Andrew Ilyas
- Adversarial Examples Are Not Bugs, They Are Features
2019/05/06 by Andrew Ilyas, Ilyas, Andrew, Shibani Santurkar +10 · 6 voices · 61 citations
Computer Science · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #cs.CR #cs.CV #cs.LG #stat.ML
- Optimizing ML Training with Metagradient Descent
2025/03/17 by Logan Engstrom, Engstrom, Logan, Andrew Ilyas +9 · 12 voices · 8 citations
#stat.ML #cs.AI #cs.LG
- Raising the Cost of Malicious AI-Powered Image Editing
2023/02/13 by Hadi Salman, Salman, Hadi, Alaa Khaddaj +8 · 2 voices · 26 citations
Computer Science · Biochemistry, Genetics and Molecular Biology · #cs.LG
- How Does Batch Normalization Help Optimization?
2018/05/29 by Shibani Santurkar, Dimitris Tsipras, Santurkar, Shibani +5 · 30 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE)
- TRAK: Attributing Model Behavior at Scale
2023/03/24 by Sung‐Min Park, Kristian Georgiev, Park, Sung Min +7 · 45 citations
Medicine · Computer Science · #COVID-19 diagnosis using AI #Explainable Artificial Intelligence (XAI) #Domain Adaptation and Few-Shot Learning
- Noise or Signal: The Role of Image Backgrounds in Object Recognition
2020/06/17 by Kai Xiao, Logan Engstrom, Xiao, Kai +5 · 28 citations
Computer Science · #Advanced Neural Network Applications #Adversarial Robustness in Machine Learning #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG)
- Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors
2018/07/20 by Andrew Ilyas, Logan Engstrom, Ilyas, Andrew +3 · 10 citations
Computer Science · Psychology · #Advanced Malware Detection Techniques #Adversarial Robustness in Machine Learning #Cryptography and Security (cs.CR) #Deception detection and forensic psychology #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
- From ImageNet to Image Classification: Contextualizing Progress on Benchmarks
2020/05/22 by Dimitris Tsipras, Tsipras, Dimitris, Shibani Santurkar +7 · 8 citations
Computer Science · Medicine · #Mobile Crowdsensing and Crowdsourcing #Data Stream Mining Techniques #COVID-19 diagnosis using AI
- Query-Efficient Black-box Adversarial Examples (superceded)
2017/12/19 by Andrew Ilyas, Logan Engstrom, Ilyas, Andrew +5 · 4 citations
Computer Science · #Adversarial Robustness in Machine Learning #Domain Adaptation and Few-Shot Learning #Advanced Neural Network Applications
- Image Synthesis with a Single (Robust) Classifier
2019/06/06 by Shibani Santurkar, Santurkar, Shibani, Dimitris Tsipras +9 · 4 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · #Adversarial Robustness in Machine Learning #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural and Evolutionary Computing (cs.NE)
- Measuring Strategization in Recommendation: Users Adapt Their Behavior to Shape Future Content
2024/05/09 by Sarah H. Cen, Andrew Ilyas, Cen, Sarah H. +7 · 3 citations
Computer Science · Social Sciences · #Computers and Society (cs.CY) #Digital Marketing and Social Media #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC) #Information Retrieval (cs.IR) #Knowledge Management and Sharing #Machine Learning (cs.LG) #Methodology (stat.ME) #Recommender Systems and Techniques
- Attribute-to-Delete: Machine Unlearning via Datamodel Matching
2024/10/30 by Kristian Georgiev, Georgiev, Kristian, Roy Rinberg +11 · 4 citations
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification
- MAGIC: Near-Optimal Data Attribution for Deep Learning
2025/04/23 by Andrew Ilyas, Logan Engstrom, Ilyas, Andrew +1 · 4 citations
Computer Science · #Neural Networks and Applications
- Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selection
2024/06/24 by Saachi Jain, Kimia Hamidieh, Jain, Saachi +9 · 1 voice · 2 citations
#cs.LG #cs.CY #stat.ML
- User Strategization and Trustworthy Algorithms
2023/12/29 by Sarah H. Cen, Andrew Ilyas, Cen, Sarah H. +3 · 2 citations
Computer Science · Social Sciences · Neuroscience · #Blockchain Technology Applications and Security #Privacy, Security, and Data Protection #Mind wandering and attention
- DataMIL: Selecting Data for Robot Imitation Learning with Datamodels
2025/05/14 by Shivin Dass, Alaa Khaddaj, Dass, Shivin +9 · 6 citations
Computer Science · Engineering · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Reinforcement Learning in Robotics #Robot Manipulation and Learning #Robotics (cs.RO)
- Unadversarial Examples: Designing Objects for Robust Vision
2020/12/22 by Hadi Salman, Salman, Hadi, Andrew Ilyas +9 · 1 citation
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Machine Learning and Algorithms
- When does Bias Transfer in Transfer Learning?
2022/07/06 by Hadi Salman, Salman, Hadi, Saachi Jain +9 · 1 citation
Computer Science · Medicine · #COVID-19 diagnosis using AI #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multimodal Machine Learning Applications
- Probably Approximately Correct Labels
2025/06/12 by Emmanuel J. Candès, Candès, Emmanuel J., Andrew Ilyas +3 · 1 voice · 3 citations
Computer Science · Mathematics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.ML
- Large-Scale, Longitudinal Study of Large Language Models During the 2024 US Election Season
2025/09/22 by Sarah H. Cen, Cen, Sarah H., Andrew Ilyas +11 · 3 voices · 1 citation
#cs.CY #cs.LG