Soheil Feizi

ORCID

Publication Activity (10 Years)

Years Active: 2008-2024
Publications (10 Years): 189

Top Venues

Publications

Hamid Kazemi, Atoosa Malemir Chegini, Jonas Geiping, Soheil Feizi, Tom Goldstein
What do we learn from inverting CLIP models? CoRR (2024)
Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei, Aounon Kumar, Atoosa Malemir Chegini, Wenxiao Wang, Soheil Feizi
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks. ICLR (2024)
Samyadeep Basu, Nanxuan Zhao, Vlad I. Morariu, Soheil Feizi, Varun Manjunatha
Localizing and Editing Knowledge In Text-to-Image Generative Models. ICLR (2024)
Sriram Balasubramanian, Samyadeep Basu, Soheil Feizi
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP. CoRR (2024)
Mazda Moayeri, Samyadeep Basu, Sriram Balasubramanian, Priyatham Kattakinda, Atoosa Malemir Chegini, Robert Brauneis, Soheil Feizi
Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models. CoRR (2024)
Samyadeep Basu, Shell Xu Hu, Daniela Massiceti, Soheil Feizi
Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning. AAAI (2024)
Neha Mukund Kalibhat, Kanika Narang, Hamed Firooz, Maziar Sanjabi, Soheil Feizi
Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features. AAAI (2024)
Samyadeep Basu, Keivan Rezaei, Priyatham Kattakinda, Ryan Rossi, Cherry Zhao, Vlad I. Morariu, Varun Manjunatha, Soheil Feizi
On Mechanistic Knowledge Localization in Text-to-Image Generative Models. CoRR (2024)
Keivan Rezaei, Mehrdad Saberi, Mazda Moayeri, Soheil Feizi
PRIME: Prioritizing Interpretability in Failure Mode Extraction. ICLR (2024)
Mazda Moayeri, Elham Tabassi, Soheil Feizi
WorldBench: Quantifying Geographic Disparities in LLM Factual Recall. FAccT (2024)
Samyadeep Basu, Martin Grayson, Cecily Morrison, Besmira Nushi, Soheil Feizi, Daniela Massiceti
Understanding Information Storage and Transfer in Multi-modal Large Language Models. CoRR (2024)
Arman Zarei, Keivan Rezaei, Samyadeep Basu, Mehrdad Saberi, Mazda Moayeri, Priyatham Kattakinda, Soheil Feizi
Understanding and Mitigating Compositional Issues in Text-to-Image Generative Models. CoRR (2024)
Donghyeon Joo, Ramyad Hadidi, Soheil Feizi, Bahar Asgari
Endor: Hardware-Friendly Sparse Format for Offloaded LLM Inference. CoRR (2024)
Neha Mukund Kalibhat, Priyatham Kattakinda, Arman Zarei, Nikita Seleznev, Samuel Sharpe, Senthil Kumar, Soheil Feizi
Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning. CoRR (2024)
Sahil Singla, Atoosa Malemir Chegini, Mazda Moayeri, Soheil Feizi
Data-Centric Debugging: mitigating model failures via targeted image retrieval. WACV (2024)
Shoumik Saha, Wenxiao Wang, Yigitcan Kaya, Soheil Feizi, Tudor Dumitras
DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness. ICLR (2024)
Mihai Christodorescu, Ryan Craven, Soheil Feizi, Neil Zhenqiang Gong, Mia Hoffmann, Somesh Jha, Zhengyuan Jiang, Mehrdad Saberi Kamarposhti, John C. Mitchell, Jessica Newman, Emelia Probasco, Yanjun Qi, Khawaja Shams, Matthew Turek
Securing the Future of GenAI: Policy and Technology. IACR Cryptol. ePrint Arch. 2024 (2024)
Vinu Sankar Sadasivan, Shoumik Saha, Gaurang Sriramanan, Priyatham Kattakinda, Atoosa Malemir Chegini, Soheil Feizi
Fast Adversarial Attacks on Language Models In One GPU Minute. CoRR (2024)
Soumya Suvra Ghosal, Samyadeep Basu, Soheil Feizi, Dinesh Manocha
IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning. CoRR (2024)
Mihai Christodorescu, Ryan Craven, Soheil Feizi, Neil Gong, Mia Hoffmann, Somesh Jha, Zhengyuan Jiang, Mehrdad Saberi Kamarposhti, John C. Mitchell, Jessica Newman, Emelia Probasco, Yanjun Qi, Khawaja Shams, Matthew Turek
Securing the Future of GenAI: Policy and Technology. CoRR (2024)
Mehrdad Saberi, Vinu Sankar Sadasivan, Arman Zarei, Hessam Mahdavifar, Soheil Feizi
