Soheil Feizi

Orcid: 0000-0003-0944-8242

According to our database1, Soheil Feizi authored at least 161 papers between 2008 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Securing the Future of GenAI: Policy and Technology.
IACR Cryptol. ePrint Arch., 2024

RESTOR: Knowledge Recovery through Machine Unlearning.
CoRR, 2024

Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models.
CoRR, 2024

Endor: Hardware-Friendly Sparse Format for Offloaded LLM Inference.
CoRR, 2024

Understanding and Mitigating Compositional Issues in Text-to-Image Generative Models.
CoRR, 2024

Understanding Information Storage and Transfer in Multi-modal Large Language Models.
CoRR, 2024

DREW : Towards Robust Data Provenance by Leveraging Error-Controlled Watermarking.
CoRR, 2024

Loki: Low-Rank Keys for Efficient Sparse Attention.
CoRR, 2024

Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP.
CoRR, 2024

Understanding the Effect of using Semantically Meaningful Tokens for Visual Representation Learning.
CoRR, 2024

On Mechanistic Knowledge Localization in Text-to-Image Generative Models.
CoRR, 2024

Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models.
CoRR, 2024

What do we learn from inverting CLIP models?
CoRR, 2024

Data-Centric Debugging: mitigating model failures via targeted image retrieval.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

Fast Adversarial Attacks on Language Models In One GPU Minute.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

On Mechanistic Knowledge Localization in Text-to-Image Generative Models.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

PRIME: Prioritizing Interpretability in Failure Mode Extraction.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

Localizing and Editing Knowledge In Text-to-Image Generative Models.
Proceedings of the Twelfth International Conference on Learning Representations, 2024

WorldBench: Quantifying Geographic Disparities in LLM Factual Recall.
Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency, 2024

IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

Measuring Self-Supervised Representation Quality for Downstream Classification Using Discriminative Features.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses.
IEEE Trans. Pattern Anal. Mach. Intell., November, 2023

Interpretable Mixture of Experts.
Trans. Mach. Learn. Res., 2023

Identifying and Mitigating the Security Risks of Generative AI.
Found. Trends Priv. Secur., 2023

Identifying and Mitigating Model Failures through Few-shot CLIP-aided Diffusion Generation.
CoRR, 2023

Instruct2Attack: Language-Guided Semantic Adversarial Attacks.
CoRR, 2023

Online Advertisements with LLMs: Opportunities and Challenges.
CoRR, 2023

EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods.
CoRR, 2023

Certifying LLM Safety against Adversarial Prompting.
CoRR, 2023

Identifying and Mitigating the Security Risks of Generative AI.
CoRR, 2023

Augmenting CLIP with Improved Visio-Linguistic Reasoning.
CoRR, 2023

On Practical Aspects of Aggregation Defenses against Data Poisoning Attacks.
CoRR, 2023

Provable Robustness for Streaming Models with a Sliding Window.
CoRR, 2023

Adversarial Robustness of Learning-based Static Malware Classifiers.
CoRR, 2023

Can AI-Generated Text be Reliably Detected?
CoRR, 2023

Diffused Redundancy in Pre-trained Representations.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Exploring Geometry of Blind Spots in Vision models.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Temporal Robustness against Data poisoning.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Run-off Election: Improved Provable Defense against Data Poisoning Attacks.
Proceedings of the International Conference on Machine Learning, 2023

Text-To-Concept (and Back) via Cross-Model Alignment.
Proceedings of the International Conference on Machine Learning, 2023

Identifying Interpretable Subspaces in Image Representations.
Proceedings of the International Conference on Machine Learning, 2023

Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Provable Robustness against Wasserstein Distribution Shifts via Input Randomization.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Towards Improved Input Masking for Convolutional Neural Networks.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

CUDA: Convolution-Based Unlearnable Datasets.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Text2Concept: Concept Activation Vectors Directly from Text.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Adapting Self-Supervised Representations to Multi-Domain Setups.
Proceedings of the 34th British Machine Vision Conference 2023, 2023

Goal-Conditioned Q-learning as Knowledge Distillation.
Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022
Mutual Adversarial Training: Learning Together is Better Than Going Alone.
IEEE Trans. Inf. Forensics Secur., 2022

Spuriosity Rankings: Sorting Data for Spurious Correlation Robustness.
CoRR, 2022

Towards Better Input Masking for Convolutional Neural Networks.
CoRR, 2022

Invariant Learning via Diffusion Dreamed Distribution Shifts.
CoRR, 2022

Data-Centric Debugging: mitigating model failures via targeted data collection.
CoRR, 2022

Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems.
CoRR, 2022

Interpretable Mixture of Experts for Structured Data.
CoRR, 2022

Core Risk Minimization using Salient ImageNet.
CoRR, 2022

Understanding Failure Modes of Self-Supervised Learning.
CoRR, 2022

Certifying Model Accuracy under Distribution Shifts.
CoRR, 2022

Toward Efficient Robust Training against Union of $\ell_p$ Threat Models.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Explicit Tradeoffs between Adversarial and Natural Distributional Robustness.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Hard ImageNet: Segmentations for Objects with Strong Spurious Cues.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Improved techniques for deterministic l2 robustness.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Lethal Dose Conjecture on Data Poisoning.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

FOCUS: Familiar Objects in Common and Uncommon Settings.
Proceedings of the International Conference on Machine Learning, 2022

Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregation.
Proceedings of the International Conference on Machine Learning, 2022

Policy Smoothing for Provably Robust Reinforcement Learning.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Salient ImageNet: How to discover spurious features in Deep Learning?
Proceedings of the Tenth International Conference on Learning Representations, 2022

A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Provable Adversarial Robustness for Fractional Lp Threat Models.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021
On Hard Episodes in Meta-Learning.
CoRR, 2021

Causal ImageNet: How to discover spurious features in Deep Learning?
CoRR, 2021

Householder Activations for Provable Robustness against Adversarial Attacks.
CoRR, 2021

Understanding Overparameterization in Generative Adversarial Networks.
CoRR, 2021

Improved, Deterministic Smoothing for L1 Certified Robustness.
CoRR, 2021

Unsupervised anomaly detection with adversarial mirrored autoencoders.
Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

Improving Deep Learning Interpretability by Saliency Guided Training.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Skew Orthogonal Convolutions.
Proceedings of the 38th International Conference on Machine Learning, 2021

Improved, Deterministic Smoothing for L<sub>1</sub> Certified Robustness.
Proceedings of the 38th International Conference on Machine Learning, 2021

Perceptual Adversarial Robustness: Defense Against Unseen Threat Models.
Proceedings of the 9th International Conference on Learning Representations, 2021

Influence Functions in Deep Learning Are Fragile.
Proceedings of the 9th International Conference on Learning Representations, 2021

Understanding Over-parameterization in Generative Adversarial Networks.
Proceedings of the 9th International Conference on Learning Representations, 2021

Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution Layers.
Proceedings of the 9th International Conference on Learning Representations, 2021

Deep Partition Aggregation: Provable Defenses against General Poisoning Attacks.
Proceedings of the 9th International Conference on Learning Representations, 2021

Low Curvature Activations Reduce Overfitting in Adversarial Training.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning.
Proceedings of the FAccT '21: 2021 ACM Conference on Fairness, 2021

GANs with Conditional Independence Graphs: On Subadditivity of Probability Divergences.
Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Winning Lottery Tickets in Deep Generative Models.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Spectral Alignment of Graphs.
IEEE Trans. Netw. Sci. Eng., 2020

Understanding GANs in the LQG Setting: Formulation, Generalization and Stability.
IEEE J. Sel. Areas Inf. Theory, 2020

Tight Second-Order Certificates for Randomized Smoothing.
CoRR, 2020

GANs with Variational Entropy Regularizers: Applications in Mitigating the Mode-Collapse Issue.
CoRR, 2020

Deep Partition Aggregation: Provable Defense against General Poisoning Attacks.
CoRR, 2020

Mirrored Autoencoders with Simplex Interpolation for Unsupervised Anomaly Detection.
CoRR, 2020

Subadditivity of Probability Divergences on Bayes-Nets with Applications to Time Series GANs.
CoRR, 2020

Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Certifying Confidence via Randomized Smoothing.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Benchmarking Deep Learning Interpretability in Time Series Predictions.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Robust Optimal Transport with Applications in Generative Modeling and Domain Adaptation.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

(De)Randomized Smoothing for Certifiable Defense against Patch Attacks.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness.
Proceedings of the 37th International Conference on Machine Learning, 2020

On Second-Order Group Influence Functions for Black-Box Predictions.
Proceedings of the 37th International Conference on Machine Learning, 2020

Second-Order Provable Defenses against Adversarial Attacks.
Proceedings of the 37th International Conference on Machine Learning, 2020

Deep k-NN Defense Against Clean-Label Data Poisoning Attacks.
Proceedings of the Computer Vision - ECCV 2020 Workshops, 2020

Adversarial Robustness of Flow-Based Generative Models.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attacks.
Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

Maximum Likelihood Embedding of Logistic Random Dot Product Graphs.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

