Search Results for author: Shahroz Tariq

Found 16 papers, 6 papers with code

Integrative Tensor-based Anomaly Detection System For Satellites

no code implementations ICLR 2020 Youjin Shin, Sangyup Lee, Shahroz Tariq, Myeong Shin Lee, OkchulJung, Daewon Chung, Simon Woo

Detecting anomalies is of growing importance for various industrial applications and mission-critical infrastructures, including satellite systems.

Anomaly Detection

Am I a Real or Fake Celebrity? Measuring Commercial Face Recognition Web APIs under Deepfake Impersonation Attack

no code implementations1 Mar 2021 Shahroz Tariq, Sowon Jeon, Simon S. Woo

Moreover, we propose practical defense strategies to mitigate DI attacks, reducing the attack success rates to as low as 0% and 0. 02% for targeted and non-targeted attacks, respectively.

Face Recognition Face Swapping

One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework

1 code implementation1 May 2021 Shahroz Tariq, Sangyup Lee, Simon S. Woo

Beyond detecting a single type of DF from benchmark deepfake datasets, we focus on developing a generalized approach to detect multiple types of DFs, including deepfakes from unknown generation methods such as DeepFake-in-the-Wild (DFW) videos.

Face Swapping

CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation

2 code implementations6 Jul 2021 Minha Kim, Shahroz Tariq, Simon S. Woo

Over the last few decades, artificial intelligence research has made tremendous strides, but it still heavily relies on fixed datasets in stationary environments.

Continual Learning Domain Adaptation +3

Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors

no code implementations7 Sep 2021 Hasam Khalid, Minha Kim, Shahroz Tariq, Simon S. Woo

On the other hand, to develop a good deepfake detector that can cope with the recent advancements in deepfake generation, we need to have a detector that can detect deepfakes of multiple modalities, i. e., videos and audios.

DeepFake Detection Face Swapping

Evaluating the Robustness of Time Series Anomaly and Intrusion Detection Methods against Adversarial Attacks

no code implementations29 Sep 2021 Shahroz Tariq, Simon S. Woo

To the best of our knowledge, we are the first to demonstrate the vulnerabilities of anomaly and intrusion detection systems against adversarial attacks.

Intrusion Detection Time Series +1

Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerability

1 code implementation24 Aug 2022 Shahroz Tariq, Binh M. Le, Simon S. Woo

To the best of our understanding, we demonstrate, for the first time, the vulnerabilities of anomaly detection systems against adversarial attacks.

Anomaly Detection Time Series +1

Why Do Facial Deepfake Detectors Fail?

no code implementations25 Feb 2023 Binh Le, Shahroz Tariq, Alsharif Abuadbba, Kristen Moore, Simon Woo

Recent rapid advancements in deepfake technology have allowed the creation of highly realistic fake media, such as video, image, and audio.

DeepFake Detection Face Swapping +1

Bridging Optimal Transport and Jacobian Regularization by Optimal Trajectory for Enhanced Adversarial Defense

no code implementations21 Mar 2023 Binh M. Le, Shahroz Tariq, Simon S. Woo

Our work is the first carefully analyzes and characterizes these two schools of approaches, both theoretically and empirically, to demonstrate how each approach impacts the robust learning of a classifier.

Adversarial Attack Adversarial Defense +1

Deepfake in the Metaverse: Security Implications for Virtual Gaming, Meetings, and Offices

no code implementations26 Mar 2023 Shahroz Tariq, Alsharif Abuadbba, Kristen Moore

This paper examines the security implications of deepfakes in the metaverse, specifically in the context of gaming, online meetings, and virtual offices.

Face Swapping

SoK: Facial Deepfake Detectors

no code implementations9 Jan 2024 Binh M. Le, Jiwon Kim, Shahroz Tariq, Kristen Moore, Alsharif Abuadbba, Simon S. Woo

Our systematized analysis and experimentation lay the groundwork for a deeper understanding of deepfake detectors and their generalizability, paving the way for future research focused on creating detectors adept at countering various attack scenarios.

DeepFake Detection Face Swapping

A2C: A Modular Multi-stage Collaborative Decision Framework for Human-AI Teams

no code implementations25 Jan 2024 Shahroz Tariq, Mohan Baruwal Chhetri, Surya Nepal, Cecile Paris

By harnessing the strengths of both humans and AI, it significantly improves the efficiency and effectiveness of complex decision-making in dynamic and evolving environments.

Decision Making

Cannot find the paper you are looking for? You can Submit a new open access paper.