DREW : Towards Robust Data Provenance by Leveraging Error-Controlled Watermarking. CoRR (2024)
Prajwal Singhania, Siddharth Singh, Shwai He, Soheil Feizi, Abhinav Bhatele
Loki: Low-Rank Keys for Efficient Sparse Attention. CoRR (2024)
Keivan Rezaei, Mehrdad Saberi, Mazda Moayeri, Soheil Feizi
PRIME: Prioritizing Interpretability in Failure Mode Extraction. CoRR (2023)
Samyadeep Basu, Daniela Massiceti, Shell Xu Hu, Soheil Feizi
Strong Baselines for Parameter Efficient Few-Shot Fine-tuning. CoRR (2023)
Chun Pong Lau, Jiang Liu, Hossein Souri, Wei-An Lin, Soheil Feizi, Rama Chellappa
Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses. IEEE Trans. Pattern Anal. Mach. Intell. 45 (11) (2023)
Vinu Sankar Sadasivan, Mahdi Soltanolkotabi, Soheil Feizi
CUDA: Convolution-based Unlearnable Datasets. CoRR (2023)
Samyadeep Basu, Nanxuan Zhao, Vlad I. Morariu, Soheil Feizi, Varun Manjunatha
Localizing and Editing Knowledge in Text-to-Image Generative Models. CoRR (2023)
Sriram Balasubramanian, Gaurang Sriramanan, Vinu Sankar Sadasivan, Soheil Feizi
Exploring Geometry of Blind Spots in Vision models. NeurIPS (2023)
Clark W. Barrett, Brad Boyd, Ellie Burzstein, Nicholas Carlini, Brad Chen, Jihye Choi, Amrita Roy Chowdhury, Mihai Christodorescu, Anupam Datta, Soheil Feizi, Kathleen Fisher, Tatsunori Hashimoto, Dan Hendrycks, Somesh Jha, Daniel Kang, Florian Kerschbaum, Eric Mitchell, John C. Mitchell, Zulfikar Ramzan, Khawaja Shams, Dawn Song, Ankur Taly, Diyi Yang
Identifying and Mitigating the Security Risks of Generative AI. CoRR (2023)
Sriram Balasubramanian, Gaurang Sriramanan, Vinu Sankar Sadasivan, Soheil Feizi
Exploring Geometry of Blind Spots in Vision Models. CoRR (2023)
Jiang Liu, Chen Wei, Yuxiang Guo, Heng Yu, Alan L. Yuille, Soheil Feizi, Chun Pong Lau, Rama Chellappa
Instruct2Attack: Language-Guided Semantic Adversarial Attacks. CoRR (2023)
Keivan Rezaei, Kiarash Banihashem, Atoosa Malemir Chegini, Soheil Feizi
Run-Off Election: Improved Provable Defense against Data Poisoning Attacks. CoRR (2023)
Wenxiao Wang, Soheil Feizi
Temporal Robustness against Data Poisoning. CoRR (2023)
Samyadeep Basu, Mehrdad Saberi, Shweta Bhardwaj, Atoosa Malemir Chegini, Daniela Massiceti, Maziar Sanjabi, Shell Xu Hu, Soheil Feizi
EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods. CoRR (2023)
Vinu Sankar Sadasivan, Mahdi Soltanolkotabi, Soheil Feizi
CUDA: Convolution-Based Unlearnable Datasets. CVPR (2023)
Atoosa Malemir Chegini, Soheil Feizi
Identifying and Mitigating Model Failures through Few-shot CLIP-aided Diffusion Generation. CoRR (2023)
Soheil Feizi, MohammadTaghi Hajiaghayi, Keivan Rezaei, Suho Shin
Online Advertisements with LLMs: Opportunities and Challenges. CoRR (2023)
Clark W. Barrett, Brad Boyd, Elie Bursztein, Nicholas Carlini, Brad Chen, Jihye Choi, Amrita Roy Chowdhury, Mihai Christodorescu, Anupam Datta, Soheil Feizi, Kathleen Fisher, Tatsunori Hashimoto, Dan Hendrycks, Somesh Jha, Daniel Kang, Florian Kerschbaum, Eric Mitchell, John C. Mitchell, Zulfikar Ramzan, Khawaja Shams, Dawn Song, Ankur Taly, Diyi Yang
Identifying and Mitigating the Security Risks of Generative AI. Found. Trends Priv. Secur. 6 (1) (2023)
Mazda Moayeri, Keivan Rezaei, Maziar Sanjabi, Soheil Feizi
Text-To-Concept (and Back) via Cross-Model Alignment. ICML (2023)
Neha Mukund Kalibhat, Shweta Bhardwaj, C. Bayan Bruss, Hamed Firooz, Maziar Sanjabi, Soheil Feizi
Identifying Interpretable Subspaces in Image Representations. CoRR (2023)
Neha Mukund Kalibhat, Shweta Bhardwaj, C. Bayan Bruss, Hamed Firooz, Maziar Sanjabi, Soheil Feizi
Identifying Interpretable Subspaces in Image Representations. ICML (2023)
Samyadeep Basu, Maziar Sanjabi, Daniela Massiceti, Shell Xu Hu, Soheil Feizi
Augmenting CLIP with Improved Visio-Linguistic Reasoning. CoRR (2023)
Wenxiao Wang, Soheil Feizi
