← Authors

Soheil Feizi

87 papers · 2014–2026 · 12 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (11) 🐝 Cross-Pollinator (10) πŸƒ Academic Marathon (11) 🌈 Renaissance Researcher (5) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (16) 🧭 Keyword Pioneer 🏠 Conference Loyalist (25) 🀝 Dynamic Duo (12) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ”¬ Deep Specialist (18) 🧬 Topic Evolution πŸ† Keyword Champion (9) ❓ The Questioner (2) πŸ—ƒοΈ Keyword Collector (296) πŸ“ˆ Trend Setter πŸ’Ž Century Club (85) ⚑ Prolific Year (13) πŸ”₯ Unstoppable (9)

Conferences

NIPS (25) ICLR (19) ICML (14) AAAI (7) EMNLP (5) AISTATS (4) ICCV (4) CVPR (3) ACL (2) EACL (2) UAI (1) WACV (1)

Top co-authors

Samyadeep Basu (13) Sahil Singla (12) Alexander Levine (12) Mazda Moayeri (11) Wenxiao Wang (8) Yogesh Balaji (8) Sriram Balasubramanian (7) Vinu Sankar Sadasivan (6) Keivan Rezaei (6) Aounon Kumar (5)

Research topics

Privacy (2)

Keywords

adversarial robustness (17) adversarial training (9) certified robustness (9) image classification (8) randomized smoothing (6) neural network (6) generative adversarial network (5) data poisoning (5) wasserstein distance (5) adversarial attack (5) transfer learning (4) large language model (4) robust optimization (3) vision-language model (3) deep neural network (3) threat model (3) model robustness (3) domain adaptation (3) knowledge distillation (3) maximum likelihood (3)

Papers

Attacker’s Noise Can Manipulate Your Audio-based LLM in the Real World EACL 2026
Decomposition-Enhanced Training for Post-Hoc Attributions in Language Models EACL 2026
How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings ICLR 2025
RePanda: Pandas-powered Tabular Verification and Reasoning ACL 2025
Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing ACL 2025
DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors EMNLP 2025
Tool Preferences in Agentic LLMs are Unreliable EMNLP 2025
A Closer Look at Bias and Chain-of-Thought Faithfulness of Large (Vision) Language Models EMNLP 2025
Unearthing Skill-level Insights for Understanding Trade-offs of Foundation Models ICLR 2025
Rethinking Artistic Copyright Infringements In the Era Of Text-to-Image Generative Models ICLR 2025
DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness ICLR 2024
Understanding Information Storage and Transfer in Multi-Modal Large Language Models NIPS 2024
Loki: Low-rank Keys for Efficient Sparse Attention NIPS 2024
LLM-Check: Investigating Detection of Hallucinations in Large Language Models NIPS 2024
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP NIPS 2024
Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning AAAI 2024
Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features AAAI 2024
On Mechanistic Knowledge Localization in Text-to-Image Generative Models ICML 2024
Localizing and Editing Knowledge In Text-to-Image Generative Models ICLR 2024
PRIME: Prioritizing Interpretability in Failure Mode Extraction ICLR 2024
Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP EMNLP 2024
IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning EMNLP 2024
Fast Adversarial Attacks on Language Models In One GPU Minute ICML 2024
Data-Centric Debugging: Mitigating Model Failures via Targeted Image Retrieval WACV 2024
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks ICLR 2024
CUDA: Convolution-Based Unlearnable Datasets CVPR 2023
Identifying Interpretable Subspaces in Image Representations ICML 2023
Goal-Conditioned Q-learning as Knowledge Distillation AAAI 2023
Run-off Election: Improved Provable Defense against Data Poisoning Attacks ICML 2023
Towards Improved Input Masking for Convolutional Neural Networks ICCV 2023
Diffused Redundancy in Pre-trained Representations NIPS 2023
Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases NIPS 2023
Exploring Geometry of Blind Spots in Vision models NIPS 2023
Temporal Robustness against Data poisoning NIPS 2023
Provable Robustness against Wasserstein Distribution Shifts via Input Randomization ICLR 2023
Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication ICLR 2023
Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks ICLR 2023
Text-To-Concept (and Back) via Cross-Model Alignment ICML 2023
Provable Adversarial Robustness for Fractional Lp Threat Models AISTATS 2022
A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes CVPR 2022
Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation ICML 2022
FOCUS: Familiar Objects in Common and Uncommon Settings ICML 2022
Segment and Complete: Defending Object Detectors Against Adversarial Patch Attacks With Robust Patch Detection CVPR 2022
Explicit Tradeoffs between Adversarial and Natural Distributional Robustness NIPS 2022
Improved techniques for deterministic l2 robustness NIPS 2022
Salient ImageNet: How to discover spurious features in Deep Learning? ICLR 2022
Toward Efficient Robust Training against Union of $\ell_p$ Threat Models NIPS 2022
Hard ImageNet: Segmentations for Objects with Strong Spurious Cues NIPS 2022
Policy Smoothing for Provably Robust Reinforcement Learning ICLR 2022
Lethal Dose Conjecture on Data Poisoning NIPS 2022
Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100 ICLR 2022
Winning Lottery Tickets in Deep Generative Models AAAI 2021
Improving Deep Learning Interpretability by Saliency Guided Training NIPS 2021
GANs with Conditional Independence Graphs: On Subadditivity of Probability Divergences AISTATS 2021
Unsupervised anomaly detection with adversarial mirrored autoencoders UAI 2021
Low Curvature Activations Reduce Overfitting in Adversarial Training ICCV 2021
Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings ICCV 2021
Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution Layers ICLR 2021
Understanding Over-parameterization in Generative Adversarial Networks ICLR 2021
Deep Partition Aggregation: Provable Defenses against General Poisoning Attacks ICLR 2021
Influence Functions in Deep Learning Are Fragile ICLR 2021
Perceptual Adversarial Robustness: Defense Against Unseen Threat Models ICLR 2021
Improved, Deterministic Smoothing for L_1 Certified Robustness ICML 2021
Skew Orthogonal Convolutions ICML 2021
Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attacks AISTATS 2020
Adversarial Robustness of Flow-Based Generative Models AISTATS 2020
Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness ICML 2020
Second-Order Provable Defenses against Adversarial Attacks ICML 2020
Benchmarking Deep Learning Interpretability in Time Series Predictions NIPS 2020
(De)Randomized Smoothing for Certifiable Defense against Patch Attacks NIPS 2020
Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation NIPS 2020
Maximum Likelihood Embedding of Logistic Random Dot Product Graphs AAAI 2020
Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation AAAI 2020
Adversarially Robust Distillation AAAI 2020
Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks NIPS 2020
Certifying Confidence via Randomized Smoothing NIPS 2020
On Second-Order Group Influence Functions for Black-Box Predictions ICML 2020
Functional Adversarial Attacks NIPS 2019
Quantum Wasserstein Generative Adversarial Networks NIPS 2019
Are adversarial examples inevitable? ICLR 2019
Normalized Wasserstein for Mixture Distributions With Applications in Adversarial Learning and Domain Adaptation ICCV 2019
Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs ICML 2019
Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation ICML 2019
Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks NIPS 2019
Porcupine Neural Networks: Approximating Neural Network Landscapes NIPS 2018
Tensor Biclustering NIPS 2017
Biclustering Using Message Passing NIPS 2014