Search Results for author:
Found 15 papers, 1 papers with code
Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifiers
Machine Learning (ML) algorithms are used to train computers to perform a variety of complex tasks and improve with experience.
Have You Stolen My Model? Evasion Attacks Against Deep Neural Network Watermarking Techniques
The watermark allows the legitimate owner to detect copyright infringements of his model.
The Naked Sun: Malicious Cooperation Between Benign-Looking Processes
Recent progress in machine learning has generated promising results in behavioral malware detection.
EnCoD: Distinguishing Compressed and Encrypted File Fragments
To address this issue, we design EnCoD, a learning-based classifier which can reliably distinguish compressed and encrypted data, starting with fragments as small as 512 bytes.
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.
Evaluating the Robustness of Geometry-Aware Instance-Reweighted Adversarial Training
The original model shows an accuracy of 59% under AutoAttack - when trained with additional data with pseudo-labels.
Reliable Detection of Compressed and Encrypted Data
We evaluate EnCoD on a dataset of 16 different file types and fragment sizes ranging from 512B to 8KB.
PassFlow: Guessing Passwords with Generative Flows
In this paper, we propose PassFlow, a flow-based generative model approach to password guessing.
MalPhase: Fine-Grained Malware Detection Using Network Flow Data
Economic incentives encourage malware authors to constantly develop new, increasingly complex malware to steal sensitive data or blackmail individuals and companies into paying large ransoms.
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.
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.
Minerva: A File-Based Ransomware Detector
Ransomware is a rapidly evolving type of malware designed to encrypt user files on a device, making them inaccessible in order to exact a ransom.
OliVaR: Improving Olive Variety Recognition using Deep Neural Networks
The morphological classification consists of the visual pairwise comparison of different organs of the olive tree, where the most important organ is considered to be the endocarp.
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.
Have You Poisoned My Data? Defending Neural Networks against Data Poisoning
We thoroughly evaluate our proposed approach and compare it to existing state-of-the-art defenses using multiple architectures, datasets, and poison budgets.
