Related papers: Redefining Website Fingerprinting Attacks With Mul…
Running language models in the browser presents a unique opportunity to build efficient, private, and portable AI applications, but requires contending with constrained memory availability and heterogeneous hardware targets. To realize this…
Personalization today is fundamentally platform-centric: services build user representations from the behavioral fragments they observe. Yet no platform can construct a complete picture of the user, as competitive incentives, legal…
While many online services provide privacy policies for end users to read and understand what personal data are being collected, these documents are often lengthy and complicated. As a result, the vast majority of users do not read them at…
Device fingerprinting is a widely used technique that allows a third party to identify a particular device. Applications of device fingerprinting include authentication, attacker identification, or software license binding. Device…
Large language models (LLMs) and LLM-based agents have been widely deployed in a wide range of applications in the real world, including healthcare diagnostics, financial analysis, customer support, robotics, and autonomous driving,…
Tor provides low-latency anonymous and uncensored network access against a local or network adversary. Due to the design choice to minimize traffic overhead (and increase the pool of potential users) Tor allows some information about the…
Website fingerprinting (WF) attacks on Tor can infer user destinations from encrypted traffic metadata. However, their real-world effectiveness remains debated due to laboratory settings that fail to capture network fluctuations, evaluate…
Personalized user understanding from large-scale digital traces remains a fundamental challenge. Traditional user profiling methods rely on discriminative models and manual feature engineering to predict discrete attributes, often producing…
Large Language Model (LLM)-based mobile agents have made significant performance advancements. However, these agents often follow explicit user instructions while overlooking personalized needs, leading to significant limitations for real…
Large language models (LLMs) have fueled many intelligent web agents, but most existing ones perform far from satisfying in real-world web navigation tasks due to three factors: (1) the complexity of HTML text data (2) versatility of…
The widespread adoption of Large Language Models (LLMs) and LLM-powered agents in multi-user settings underscores the need for reliable, usable methods to accommodate diverse preferences and resolve conflicting directives. Drawing on…
Anonymity systems like Tor are vulnerable to Website Fingerprinting (WF) attacks, where a local passive eavesdropper infers the victim's activity. Current WF attacks based on deep learning classifiers have successfully overcome numerous…
Protecting users' privacy over the Internet is of great importance; however, it becomes harder and harder to maintain due to the increasing complexity of network protocols and components. Therefore, investigating and understanding how data…
Multi-modal large language model (MLLM)-based web agents interact with webpage environments by generating actions based on screenshots of the webpages. In this work, we propose WebInject, a prompt injection attack that manipulates the…
A long-standing challenge in developing accurate recommendation models is simulating user behavior, mainly due to the complex and stochastic nature of user interactions. Towards this, one promising line of work has been the use of Large…
The rapid evolution of wireless networks presents unprecedented challenges in managing complex and dynamic systems. Existing methods are increasingly facing fundamental limitations in addressing these challenges. In this paper, we introduce…
Large language models (LLMs) have driven profound transformations in wireless networks. However, within wireless environments, the training of LLMs faces significant challenges related to security and privacy. Federated Learning (FL), with…
In this paper, we demonstrate that it is possible to automatically generate fingerprints for various web server types using multifactor Bayesian inference on randomly selected servers on the Internet, without building an a priori catalog of…
Web agents powered by large language models (LLMs) must process lengthy web page observations to complete user goals; these pages often exceed tens of thousands of tokens. This saturates context limits and increases computational cost…
Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can reveal significant information about their data. This has…