Search Results for author:
Found 16 papers, 14 papers with code
Exploring the Adversarial Capabilities of Large Language Models
The proliferation of large language models (LLMs) has sparked widespread and general interest due to their strong language generation capabilities, offering great potential for both industry and research.
Defending Our Privacy With Backdoors
We propose a rather easy yet effective defense based on backdoor attacks to remove private information such as names and faces of individuals from vision-language models by fine-tuning them for only a few minutes instead of re-training them from scratch.
Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
Label smoothing -- using softened labels instead of hard ones -- is a widely adopted regularization method for deep learning, showing diverse benefits such as enhanced generalization and calibration.
Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data
To address this challenge, we propose a novel approach that enables model training on potentially poisoned datasets by utilizing the power of recent diffusion models.
Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models
The field of artificial intelligence (AI) has experienced remarkable progress in recent years, driven by the widespread adoption of open-source machine learning models in both research and industry.
Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations
Neural network-based image classifiers are powerful tools for computer vision tasks, but they inadvertently reveal sensitive attribute information about their classes, raising concerns about their privacy.
Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness
Generative AI models have recently achieved astonishing results in quality and are consequently employed in a fast-growing number of applications.
SEGA: Instructing Text-to-Image Models using Semantic Guidance
This leaves the user with little semantic control.
The Stable Artist: Steering Semantics in Diffusion Latent Space
Large, text-conditioned generative diffusion models have recently gained a lot of attention for their impressive performance in generating high-fidelity images from text alone.
Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis
We introduce backdoor attacks against text-guided generative models and demonstrate that their text encoders pose a major tampering risk.
Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis
Models for text-to-image synthesis, such as DALL-E~2 and Stable Diffusion, have recently drawn a lot of interest from academia and the general public.
Does CLIP Know My Face?
Our large-scale experiments on CLIP demonstrate that individuals used for training can be identified with very high accuracy.
Combining AI and AM - Improving Approximate Matching through Transformer Networks
Then DLAM is able to detect the patterns in a typically much larger file, that is DLAM focuses on the use case of fragment detection.
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
Model inversion attacks (MIAs) aim to create synthetic images that reflect the class-wise characteristics from a target classifier's private training data by exploiting the model's learned knowledge.
To Trust or Not To Trust Prediction Scores for Membership Inference Attacks
Membership inference attacks (MIAs) aim to determine whether a specific sample was used to train a predictive model.
Learning to Break Deep Perceptual Hashing: The Use Case NeuralHash
Specifically, we show that current deep perceptual hashing may not be robust.
