0

Soheil Feizi

Papers
21

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
21papers

Authored papers

21

Failing to Explore: Language Models on Interactive Tasks

arXiv 2026

2026

Adversarial Paraphrasing: A Universal Attack for Humanizing AI-Generated Text

arXiv 2025

2025

Schoenfeld's Anatomy of Mathematical Reasoning by Language Models

arXiv 2025

2025

Almost AI, Almost Human: The Challenge of Detecting AI-Polished Writing

arXiv 2025

2025

Gaming Tool Preferences in Agentic LLMs

arXiv 2025

2025

DyePack: Provably Flagging Test Set Contamination in LLMs Using Backdoors

arXiv 2025

2025

What do we learn from inverting CLIP models?

arXiv 2024

2024

Loki: Low-rank Keys for Efficient Sparse Attention

arXiv 2024

2024

RESTOR: Knowledge Recovery through Machine Unlearning

arXiv 2024

2024

Understanding and Mitigating Compositional Issues in Text-to-Image Generative Models

arXiv 2024

2024

Fast Adversarial Attacks on Language Models In One GPU Minute

arXiv 2024

2024

Certifying LLM Safety against Adversarial Prompting

arXiv 2023

2023

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks

arXiv 2023

2023

Text-To-Concept (and Back) via Cross-Model Alignment

arXiv 2023

2023

CUDA: Convolution-based Unlearnable Datasets

CVPR 2023 1

2023

DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness

arXiv 2023

2023

Exploring Geometry of Blind Spots in Vision Models

exploring-geometry-of-blind-spots-in-vision

2023

Can AI-Generated Text be Reliably Detected?

arXiv 2023

2023

Run-Off Election: Improved Provable Defense against Data Poisoning Attacks

arXiv 2023

2023

Towards Improved Input Masking for Convolutional Neural Networks

ICCV 2023 1

2022

FOCUS: Familiar Objects in Common and Uncommon Settings

focus-familiar-objects-in-common-and-uncommon-1

2021

Affiliations

No known affiliations.

Frequent co-authors

10

from 21 papers