Temporal Robustness against Data poisoning. NeurIPS (2023)
Mazda Moayeri, Wenxiao Wang, Sahil Singla, Soheil Feizi
Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases. NeurIPS (2023)
Aya Abdelsalam Ismail, Sercan Ö. Arik, Jinsung Yoon, Ankur Taly, Soheil Feizi, Tomas Pfister
Interpretable Mixture of Experts. Trans. Mach. Learn. Res. 2023 (2023)
Keivan Rezaei, Kiarash Banihashem, Atoosa Malemir Chegini, Soheil Feizi
Run-off Election: Improved Provable Defense against Data Poisoning Attacks. ICML (2023)
Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei, Aounon Kumar, Atoosa Malemir Chegini, Wenxiao Wang, Soheil Feizi
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks. CoRR (2023)
Neha Mukund Kalibhat, Samuel Sharpe, Jeremy Goodsitt, C. Bayan Bruss, Soheil Feizi
Adapting Self-Supervised Representations to Multi-Domain Setups. CoRR (2023)
Vedant Nanda, Till Speicher, John P. Dickerson, Soheil Feizi, Krishna P. Gummadi, Adrian Weller
Diffused Redundancy in Pre-trained Representations. CoRR (2023)
Samyadeep Basu, Megan Stanley, John Bronskill, Soheil Feizi, Daniela Massiceti
Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks. ICLR (2023)
Aounon Kumar, Chirag Agarwal, Suraj Srinivas, Soheil Feizi, Hima Lakkaraju
Certifying LLM Safety against Adversarial Prompting. CoRR (2023)
Shoumik Saha, Wenxiao Wang, Yigitcan Kaya, Soheil Feizi
Adversarial Robustness of Learning-based Static Malware Classifiers. CoRR (2023)
Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi
Provable Robustness against Wasserstein Distribution Shifts via Input Randomization. ICLR (2023)
Sriram Balasubramanian, Soheil Feizi
Towards Improved Input Masking for Convolutional Neural Networks. ICCV (2023)
Neha Mukund Kalibhat, Samuel Sharpe, Jeremy Goodsitt, C. Bayan Bruss, Soheil Feizi
Adapting Self-Supervised Representations to Multi-Domain Setups. BMVC (2023)
Yanchao Sun, Ruijie Zheng, Parisa Hassanzadeh, Yongyuan Liang, Soheil Feizi, Sumitra Ganesh, Furong Huang
Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication. ICLR (2023)
Vinu Sankar Sadasivan, Aounon Kumar, Sriram Balasubramanian, Wenxiao Wang, Soheil Feizi
Can AI-Generated Text be Reliably Detected? CoRR (2023)
Mazda Moayeri, Keivan Rezaei, Maziar Sanjabi, Soheil Feizi
Text2Concept: Concept Activation Vectors Directly from Text. CVPR Workshops (2023)
Aounon Kumar, Vinu Sankar Sadasivan, Soheil Feizi
Provable Robustness for Streaming Models with a Sliding Window. CoRR (2023)
Wenxiao Wang, Soheil Feizi
On Practical Aspects of Aggregation Defenses against Data Poisoning Attacks. CoRR (2023)
Vedant Nanda, Till Speicher, John P. Dickerson, Krishna P. Gummadi, Soheil Feizi, Adrian Weller
Diffused Redundancy in Pre-trained Representations. NeurIPS (2023)
Alexander Levine, Soheil Feizi
Goal-Conditioned Q-learning as Knowledge Distillation. AAAI (2023)
Mazda Moayeri, Keivan Rezaei, Maziar Sanjabi, Soheil Feizi
Text-To-Concept (and Back) via Cross-Model Alignment. CoRR (2023)
Mazda Moayeri, Phillip Pope, Yogesh Balaji, Soheil Feizi
A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes. CVPR (2022)
Aya Abdelsalam Ismail, Sercan Ö. Arik, Jinsung Yoon, Ankur Taly, Soheil Feizi, Tomas Pfister
Interpretable Mixture of Experts for Structured Data. CoRR (2022)
Wenxiao Wang, Alexander Levine, Soheil Feizi
Lethal Dose Conjecture on Data Poisoning. CoRR (2022)
Alexander Levine, Soheil Feizi
Provable Adversarial Robustness for Fractional Lp Threat Models. AISTATS (2022)
Wenxiao Wang, Alexander Levine, Soheil Feizi
Lethal Dose Conjecture on Data Poisoning. NeurIPS (2022)
Sahil Singla, Soheil Feizi
Improved techniques for deterministic l2 robustness. CoRR (2022)
Mazda Moayeri, Kiarash Banihashem, Soheil Feizi
Explicit Tradeoffs between Adversarial and Natural Distributional Robustness. NeurIPS (2022)
