Explainable Transformer-Based Email Phishing Classification with Adversarial Robustness

Phishing and related cyber threats are becoming more varied and technologically advanced. Among these, email-based phishing remains the most dominant and persistent threat. These attacks exploit human vulnerabilities to disseminate malware or gain unauthorized access to sensitive information. Dee...

deepagents (=0.0.12rc3), gradient-adk (>=0.0.3 <=0.1.9) +2 more potentially affected by CVE-2025-64439 via langgraph (>=1.0.0 <=1.0.0a4)

langgraph PYPI version =1.0.0, =0.0.3, =0.1.9 - langchain =1.0.0a10 - novachain =0.1.0 Source cves: CVE-2025-64439 Source advisory: SNYK:PYTHON-LANGGRAPH-13843663...

Machine and Deep Learning for Indoor UWB Jammer Localization

Ultra-wideband UWB localization delivers centimeter-scale accuracy but is vulnerable to jamming attacks, creating security risks for asset tracking and intrusion detection in smart buildings. Although machine learning ML and deep learning DL methods have improved tag localization, localizing...

Colliding with Adversaries at ECML-PKDD 2025 Adversarial Attack Competition 1st Prize Solution

This report presents the winning solution for Task 1 of Colliding with Adversaries: A Challenge on Robust Learning in High Energy Physics Discovery at ECML-PKDD 2025. The task required designing an adversarial attack against a provided classification model that maximizes misclassification while...

Injection, Attack and Erasure: Revocable Backdoor Attacks Via Machine Unlearning

Backdoor attacks pose a persistent security risk to deep neural networks DNNs due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack strategies still leave persistent traces that may be detect...

EUVD-2017-14481

Malware in sbrugna...

EUVD-2011-2602

Malware in sbrugna...

EUVD-2024-29242

Malicious code in bioql PyPI...

Decoding Deception: Understanding Automatic Speech Recognition Vulnerabilities in Evasion and Poisoning Attacks

Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on white-box attacks with constrained optimizations, and...

A Comparative Analysis of Ensemble-Based Machine Learning Approaches with Explainable AI for Multi-Class Intrusion Detection in Drone Networks

The growing integration of drones into civilian, commercial, and defense sectors introduces significant cybersecurity concerns, particularly with the increased risk of network-based intrusions targeting drone communication protocols. Detecting and classifying these intrusions is inherently...

Flow-Based Detection and Identification of Zero-Day IoT Cameras

The majority of consumer IoT devices lack mechanisms for administrators to monitor and control them, hindering tailored security policies. A key challenge is identifying whether a new device, especially a streaming IoT camera, has joined the network. We present zCamInspector, a system for...

Mask-GCG: Are All Tokens in Adversarial Suffixes Necessary for Jailbreak Attacks?

Jailbreak attacks on Large Language Models LLMs have demonstrated various successful methods whereby attackers manipulate models into generating harmful responses that they are designed to avoid. Among these, Greedy Coordinate Gradient GCG has emerged as a general and effective approach that...

Foe for Fraud: Transferable Adversarial Attacks in Credit Card Fraud Detection

Credit card fraud detection CCFD is a critical application of Machine Learning ML in the financial sector, where accurately identifying fraudulent transactions is essential for mitigating financial losses. ML models have demonstrated their effectiveness in fraud detection task, in particular with...

Enhancing Privacy in Decentralized Min-Max Optimization: a Differentially Private Approach

Decentralized min-max optimization allows multi-agent systems to collaboratively solve global min-max optimization problems by facilitating the exchange of model updates among neighboring agents, eliminating the need for a central server. However, sharing model updates in such systems carry a ris...

Label Inference Attacks against Federated Unlearning

Federated Unlearning FU has emerged as a promising solution to respond to the right to be forgotten of clients, by allowing clients to erase their data from global models without compromising model performance. Unfortunately, researchers find that the parameter variations of models induced by FU...

Optimizing IoT Threat Detection with Kolmogorov-Arnold Networks (KANs)

The exponential growth of the Internet of Things IoT has led to the emergence of substantial security concerns, with IoT networks becoming the primary target for cyberattacks. This study examines the potential of Kolmogorov-Arnold Networks KANs as an alternative to conventional machine learning...

SelectiveShield: Lightweight Hybrid Defense against Gradient Leakage in Federated Learning

Federated Learning FL enables collaborative model training on decentralized data but remains vulnerable to gradient leakage attacks that can reconstruct sensitive user information. Existing defense mechanisms, such as differential privacy DP and homomorphic encryption HE, often introduce a...

Evaluating Selective Encryption against Gradient Inversion Attacks

Gradient inversion attacks pose significant privacy threats to distributed training frameworks such as federated learning, enabling malicious parties to reconstruct sensitive local training data from gradient communications between clients and an aggregation server during the aggregation process...

When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs

As large language models become increasingly integrated into daily life, audio has emerged as a key interface for human-AI interaction. However, this convenience also introduces new vulnerabilities, making audio a potential attack surface for adversaries. Our research introduces WhisperInject, a...

IMU: Influence-Guided Machine Unlearning

Recent studies have shown that deep learning models are vulnerable to attacks and tend to memorize training data points, raising significant concerns about privacy leakage. This motivates the development of machine unlearning MU, i.e., a paradigm that enables models to selectively forget specific...