Exploit for Use After Free in Microsoft

CVE-2025-62221 Windows Cloud Files Mini Filter Driver Exploit...

T2I-Based Physical-World Appearance Attack against Traffic Sign Recognition Systems in Autonomous Driving

Traffic Sign Recognition TSR systems play a critical role in Autonomous Driving AD systems, enabling real-time detection of road signs, such as STOP and speed limit signs. While these systems are increasingly integrated into commercial vehicles, recent research has exposed their vulnerability to...

BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-Tuning

Knowledge Distillation KD is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party repositories introduces serious security risks -- most notably backdoor attacks. Existing KD backdoor methods are typically complex and computationally...

Design and Detection of Covert Man-In-The-Middle Cyberattacks on Water Treatment Plants

Cyberattacks targeting critical infrastructures, such as water treatment facilities, represent significant threats to public health, safety, and the environment. This paper introduces a systematic approach for modeling and assessing covert man-in-the-middle MitM attacks that leverage system...

HAMLOCK: HArdware-Model LOgically Combined AttacK

The growing use of third-party hardware accelerators e.g., FPGAs, ASICs for deep neural networks DNNs introduces new security vulnerabilities. Conventional model-level backdoor attacks, which only poison a model's weights to misclassify inputs with a specific trigger, are often detectable because...

This Is How Your LLM Gets Compromised

Poisoned data. Malicious LoRAs. Trojan model files. AI attacks are stealthier than ever—often invisible until it’s too late. Here’s how to catch them before they catch you...

SilentStriker: toward Stealthy Bit-Flip Attacks on Large Language Models

The rapid adoption of large language models LLMs in critical domains has spurred extensive research into their security issues. While input manipulation attacks e.g., prompt injection have been well studied, Bit-Flip Attacks BFAs -- which exploit hardware vulnerabilities to corrupt model paramete...

EvilOSX

This is an evil RAT Remote Administration Tool for macOS / OS X. It is a Python-based tool that allows for remote access and control of a compromised system. The tool is designed to be undetectable by anti-virus software and is persistent, meaning it will survive a reboot. The tool has a modular...

charlotte

This is a C++ shellcode launcher, fully undetected as of May 13th, 2021. It dynamically invokes Windows API functions, XOR encrypts shellcode and function names, and uses random XOR keys and variables per run. The code is designed to be stealthy and evade detection. The code is written in C++ and...

Detecting Stealthy Data Poisoning Attacks in AI Code Generators

Deep learning DL models for natural language-to-code generation have become integral to modern software development pipelines. However, their heavy reliance on large amounts of data, often collected from unsanitized online sources, exposes them to data poisoning attacks, where adversaries inject...

Crypto24 Ransomware Group Blends Legitimate Tools with Custom Malware for Stealth Attacks

Crypto24 is a ransomware group that stealthily blends legitimate tools with custom malware, using advanced evasion techniques to bypass security and EDR technologies...

VeriPHY: Physical Layer Signal Authentication for Wireless Communication in 5G Environments

Physical layer authentication PLA uses inherent characteristics of the communication medium to provide secure and efficient authentication in wireless networks, bypassing the need for traditional cryptographic methods. With advancements in deep learning, PLA has become a widely adopted technique...

Attack the Messages, Not the Agents: a Multi-Round Adaptive Stealthy Tampering Framework for LLM-MAS

Large language model-based multi-agent systems LLM-MAS effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting LLM-MAS either compromise agent internals or rely on direct...

SquidLoader Malware Campaign Hits Hong Kong Financial Firms

Trellix exposes SquidLoader malware targeting Hong Kong, Singapore, and Australia's financial service institutions. Learn about its advanced evasion tactics and stealthy attacks...

Quantum Properties Trojans (QuPTs) for Attacking Quantum Neural Networks

Quantum neural networks QNN hold immense potential for the future of quantum machine learning QML. However, QNN security and robustness remain largely unexplored. In this work, we proposed novel Trojan attacks based on the quantum computing properties in a QNN-based binary classifier. Our propose...

The Hidden Threat in Plain Text: Attacking RAG Data Loaders

Large Language Models LLMs have transformed human-machine interaction since ChatGPT's 2022 debut, with Retrieval-Augmented Generation RAG emerging as a key framework that enhances LLM outputs by integrating external knowledge. However, RAG's reliance on ingesting external documents introduces new...

SPA: Towards More Stealth and Persistent Backdoor Attacks in Federated Learning

Federated Learning FL has emerged as a leading paradigm for privacy-preserving distributed machine learning, yet the distributed nature of FL introduces unique security challenges, notably the threat of backdoor attacks. Existing backdoor strategies predominantly rely on end-to-end label...

CodeGuard: a Generalized and Stealthy Backdoor Watermarking for Generative Code Models

Generative code models GCMs significantly enhance development efficiency through automated code generation and code summarization. However, building and training these models require computational resources and time, necessitating effective digital copyright protection to prevent unauthorized lea...

When Forgetting Triggers Backdoors: a Clean Unlearning Attack

Machine unlearning has emerged as a key component in ensuring Right to be Forgotten, enabling the removal of specific data points from trained models. However, even when the unlearning is performed without poisoning the forget-set clean unlearning, it can be exploited for stealthy attacks that...

ExtendAttack: Attacking Servers of LRMs via Extending Reasoning

Large Reasoning Models LRMs have demonstrated promising performance in complex tasks. However, the resource-consuming reasoning processes may be exploited by attackers to maliciously occupy the resources of the servers, leading to a crash, like the DDoS attack in cyber. To this end, we propose a...