Wenxiao Wang, Alexander Levine, Soheil Feizi
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation. CoRR (2022)
Neha Mukund Kalibhat, Kanika Narang, Liang Tan, Hamed Firooz, Maziar Sanjabi, Soheil Feizi
Understanding Failure Modes of Self-Supervised Learning. CoRR (2022)
Sahil Singla, Atoosa Malemir Chegini, Mazda Moayeri, Soheil Feizi
Data-Centric Debugging: mitigating model failures via targeted data collection. CoRR (2022)
Mazda Moayeri, Wenxiao Wang, Sahil Singla, Soheil Feizi
Spuriosity Rankings: Sorting Data for Spurious Correlation Robustness. CoRR (2022)
Alexander Levine, Soheil Feizi
Provable Adversarial Robustness for Fractional Lp Threat Models. CoRR (2022)
Jiang Liu, Chun Pong Lau, Hossein Souri, Soheil Feizi, Rama Chellappa
Mutual Adversarial Training: Learning Together is Better Than Going Alone. IEEE Trans. Inf. Forensics Secur. 17 (2022)
Jiang Liu, Alexander Levine, Chun Pong Lau, Rama Chellappa, Soheil Feizi
Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection. CVPR (2022)
Sahil Singla, Mazda Moayeri, Soheil Feizi
Core Risk Minimization using Salient ImageNet. CoRR (2022)
Mazda Moayeri, Sahil Singla, Soheil Feizi
Hard ImageNet: Segmentations for Objects with Strong Spurious Cues. NeurIPS (2022)
Sriram Balasubramanian, Soheil Feizi
Towards Better Input Masking for Convolutional Neural Networks. CoRR (2022)
Wenxiao Wang, Alexander Levine, Soheil Feizi
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation. ICML (2022)
Priyatham Kattakinda, Soheil Feizi
FOCUS: Familiar Objects in Common and Uncommon Settings. ICML (2022)
Gaurang Sriramanan, Maharshi Gor, Soheil Feizi
Toward Efficient Robust Training against Union of $\ell_p$ Threat Models. NeurIPS (2022)
Yanchao Sun, Ruijie Zheng, Parisa Hassanzadeh, Yongyuan Liang, Soheil Feizi, Sumitra Ganesh, Furong Huang
Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems. CoRR (2022)
Sahil Singla, Surbhi Singla, Soheil Feizi
Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100. ICLR (2022)
Mazda Moayeri, Phillip Pope, Yogesh Balaji, Soheil Feizi
A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes. CoRR (2022)
Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi
Certifying Model Accuracy under Distribution Shifts. CoRR (2022)
Sahil Singla, Soheil Feizi
Improved techniques for deterministic l2 robustness. NeurIPS (2022)
Sahil Singla, Soheil Feizi
Salient ImageNet: How to discover spurious features in Deep Learning? ICLR (2022)
Aounon Kumar, Alexander Levine, Soheil Feizi
Policy Smoothing for Provably Robust Reinforcement Learning. ICLR (2022)
Alexander Levine, Soheil Feizi
Goal-Conditioned Q-Learning as Knowledge Distillation. CoRR (2022)
Priyatham Kattakinda, Alexander Levine, Soheil Feizi
Invariant Learning via Diffusion Dreamed Distribution Shifts. CoRR (2022)
Mazda Moayeri, Kiarash Banihashem, Soheil Feizi
Explicit Tradeoffs between Adversarial and Natural Distributional Robustness. CoRR (2022)
Aya Abdelsalam Ismail, Héctor Corrada Bravo, Soheil Feizi
Improving Deep Learning Interpretability by Saliency Guided Training. NeurIPS (2021)
Sahil Singla, Soheil Feizi
Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution Layers. ICLR (2021)
Mazda Moayeri, Soheil Feizi
Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings. CoRR (2021)
Sahil Singla, Soheil Feizi
Skew Orthogonal Convolutions. ICML (2021)
Sahil Singla, Soheil Feizi
Causal ImageNet: How to discover spurious features in Deep Learning? CoRR (2021)
Mazda Moayeri, Soheil Feizi
Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings. ICCV (2021)
Vedant Nanda, Samuel Dooley, Sahil Singla, Soheil Feizi, John P. Dickerson
Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning. FAccT (2021)

Soheil Feizi.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Soheil Feizi