Related papers: From Similarity to Vulnerability: Key Collision At…
Cascade systems route computational requests to smaller models when possible and defer to larger models only when necessary, offering a promising approach to balance cost and quality in LLM deployment. However, they face a fundamental…
Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based…
As context windows in LLMs scale to 100K+ tokens, the key-value (KV) cache becomes the dominant memory bottleneck, with recent methods claiming 80-90% savings and minimal benchmark degradation. We argue these evaluations miss a structural…
Large language models (LLMs), such as ChatGPT, have emerged with astonishing capabilities approaching artificial general intelligence. While providing convenience for various societal needs, LLMs have also lowered the cost of generating…
Accurately quantifying uncertainty in large language models (LLMs) is crucial for their reliable deployment, especially in high-stakes applications. Current state-of-the-art methods for measuring semantic uncertainty in LLMs rely on strict…
Cloud-device collaborative recommendation partitions computation across the cloud and user devices: the cloud provides semantic user modeling, while the device leverages recent interactions and cloud semantic signals for privacy-preserving,…
Phishing detection is a critical cybersecurity task that involves the identification and neutralization of fraudulent attempts to obtain sensitive information, thereby safeguarding individuals and organizations from data breaches and…
Despite the transformative impact of deep learning across multiple domains, the inherent opacity of these models has driven the development of Explainable Artificial Intelligence (XAI). Among these efforts, Concept Bottleneck Models (CBMs)…
Security alignment enables the Large Language Model (LLM) to gain the protection against malicious queries, but various jailbreak attack methods reveal the vulnerability of this security mechanism. Previous studies have isolated LLM…
Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm…
Cache randomization has recently been revived as a promising defense against conflict-based cache side-channel attacks. As two of the latest implementations, CEASER-S and ScatterCache both claim to thwart conflict-based cache side-channel…
Similarity search methods are widely used as kernels in various machine learning applications. Nearest neighbor search (NNS) algorithms are often used to retrieve similar entries, given a query. While there exist efficient techniques for…
Large Language Models (LLMs) are being deployed across various domains today. However, their capacity to solve Capture the Flag (CTF) challenges in cybersecurity has not been thoroughly evaluated. To address this, we develop a novel method…
While Deep Learning (DL) technologies are a promising tool to solve networking problems that map to classification tasks, their computational complexity is still too high with respect to real-time traffic measurements requirements. To…
Software vulnerabilities are a primary threat to modern infrastructure. While static analysis and Graph Neural Networks have long served as the foundation for vulnerability detection, the emergence of Large Language Models (LLMs) has…
Large language models (LLMs) have shown state-of-the-art results in translating natural language questions into SQL queries (Text-to-SQL), a long-standing challenge within the database community. However, security concerns remain largely…
In this fast-evolving area of LLMs, our paper discusses the significant security risk presented by prompt injection attacks. It focuses on small open-sourced models, specifically the LLaMA family of models. We introduce novel defense…
Both humans and Large Language Models (LLMs) store a vast repository of semantic memories. In humans, efficient and strategic access to this memory store is a critical foundation for a variety of cognitive functions. Such access has long…
The fast advancements in Large Language Models (LLMs) are driving an increasing number of applications. Together with the growing number of users, we also see an increasing number of attackers who try to outsmart these systems. They want…
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…