Related papers: Redefining Website Fingerprinting Attacks With Mul…
Content based data classification is an open challenge. Traditional Data Loss Prevention (DLP)-like systems solve this problem by fingerprinting the data in question and monitoring endpoints for the fingerprinted data. With a large number…
Recent advancements in large language models (LLMs) have led to the creation of intelligent agents capable of performing complex tasks. This paper introduces a novel LLM-based multimodal agent framework designed to operate smartphone…
To fulfill user instructions, autonomous web agents must contend with the inherent complexity and volatile nature of real-world websites. Conventional paradigms predominantly rely on Supervised Fine-Tuning (SFT) or Offline Reinforcement…
Website Fingerprinting attacks enable a passive eavesdropper to recover the user's otherwise anonymized web browsing activity by matching the observed traffic with prerecorded web traffic templates. The defenses that have been proposed to…
Large language models (LLMs) offer promising capabilities for simulating social media dynamics at scale, enabling studies that would be ethically or logistically challenging with human subjects. However, the field lacks standardized data…
Large language models (LLMs) have demonstrated exceptional capabilities in text understanding and generation, and they are increasingly being utilized across various domains to enhance productivity. However, due to the high costs of…
Large Language Models (LLMs) have emerged as a transformative and disruptive technology, enabling a wide range of applications in natural language processing, machine translation, and beyond. However, this widespread integration of LLMs…
Quantitative Information Flow (QIF) provides a robust information-theoretical framework for designing secure systems with minimal information leakage. While previous research has addressed the design of such systems under hard constraints…
Web navigation is a unique domain that can automate many repetitive real-life tasks and is challenging as it requires long-horizon sequential decision making beyond typical multimodal large language model (MLLM) tasks. Yet, specialized…
Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as…
With the widespread application of large language models (LLMs), user privacy protection has become a significant research topic. Existing privacy preference modeling methods often rely on large-scale user data, making effective privacy…
Deep neural networks (DNNs) have achieved remarkable success in radio frequency (RF) fingerprinting for wireless device authentication. However, their practical deployment faces two major limitations: domain shift, where models trained in…
With the rise of sophisticated scam websites that exploit human psychological vulnerabilities, distinguishing between legitimate and scam websites has become increasingly challenging. This paper presents ScamFerret, an innovative agent…
Multi-agent LLM frameworks are widely used to accelerate the development of agent systems powered by large language models (LLMs). These frameworks impose distinct architectural structures that govern how agents interact, store information,…
Browser fingerprinting is a relatively new method of uniquely identifying browsers that can be used to track web users. In some ways it is more privacy-threatening than tracking via cookies, as users have no direct control over it. A number…
The broad capabilities and substantial resources required to train Large Language Models (LLMs) make them valuable intellectual property, yet they remain vulnerable to copyright infringement, such as unauthorized use and model theft. LLM…
The Web is evolving from a medium that humans browse to an environment where software agents act on behalf of users. Advances in large language models (LLMs) make natural language a practical interface for goal-directed tasks, yet most…
Autonomous web agents powered by large language models (LLMs) show strong potential for performing goal-oriented tasks such as information retrieval, report generation, and online transactions. These agents mark a key step toward practical…
Watermarking of large language models (LLMs) generation embeds an imperceptible statistical pattern within texts, making it algorithmically detectable. Watermarking is a promising method for addressing potential harm and biases from LLMs,…
Website hacking is a frequent attack type used by malicious actors to obtain confidential information, modify the integrity of web pages or make websites unavailable. The tools used by attackers are becoming more and more automated and…