Nasir Memon
YOU?
Author Swipe
View article: DiffClean: Diffusion-based Makeup Removal for Accurate Age Estimation
DiffClean: Diffusion-based Makeup Removal for Accurate Age Estimation Open
Accurate age verification can protect underage users from unauthorized access to online platforms and e-commerce sites that provide age-restricted services. However, accurate age estimation can be confounded by several factors, including f…
View article: FaceCloak: Learning to Protect Face Templates
FaceCloak: Learning to Protect Face Templates Open
Generative models can reconstruct face images from encoded representations (templates) bearing remarkable likeness to the original face, raising security and privacy concerns. We present \textsc{FaceCloak}, a neural network framework that …
View article: WavePulse: Real-time Content Analytics of Radio Livestreams
WavePulse: Real-time Content Analytics of Radio Livestreams Open
Radio remains a pervasive medium for mass information dissemination, with AM/FM stations reaching more Americans than either smartphone-based social networking or live television. Increasingly, radio broadcasts are also streamed online and…
View article: TraSCE: Trajectory Steering for Concept Erasure
TraSCE: Trajectory Steering for Concept Erasure Open
Recent advancements in text-to-image diffusion models have brought them to the public spotlight, becoming widely accessible and embraced by everyday users. However, these models have been shown to generate harmful content such as not-safe-…
View article: Classifier-Free Guidance inside the Attraction Basin May Cause Memorization
Classifier-Free Guidance inside the Attraction Basin May Cause Memorization Open
Diffusion models are prone to exactly reproduce images from the training data. This exact reproduction of the training data is concerning as it can lead to copyright infringement and/or leakage of privacy-sensitive information. In this pap…
View article: Mitigating the Impact of Attribute Editing on Face Recognition
Mitigating the Impact of Attribute Editing on Face Recognition Open
Through a large-scale study over diverse face images, we show that facial attribute editing using modern generative AI models can severely degrade automated face recognition systems. This degradation persists even with identity-preserving …
View article: PITCH: AI-assisted Tagging of Deepfake Audio Calls using Challenge-Response
PITCH: AI-assisted Tagging of Deepfake Audio Calls using Challenge-Response Open
The rise of AI voice-cloning technology, particularly audio Real-time Deepfakes (RTDFs), has intensified social engineering attacks by enabling real-time voice impersonation that bypasses conventional enrollment-based authentication. This …
View article: Zero-shot demographically unbiased image generation from an existing biased StyleGAN
Zero-shot demographically unbiased image generation from an existing biased StyleGAN Open
Face recognition systems have made significant strides thanks to data-heavy deep learning models, but these models rely on large privacy-sensitive datasets. Recent work in facial analysis and recognition have thus started making use of syn…
View article: Zero-shot demographically unbiased image generation from an existing biased StyleGAN
Zero-shot demographically unbiased image generation from an existing biased StyleGAN Open
Face recognition systems have made significant strides thanks to data-heavy deep learning models, but these models rely on large privacy-sensitive datasets. Recent work in facial analysis and recognition have thus started making use of syn…
View article: Alpha-wolves and Alpha-mammals: Exploring Dictionary Attacks on Iris Recognition Systems
Alpha-wolves and Alpha-mammals: Exploring Dictionary Attacks on Iris Recognition Systems Open
A dictionary attack in a biometric system entails the use of a small number of strategically generated images or templates to successfully match with a large number of identities, thereby compromising security. We focus on dictionary attac…
View article: Information Forensics and Security: A quarter-century-long journey
Information Forensics and Security: A quarter-century-long journey Open
Information Forensics and Security (IFS) is an active R&D area whose goal is to ensure that people use devices, data, and intellectual properties for authorized purposes and to facilitate the gathering of solid evidence to hold perpetrator…
View article: Fair GANs through model rebalancing for extremely imbalanced class distributions
Fair GANs through model rebalancing for extremely imbalanced class distributions Open
Deep generative models require large amounts of training data. This often poses a problem as the collection of datasets can be expensive and difficult, in particular datasets that are representative of the appropriate underlying distributi…
View article: Identity-Preserving Aging of Face Images via Latent Diffusion Models
Identity-Preserving Aging of Face Images via Latent Diffusion Models Open
The performance of automated face recognition systems is inevitably impacted by the facial aging process. However, high quality datasets of individuals collected over several years are typically small in scale. In this work, we propose, tr…
View article: Information Forensics and Security: A quarter-century-long journey
Information Forensics and Security: A quarter-century-long journey Open
