Neal Mangaokar

Orcid: 0000-0002-0684-4971

According to our database1, Neal Mangaokar authored at least 12 papers between 2020 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2024

PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023
Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attacks.
CoRR, 2023

Investigating Stateful Defenses Against Black-Box Adversarial Examples.
CoRR, 2023

Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks.
Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, 2023

2022
Dispelling Misconceptions and Characterizing the Failings of Deepfake Detection.
IEEE Secur. Priv., 2022

Towards Adversarially Robust Deepfake Detection: An Ensemble Approach.
CoRR, 2022

GRAPHITE: Generating Automatic Physical Examples for Machine-Learning Attacks on Computer Vision Systems.
Proceedings of the 7th IEEE European Symposium on Security and Privacy, 2022

2021
Deepfake Videos in the Wild: Analysis and Detection.
Proceedings of the WWW '21: The Web Conference 2021, 2021

T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification.
Proceedings of the 30th USENIX Security Symposium, 2021

2020
Jekyll: Attacking Medical Image Diagnostics using Deep Generative Models.
Proceedings of the IEEE European Symposium on Security and Privacy, 2020

NoiseScope: Detecting Deepfake Images in a Blind Setting.
Proceedings of the ACSAC '20: Annual Computer Security Applications Conference, 2020


  Loading...