Related papers: Combining Machine Learning Defenses without Confli…
Machine Learning (ML) can be incredibly valuable to automate anomaly detection and cyber-attack classification, improving the way that Network Intrusion Detection (NID) is performed. However, despite the benefits of ML models, they are…
In an era of escalating cyber threats, malware poses significant risks to individuals and organizations, potentially leading to data breaches, system failures, and substantial financial losses. This study addresses the urgent need for…
The increasing rate of crime, attacks by thieves, intruders and vandals, despite all forms of security gadgets and locks still need the attention of researchers to find a permanent solution to the well being of lives and properties of…
The widespread deployment of large language models (LLMs) across critical domains has amplified the societal risks posed by algorithmically generated misinformation. Unlike traditional false content, LLM-generated misinformation can be…
This paper studies how multimodal large language models (MLLMs) undermine the security guarantees of visual CAPTCHA. We identify the attack surface where an adversary can cheaply automate CAPTCHA solving using off-the-shelf models. We…
Machine Learning is becoming a pivotal aspect of many systems today, offering newfound performance on classification and prediction tasks, but this rapid integration also comes with new unforeseen vulnerabilities. To harden these systems…
The scale of Internet-connected systems has increased considerably, and these systems are being exposed to cyber attacks more than ever. The complexity and dynamics of cyber attacks require protecting mechanisms to be responsive, adaptive,…
Recently, coordinated attack campaigns started to become more widespread on the Internet. In May 2017, WannaCry infected more than 300,000 machines in 150 countries in a few days and had a large impact on critical infrastructure. Existing…
Scientific collaborations benefit from collaborative learning of distributed sources, but remain difficult to achieve when data are sensitive. In recent years, privacy preserving techniques have been widely studied to analyze distributed…
As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…
Motivated by the superior performance of deep learning in many applications including computer vision and natural language processing, several recent studies have focused on applying deep neural network for devising future generations of…
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…
Developers try to evaluate whether an AI system can be misused by adversaries before releasing it; for example, they might test whether a model enables cyberoffense, user manipulation, or bioterrorism. In this work, we show that…
Nowadays, considering the speed of the processes and the amount of data used in cyber defense, it cannot be expected to have an effective defense by using only human power without the help of automation systems. However, for the effective…
Large Language Models (LLMs) are powerful tools with profound societal impacts, yet their ability to generate responses to diverse and uncontrolled inputs leaves them vulnerable to adversarial attacks. While existing defenses often struggle…
Reinforcement Learning (RL), one of the core paradigms in machine learning, learns to make decisions based on real-world experiences. This approach has significantly advanced AI applications across various domains, notably in smart grid…
Deep Neural Networks (DNNs) are often vulnerable to adversarial examples.Several proposed defenses deploy an ensemble of models with the hope that, although the individual models may be vulnerable, an adversary will not be able to find an…
The generation of feasible adversarial examples is necessary for properly assessing models that work in constrained feature space. However, it remains a challenging task to enforce constraints into attacks that were designed for computer…
Empirical defenses for machine learning privacy forgo the provable guarantees of differential privacy in the hope of achieving higher utility while resisting realistic adversaries. We identify severe pitfalls in existing empirical privacy…
Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…