Information forensics and security (IFS) is an active R&D area whose goal is to ensure that people use devices, data, and intellectual properties for authorized purposes and to facilitate the gathering of solid evidence to hold perpetrator…
View article: Zero-shot racially balanced dataset generation using an existing biased StyleGAN2
Zero-shot racially balanced dataset generation using an existing biased StyleGAN2 Open
Facial recognition systems have made significant strides thanks to data-heavy deep learning models, but these models rely on large privacy-sensitive datasets. Further, many of these datasets lack diversity in terms of ethnicity and demogra…
View article: Dictionary Attacks on Speaker Verification
Dictionary Attacks on Speaker Verification Open
In this paper, we propose dictionary attacks against speaker verification - a novel attack vector that aims to match a large fraction of speaker population by chance. We introduce a generic formulation of the attack that can be used with v…
View article: A Dataless FaceSwap Detection Approach Using Synthetic Images
A Dataless FaceSwap Detection Approach Using Synthetic Images Open
Face swapping technology used to create "Deepfakes" has advanced significantly over the past few years and now enables us to create realistic facial manipulations. Current deep learning algorithms to detect deepfakes have shown promising r…
View article: GOTCHA: Real-Time Video Deepfake Detection via Challenge-Response
GOTCHA: Real-Time Video Deepfake Detection via Challenge-Response Open
With the rise of AI-enabled Real-Time Deepfakes (RTDFs), the integrity of online video interactions has become a growing concern. RTDFs have now made it feasible to replace an imposter's face with their victim in live video interactions. S…
View article: Diversity and Novelty MasterPrints: Generating Multiple DeepMasterPrints for Increased User Coverage
Diversity and Novelty MasterPrints: Generating Multiple DeepMasterPrints for Increased User Coverage Open
This work expands on previous advancements in genetic fingerprint spoofing via the DeepMasterPrints and introduces Diversity and Novelty MasterPrints. This system uses quality diversity evolutionary algorithms to generate dictionaries of a…
View article: Cross-Platform Multimodal Misinformation: Taxonomy, Characteristics and Detection for Textual Posts and Videos
Cross-Platform Multimodal Misinformation: Taxonomy, Characteristics and Detection for Textual Posts and Videos Open
Social media posts that direct users to YouTube videos are one of the most effective techniques for spreading misinformation. However, it has been observed that such posts rarely get deleted or flagged. Since multi-modal misinformation tha…
View article: Dictionary Attacks on Speaker Verification
Dictionary Attacks on Speaker Verification Open
In this paper, we propose dictionary attacks against speaker verification - a novel attack vector that aims to match a large fraction of speaker population by chance. We introduce a generic formulation of the attack that can be used with v…
View article: True or False: Studying the Work Practices of Professional Fact-Checkers
True or False: Studying the Work Practices of Professional Fact-Checkers Open
Misinformation has developed into a critical societal threat that can lead to disastrous societal consequences. Although fact-checking plays a key role in combating misinformation, relatively little research has empirically investigated wo…
View article: Distinguishability of keystroke dynamic template
Distinguishability of keystroke dynamic template Open
When keystroke dynamics are used for authentication, users tend to get different levels of security due to differences in the quality of their templates. This paper addresses this issue by proposing a metric to quantify the quality of keys…
View article: What’s in This Book and Why?
What’s in This Book and Why? Open
Multimedia forensics is a societally important and technically challenging research area that will need significant effort for the foreseeable future. While the research community is growing and work like that in this book demonstrates sig…
View article: Camera Identification at Large Scale
Camera Identification at Large Scale Open
Chapters 3 and 4 have shown that PRNU is a very effective solution for source camera verification, i.e., linking a visual object to its source camera Lukas et al. (2006). However, in order to determine the source camera, there has to be a …
View article: COLBAC: Shifting Cybersecurity from Hierarchical to Horizontal Designs
COLBAC: Shifting Cybersecurity from Hierarchical to Horizontal Designs Open
Cybersecurity suffers from an oversaturation of centralized, hierarchical systems and a lack of exploration in the area of horizontal security, or security techniques and technologies which utilize democratic participation for security dec…
View article: Hard-Attention for Scalable Image Classification
Hard-Attention for Scalable Image Classification Open
Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention architecture, which traverses image scale-space in a top-dow…
View article: The Role of the Crowd in Countering Misinformation: A Case Study of the COVID-19 Infodemic
The Role of the Crowd in Countering Misinformation: A Case Study of the COVID-19 Infodemic Open
Fact checking by professionals is viewed as a vital defense in the fight against misinformation.While fact checking is important and its impact has been significant, fact checks could have limited visibility and may not reach the intended …