Search Results for author:
Found 14 papers, 5 papers with code
Do You Trust Your Model? Emerging Malware Threats in the Deep Learning Ecosystem
We introduce MaleficNet 2. 0, a novel technique to embed self-extracting, self-executing malware in neural networks.
PassGPT: Password Modeling and (Guided) Generation with Large Language Models
Large language models (LLMs) successfully model natural language from vast amounts of text without the need for explicit supervision.
Automatic Measures for Evaluating Generative Design Methods for Architects
Of interest for architects is to use these methods to generate design proposals from conceptual sketches, usually hand-drawn sketches that are quickly developed and can embody a design intent.
CoProver: A Recommender System for Proof Construction
We evaluate CoProver on a series of well-established metrics originating from the recommender system and information retrieval communities, respectively.
Revisiting Variable Ordering for Real Quantifier Elimination using Machine Learning
Prior work has demonstrated that machine learning can be useful in determining efficient variable orderings.
Trust in Motion: Capturing Trust Ascendancy in Open-Source Projects using Hybrid AI
We refer to this process of influence-seeking and trust-building as trust ascendancy.
Adversarial Scratches: Deployable Attacks to CNN Classifiers
We present Adversarial Scratches: a novel L0 black-box attack, which takes the form of scratches in images, and which possesses much greater deployability than other state-of-the-art attacks.
TATTOOED: A Robust Deep Neural Network Watermarking Scheme based on Spread-Spectrum Channel Coding
Being trained on proprietary information, these models provide a competitive edge for the owner company.
FedComm: Federated Learning as a Medium for Covert Communication
Proposed as a solution to mitigate the privacy implications related to the adoption of deep learning, Federated Learning (FL) enables large numbers of participants to successfully train deep neural networks without having to reveal the actual private training data.
Capture the Bot: Using Adversarial Examples to Improve CAPTCHA Robustness to Bot Attacks
To this date, CAPTCHAs have served as the first line of defense preventing unauthorized access by (malicious) bots to web-based services, while at the same time maintaining a trouble-free experience for human visitors.
Scratch that! An Evolution-based Adversarial Attack against Neural Networks
We study black-box adversarial attacks for image classifiers in a constrained threat model, where adversaries can only modify a small fraction of pixels in the form of scratches on an image.
WHAT ARE GANS USEFUL FOR?
In this paper, we noticed that even though GANs might not be able to generate samples from the underlying distribution (or we cannot tell at least), they are capturing some structure of the data in that high dimensional space.
PassGAN: A Deep Learning Approach for Password Guessing
State-of-the-art password guessing tools, such as HashCat and John the Ripper, enable users to check billions of passwords per second against password hashes.
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Unfortunately, we show that any privacy-preserving collaborative deep learning is susceptible to a powerful attack that we devise in this paper.
