Related papers: Landseer: Exploring the Machine Learning Defense L…
To cope with the increasing variability and sophistication of modern attacks, machine learning has been widely adopted as a statistically-sound tool for malware detection. However, its security against well-crafted attacks has not only been…
LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…
In a federated learning (FL) system, malicious participants can easily embed backdoors into the aggregated model while maintaining the model's performance on the main task. To this end, various defenses, including training stage…
Federated Learning (FL) facilitates decentralized machine learning model training, preserving data privacy, lowering communication costs, and boosting model performance through diversified data sources. Yet, FL faces vulnerabilities such as…
Cloud Computing (CC) is revolutionizing the way IT resources are delivered to users, allowing them to access and manage their systems with increased cost-effectiveness and simplified infrastructure. However, with the growth of CC comes a…
As deep learning advances, Large Language Models (LLMs) and their multimodal counterparts, Multimodal Large Language Models (MLLMs), have shown exceptional performance in many real-world tasks. However, MLLMs face significant security…
We provide a comprehensive overview of adversarial machine learning focusing on two application domains, i.e., cybersecurity and computer vision. Research in adversarial machine learning addresses a significant threat to the wide…
Continuous integration is an indispensable step of modern software engineering practices to systematically manage the life cycles of system development. Developing a machine learning model is no difference - it is an engineering process…
This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with…
Machine learning applications are increasingly deployed not only to serve predictions using static models, but also as tightly-integrated components of feedback loops involving dynamic, real-time decision making. These applications pose a…
To address the growing demand for privacy protection in machine learning, we propose a novel and efficient machine unlearning approach for \textbf{L}arge \textbf{M}odels, called \textbf{LM}Eraser. Existing unlearning research suffers from…
The open-world deployment of Machine Learning (ML) algorithms in safety-critical applications such as autonomous vehicles needs to address a variety of ML vulnerabilities such as interpretability, verifiability, and performance limitations.…
The security of deep learning (DL) systems is an extremely important field of study as they are being deployed in several applications due to their ever-improving performance to solve challenging tasks. Despite overwhelming promises, the…
Extensive research on formal verification of machine learning (ML) systems indicates that learning from data alone often fails to capture underlying background knowledge. A variety of verifiers have been developed to ensure that a…
Large Language Models (LLMs) have shown remarkable performance across various applications, but their deployment in real-world settings faces several risks, including jailbreak attacks and privacy leaks. To mitigate these risks, numerous…
The arrival of Machine Learning (ML) completely changed how we can unlock valuable information from data. Traditional methods, where everything was stored in one place, had big problems with keeping information private, handling large…
Large Language Models (LLMs) have revolutionized artificial intelligence and machine learning through their advanced text processing and generating capabilities. However, their widespread deployment has raised significant safety and…
Machine learning algorithms are effective in several applications, but they are not as much successful when applied to intrusion detection in cyber security. Due to the high sensitivity to their training data, cyber detectors based on…
The growing penetration of renewable and distributed generation is transforming power systems and challenging conventional protection schemes that rely on fixed settings and local measurements. Machine learning (ML) offers a data-driven…
Malware classification is a difficult problem, to which machine learning methods have been applied for decades. Yet progress has often been slow, in part due to a number of unique difficulties with the task that occur through all stages of…