL #cs.LG
- Handcrafted Backdoors in Deep Neural Networks
2021/06/08 by Sanghyun Hong, Nicholas Carlini, Hong, Sanghyun +3 · 5 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
- Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
2026/01/17 by Mike A. Merrill, Alexander G. Shaw, Nicholas Carlini +82 · 3 voices · 4 citations
Computer Science · #cs.SE #cs.AI
- SoK: Watermarking for AI-Generated Content
2024/11/27 by Xuandong Zhao, Sam Gunn, Zhao, Xuandong +25 · 13 citations
Computer Science · #Advanced Steganography and Watermarking Techniques #Artificial Intelligence (cs.AI) #Chaos-based Image/Signal Encryption #Computer Graphics and Visualization Techniques #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG)
- (Certified!!) Adversarial Robustness for Free!
2022/06/21 by Nicholas Carlini, Carlini, Nicholas, Florian Tramèr +6 · 4 citations
Computer Science · Medicine · Engineering · #Adversarial Robustness in Machine Learning #COVID-19 diagnosis using AI #Advanced X-ray and CT Imaging
- On Evaluating the Durability of Safeguards for Open-Weight LLMs
2024/12/10 by Xiangyu Qi, Qi, Xiangyu, Boyi Wei +17 · 2 voices · 7 citations
Computer Science · #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #cs.AI #cs.CR
- Debugging Differential Privacy: A Case Study for Privacy Auditing
2022/02/24 by Florian Tramèr, Andreas Terzis, Tramer, Florian +9 · 3 citations
Computer Science · #Privacy-Preserving Technologies in Data #Cryptography and Data Security #Stochastic Gradient Optimization Techniques
- Privacy Side Channels in Machine Learning Systems
2023/09/11 by Edoardo Debenedetti, Giorgio Severi, Debenedetti, Edoardo +13 · 4 citations
Computer Science · #Adversarial Robustness in Machine Learning #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data
- CryptanalysisBench: Can LLMs do Cryptanalysis?
2026/07/20 by Lukas Fluri, Avital Shafran, Nicholas Carlini +5 · 3 voices
Computer Science · #cs.CR
- Students Parrot Their Teachers: Membership Inference on Model Distillation
2023/03/06 by Matthew Jagielski, Jagielski, Matthew, Milad Nasr +7 · 1 voice · 2 citations
#cs.CR #cs.LG
- Polynomial Time Cryptanalytic Extraction of Deep Neural Networks in the Hard-Label Setting
2024/10/08 by Nicholas Carlini, Jorge Chávez-Saab, Carlini, Nicholas +7 · 4 citations
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Neural Networks and Applications #Statistical and Computational Modeling
- Fundamental Tradeoffs between Invariance and Sensitivity to Adversarial Perturbations
2020/02/11 by Florian Tramèr, Tramèr, Florian, Jens Behrmann +7 · 2 citations
Computer Science · #Adversarial Robustness in Machine Learning
- Exploiting Excessive Invariance caused by Norm-Bounded Adversarial\n Robustness
2019/03/25 by Jörn-Henrik Jacobsen, Jens Behrmann, Jacobsen, Jörn-Henrik +8 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #Adversarial Robustness in Machine Learning #Bacillus and Francisella bacterial research #Computer Vision and Pattern Recognition (cs.CV) #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
2024/11/15 by Michael Aerni, Javier Rando, Aerni, Michael +9 · 2 voices · 2 citations
Computer Science · #Adversarial Robustness in Machine Learning #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Topic Modeling #cs.CL #cs.LG
- Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples
2021/06/18 by Maura Pintor, Pintor, Maura, Luca Demetrio +11 · 1 citation
Computer Science · #Advanced Malware Detection Techniques #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) #Software Testing and Debugging Techniques
- Evaluating the Robustness of the "Ensemble Everything Everywhere" Defense
2024/11/22 by Jie Zhang, Zhang, Jie, Christian Schlarmann +11 · 2 voices · 1 citation
#cs.LG #cs.CR
- AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
2025/03/03 by Nicholas Carlini, Carlini, Nicholas, Javier Rando +7 · 3 citations
Computer Science · #Adversarial Robustness in Machine Learning #Advanced Malware Detection Techniques #Security and Verification in Computing
- A LLM Assisted Exploitation of AI-Guardian
2023/07/20 by Nicholas Carlini, Carlini, Nicholas · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Artificial Intelligence (cs.AI) #Cryptography and Security (cs.CR) #Digital and Cyber Forensics #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification
- Stealing User Prompts from Mixture of Experts
2024/10/30 by Itay Yona, Yona, Itay, Ilia Shumailov +5 · 1 citation
Computer Science · #Data Mining Algorithms and Applications