Picture for Hamed Firooz

Hamed Firooz

Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning

Apr 04, 2023
Ajinkya Tejankar, Maziar Sanjabi, Qifan Wang, Sinong Wang, Hamed Firooz, Hamed Pirsiavash, Liang Tan

Figure 1 for Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning

Figure 2 for Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning

Figure 3 for Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning

Figure 4 for Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning

* Accepted to CVPR 2023

Access Paper or Ask Questions

FRAME: Evaluating Simulatability Metrics for Free-Text Rationales

Jul 02, 2022
Aaron Chan, Shaoliang Nie, Liang Tan, Xiaochang Peng, Hamed Firooz, Maziar Sanjabi, Xiang Ren

Figure 1 for FRAME: Evaluating Simulatability Metrics for Free-Text Rationales

Figure 2 for FRAME: Evaluating Simulatability Metrics for Free-Text Rationales

Figure 3 for FRAME: Evaluating Simulatability Metrics for Free-Text Rationales

Figure 4 for FRAME: Evaluating Simulatability Metrics for Free-Text Rationales

* 16 pages, 18 figures

Access Paper or Ask Questions

ER-TEST: Evaluating Explanation Regularization Methods for NLP Models

May 25, 2022
Brihi Joshi, Aaron Chan, Ziyi Liu, Shaoliang Nie, Maziar Sanjabi, Hamed Firooz, Xiang Ren

Figure 1 for ER-TEST: Evaluating Explanation Regularization Methods for NLP Models

Figure 2 for ER-TEST: Evaluating Explanation Regularization Methods for NLP Models

Figure 3 for ER-TEST: Evaluating Explanation Regularization Methods for NLP Models

Figure 4 for ER-TEST: Evaluating Explanation Regularization Methods for NLP Models

* 19 pages, 10 figures

Access Paper or Ask Questions

Detecting and Understanding Harmful Memes: A Survey

May 09, 2022
Shivam Sharma, Firoj Alam, Md. Shad Akhtar, Dimitar Dimitrov, Giovanni Da San Martino, Hamed Firooz, Alon Halevy, Fabrizio Silvestri, Preslav Nakov, Tanmoy Chakraborty

Figure 1 for Detecting and Understanding Harmful Memes: A Survey

Figure 2 for Detecting and Understanding Harmful Memes: A Survey

Figure 3 for Detecting and Understanding Harmful Memes: A Survey

* Accepted at IJCAI-ECAI 2022 (Survey Track)

Access Paper or Ask Questions

Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem

Apr 12, 2022
Khalil Mrini, Shaoliang Nie, Jiatao Gu, Sinong Wang, Maziar Sanjabi, Hamed Firooz

Figure 1 for Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem

Figure 2 for Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem

Figure 3 for Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem

Figure 4 for Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem

* Long paper accepted to ACL 2022 Findings

Access Paper or Ask Questions

UniREx: A Unified Learning Framework for Language Model Rationale Extraction

Dec 16, 2021
Aaron Chan, Maziar Sanjabi, Lambert Mathias, Liang Tan, Shaoliang Nie, Xiaochang Peng, Xiang Ren, Hamed Firooz

Figure 1 for UniREx: A Unified Learning Framework for Language Model Rationale Extraction

Figure 2 for UniREx: A Unified Learning Framework for Language Model Rationale Extraction

Figure 3 for UniREx: A Unified Learning Framework for Language Model Rationale Extraction

Figure 4 for UniREx: A Unified Learning Framework for Language Model Rationale Extraction

* 14 pages, 6 figures

Access Paper or Ask Questions