gateway_proxy_handler Component Data Compromise

The vulnerability of the gatewayproxyhandler component in the Machine Learning Lifecycle Management platform is related to insufficient validation of requests at the server side. Exploiting this vulnerability could allow an attacker to compromise the confidentiality, integrity, and accessibility ...

Exploit for CVE-2017-3143

Awesome Vulnerability Research 🦄 A curated list of the awesome resources about the Vulnerability Research First things first: There are no exploits in this project. Vulnerabilities != Exploits A Vulnerability resides in the software itself, doing nothing on its own. If you are really curious abou...

GyoiThon

This is an offensive tool for penetration testing using machine learning. It is called GyoiThon. The tool is designed to perform penetration testing using machine learning algorithms and can be used to identify vulnerabilities in web applications and services. The tool uses a variety of technique...

Two Views, One Truth: Spectral and Self-Supervised Features Fusion for Robust Speech Deepfake Detection

Recent advances in synthetic speech have made audio deepfakes increasingly realistic, posing significant security risks. Existing detection methods that rely on a single modality, either raw waveform embeddings or spectral based features, are vulnerable to non spoof disturbances and often overfit...

ModShift: Model Privacy Via Designed Shifts

In this paper, shifts are introduced to preserve model privacy against an eavesdropper in federated learning. Model learning is treated as a parameter estimation problem. This perspective allows us to derive the Fisher Information matrix of the model updates from the shifted updates and drive the...

FedBAP: Backdoor Defense Via Benign Adversarial Perturbation in Federated Learning

Federated Learning FL enables collaborative model training while preserving data privacy, but it is highly vulnerable to backdoor attacks. Most existing defense methods in FL have limited effectiveness due to their neglect of the model's over-reliance on backdoor triggers, particularly as the...

Subliminal Learning in AIs

Today's freaky LLM behavior: We study subliminal learning, a surprising phenomenon where language models learn traits from model-generated data that is semantically unrelated to those traits. For example, a "student" model learns to prefer owls when trained on sequences of numbers generated by a...

PurpCode: Reasoning for Safer Code Generation

We introduce PurpCode, the first post-training recipe for training safe code reasoning models towards generating secure code and defending against malicious cyberactivities. PurpCode trains a reasoning model in two stages: i Rule Learning, which explicitly teaches the model to reference cybersafe...

Microsoft Azure Machine Learning elevation of privilege vulnerability (CNVD-2025-17136)

Microsoft Azure Machine Learning is a machine learning services platform from Microsoft USA. Microsoft Azure Machine Learning has a security vulnerability that can be exploited by an attacker to potentially cause elevation of privilege...

Microsoft Azure Machine Learning Elevation of Privilege Vulnerability

Microsoft Azure Machine Learning is a machine learning services platform from Microsoft USA. Microsoft Azure Machine Learning has a security vulnerability that can be exploited by an attacker to potentially cause elevation of privilege...

Microsoft Azure Machine Learning elevation of privilege vulnerability (CNVD-2025-17135)

Microsoft Azure Machine Learning is a machine learning services platform from Microsoft USA. Microsoft Azure Machine Learning has a security vulnerability that can be exploited by an attacker to potentially cause elevation of privilege...

Regression-Aware Continual Learning for Android Malware Detection

Malware evolves rapidly, forcing machine learning ML-based detectors to adapt continuously. With antivirus vendors processing hundreds of thousands of new samples daily, datasets can grow to billions of examples, making full retraining impractical. Continual learning CL has emerged as a scalable...

LLM Meets the Sky: Heuristic Multi-Agent Reinforcement Learning for Secure Heterogeneous UAV Networks

This work tackles the physical layer security PLS problem of maximizing the secrecy rate in heterogeneous UAV networks HetUAVNs under propulsion energy constraints. Unlike prior studies that assume uniform UAV capabilities or overlook energy-security trade-offs, we consider a realistic scenario...

On One-Shot Signatures, Quantum Vs Classical Binding, and Obfuscating Permutations

One-shot signatures OSS were defined by Amos, Georgiou, Kiayias, and Zhandry STOC'20. These allow for signing exactly one message, after which the signing key self-destructs, preventing a second message from ever being signed. While such an object is impossible classically, Amos et al observe tha...

Leveraging Trustworthy AI for Automotive Security in Multi-Domain Operations: Towards a Responsive Human-AI Multi-Domain Task Force for Cyber Social Security

Multi-Domain Operations MDOs emphasize cross-domain defense against complex and synergistic threats, with civilian infrastructures like smart cities and Connected Autonomous Vehicles CAVs emerging as primary targets. As dual-use assets, CAVs are vulnerable to Multi-Surface Threats MSTs,...

Learning-Based Privacy-Preserving Graph Publishing against Sensitive Link Inference Attacks

Publishing graph data is widely desired to enable a variety of structural analyses and downstream tasks. However, it also potentially poses severe privacy leakage, as attackers may leverage the released graph data to launch attacks and precisely infer private information such as the existence of...

hermes-agent

Hermes Agent ☤ The self-improving AI agent b...

LENS-DF: Deepfake Detection and Temporal Localization for Long-Form Noisy Speech

This study introduces LENS-DF, a novel and comprehensive recipe for training and evaluating audio deepfake detection and temporal localization under complicated and realistic audio conditions. The generation part of the recipe outputs audios from the input dataset with several critical...

Scaling Decentralized Learning with FLock

Fine-tuning the large language models LLMs are prevented by the deficiency of centralized control and the massive computing and communication overhead on the decentralized schemes. While the typical standard federated learning FL supports data privacy, the central server requirement creates a...

In-Context Learning of Vision Language Models for Detection of Physical and Digital Attacks against Face Recognition Systems

Recent advances in biometric systems have significantly improved the detection and prevention of fraudulent activities. However, as detection methods improve, attack techniques become increasingly sophisticated. Attacks on face recognition systems can be broadly divided into physical and digital...