Robustness Certificates for Sparse Adversarial Attacks by Randomized Ablation.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

Adversarially Robust Distillation.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
Network Infusion to Infer Information Sources in Networks.
IEEE Trans. Netw. Sci. Eng., 2019

Playing it Safe: Adversarial Robustness with an Abstain Option.
CoRR, 2019

Bounding Singular Values of Convolution Layers.
CoRR, 2019

Strong Baseline Defenses Against Clean-Label Poisoning Attacks.
CoRR, 2019

Interpretable Adversarial Training for Text.
CoRR, 2019

Certifiably Robust Interpretation in Deep Learning.
CoRR, 2019

Robustness Certificates Against Adversarial Examples for ReLU Networks.
CoRR, 2019

Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation.
CoRR, 2019

Compressing GANs using Knowledge Distillation.
CoRR, 2019

Functional Adversarial Attacks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Input-Cell Attention Reduces Vanishing Saliency of Recurrent Neural Networks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Quantum Wasserstein Generative Adversarial Networks.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation.
Proceedings of the 36th International Conference on Machine Learning, 2019

Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs.
Proceedings of the 36th International Conference on Machine Learning, 2019

Are adversarial examples inevitable?
Proceedings of the 7th International Conference on Learning Representations, 2019

Normalized Wasserstein for Mixture Distributions With Applications in Adversarial Learning and Domain Adaptation.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

2018
Porcupine Neural Networks: Approximating Neural Network Landscapes.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

2017
Network Maximal Correlation.
IEEE Trans. Netw. Sci. Eng., 2017

Understanding GANs: the LQG Setting.
CoRR, 2017

Porcupine Neural Networks: (Almost) All Local Optima are Global.
CoRR, 2017

Maximally Correlated Principal Component Analysis.
CoRR, 2017

Tensor Biclustering.
Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

A memristor based binary multiplier.
Proceedings of the 30th IEEE Canadian Conference on Electrical and Computer Engineering, 2017

2016
On the analysis of complex networks: fundamental limits, scalable algorithms, and applications.
PhD thesis, 2016

Spectral Alignment of Networks.
CoRR, 2016

2015
Integrative analysis of 111 reference human epigenomes Open.
, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,
Nat., 2015

A Perspective on Future Research Directions in Information Theory.
CoRR, 2015

2014
Backward Adaptation for Power Efficient Sampling.
IEEE Trans. Signal Process., 2014

On Network Functional Compression.
IEEE Trans. Inf. Theory, 2014

Biclustering Usinig Message Passing.
Proceedings of the Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, 2014

Tunable sparse network coding for multicast networks.
Proceedings of the International Symposium on Network Coding, 2014

2012
Time-Stampless Adaptive Nonuniform Sampling for Stochastic Signals.
IEEE Trans. Signal Process., 2012

Empirical rate-distortion study of compressive sensing-based joint source-channel coding.
Proceedings of the Conference Record of the Forty Sixth Asilomar Conference on Signals, 2012

2011
A power efficient sensing/communication scheme: Joint source-channel-network coding by using compressive sensing.
Proceedings of the 49th Annual Allerton Conference on Communication, 2011

2010
Cases where finding the minimum entropy coloring of a characteristic graph is a polynomial time problem.
Proceedings of the IEEE International Symposium on Information Theory, 2010

Compressive sensing over networks.
Proceedings of the 48th Annual Allerton Conference on Communication, 2010

Locally Adaptive Sampling.
Proceedings of the 48th Annual Allerton Conference on Communication, 2010

2009
Robust Audio Data Hiding Using Correlated Quantization With Histogram-Based Detector.
IEEE Trans. Multim., 2009

Impulsive Noise Cancellation Based on Soft Decision and Recursion.
IEEE Trans. Instrum. Meas., 2009

Multi-Functional Compression with Side Information.
Proceedings of the Global Communications Conference, 2009. GLOBECOM 2009, Honolulu, Hawaii, USA, 30 November, 2009

When do only sources need to compute? On functional compression in tree networks.
Proceedings of the 47th Annual Allerton Conference on Communication, 2009

2008
Lower and Upper Bounds for Throughput Capacity of a Cognitive Ad Hoc Network Overlaid on a Cellular Network.
Proceedings of the WCNC 2008, IEEE Wireless Communications & Networking Conference, March 31 2008, 2008

Impulsive noise cancellation using CFAR and iterative techniques.
Proceedings of the 2008 International Conference on Telecommunications, 2008

Salt and pepper noise removal for image signals.
Proceedings of the 2008 International Conference on Telecommunications, 2008


  Loading...