Related papers: Machine Learning Interpretability Meets TLS Finger…

With the rapid adoption of Federated Learning (FL) as the training and tuning protocol for applications utilizing Large Language Models (LLMs), recent research highlights the need for significant modifications to FL to accommodate the…

Machine learning (ML) explainability is central to algorithmic transparency in high-stakes settings such as predictive diagnostics and loan approval. However, these same domains require rigorous privacy guaranties, creating tension between…

Encrypted traffic poses new and unique challenges for network operators because information that is useful or necessary for management purposes is not accessible anymore. This paper examines proposed approaches to provide end-to-end…

TLS stripping attacks expose sensitive web traffic by forcing secure HTTPS connections to fall back to unencrypted HTTP. At present, protection against these attacks relies on website operators explicitly opting into security by deploying…

The popularity of Machine Learning (ML) makes the privacy of sensitive data more imperative than ever. Collaborative learning techniques like Split Learning (SL) aim to protect client data while enhancing ML processes. Though promising, SL…

Behavioral transparency for Internet-of-Things (IoT) networked assets involves two distinct yet interconnected tasks: (a) characterizing device types by discerning the patterns exhibited in their network traffic, and (b) assessing…

We investigate the radioactivity of text generated by large language models (LLM), i.e. whether it is possible to detect that such synthetic input was used to train a subsequent LLM. Current methods like membership inference or active IP…

The behavior of LLMs does not depend solely on the model itself. Components of the inference system, such as the inference engine, attention backend, and hardware platform, subtly influence how inputs are processed. These components differ…

We use positional-unigram byte models along with maximum likelihood for generalized TLS fingerprinting and empirically show that it is robust to cipher stunting. Our approach creates a set of positional-unigram byte models from client hello…

This paper examines the evolving landscape of machine learning (ML) and its profound impact across various sectors, with a special focus on the emerging field of Privacy-preserving Machine Learning (PPML). As ML applications become…

Honeypots are decoy systems that lure attackers by presenting them with a seemingly vulnerable system. They provide an early detection mechanism as well as a method for learning how adversaries work and think. However, over the last years,…

Machine learning has been widely applied to various applications, some of which involve training with privacy-sensitive data. A modest number of data breaches have been studied, including credit card information in natural language data and…

As large language models (LLMs) see wider real-world use, understanding and mitigating their unsafe behaviors is critical. Interpretation techniques can reveal causes of unsafe outputs and guide safety, but such connections with safety are…

Typosquatting is a long-standing cyber threat that exploits human error in typing URLs to deceive users, distribute malware, and conduct phishing attacks. With the proliferation of domain names and new Top-Level Domains (TLDs),…

The Tor network provides users with strong anonymity by routing their internet traffic through multiple relays. While Tor encrypts traffic and hides IP addresses, it remains vulnerable to traffic analysis attacks such as the website…

Leakage of confidential information represents a serious security risk. Despite a number of novel, theoretical advances, it has been unclear if and how quantitative approaches to measuring leakage of confidential information could be…

Large Language Models (LLMs) have shown greatly enhanced performance in recent years, attributed to increased size and extensive training data. This advancement has led to widespread interest and adoption across industries and the public.…

Recent efforts in Machine Learning (ML) interpretability have focused on creating methods for explaining black-box ML models. However, these methods rely on the assumption that simple approximations, such as linear models or decision-trees,…

The recent surge in hardware security is significant due to offshoring the proprietary Intellectual property (IP). One distinct dimension of the disruptive threat is malicious logic insertion, also known as Hardware Trojan (HT). HT subverts…

Mobile communication systems now constitute an essential part of life throughout the world. Fourth generation "Long Term Evolution" (LTE) mobile communication networks are being deployed. The LTE suite of specifications is considered to be…