Search Results for author:
Found 9 papers, 4 papers with code
Organic or Diffused: Can We Distinguish Human Art from AI-generated Images?
We curate real human art across 7 styles, generate matching images from 5 generative models, and apply 8 detectors (5 automated detectors and 3 different human groups including 180 crowdworkers, 4000+ professional artists, and 13 expert artists experienced at detecting AI).
Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
In this paper, we show that poisoning attacks can be successful on generative models.
SoK: Anti-Facial Recognition Technology
The rapid adoption of facial recognition (FR) technology by both government and commercial entities in recent years has raised concerns about civil liberties and privacy.
Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks
We propose a novel iterative clustering and pruning solution that trims "innocent" training samples, until all that remains is the set of poisoned data responsible for the attack.
A Real-time Defense against Website Fingerprinting Attacks
We experimentally demonstrate that Dolos provides 94+% protection against state-of-the-art WF attacks under a variety of settings.
Website Fingerprinting Attacks
Cryptography and Security
Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks
In particular, query-based black-box attacks do not require knowledge of the deep learning model, but can compute adversarial examples over the network by submitting queries and inspecting returns.
Fawkes: Protecting Privacy against Unauthorized Deep Learning Models
In this paper, we propose Fawkes, a system that helps individuals inoculate their images against unauthorized facial recognition models.
Piracy Resistant Watermarks for Deep Neural Networks
We empirically show that our proposed watermarks achieve piracy resistance and other watermark properties, over a wide range of tasks and models.
Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networks
Attackers' optimization algorithms gravitate towards trapdoors, leading them to produce attacks similar to trapdoors in the feature space.
