Related papers: AttnDiff: Attention-based Differential Fingerprint…

The widespread adoption of Large Language Models (LLMs), exemplified by OpenAI's ChatGPT, brings to the forefront the imperative to defend against adversarial threats on these models. These attacks, which manipulate an LLM's output by…

The performance of Large Language Models (LLMs) is significantly sensitive to the contextual position of information in the input. To investigate the mechanism behind this positional bias, our extensive experiments reveal a consistent…

Large language models are increasingly customized through fine-tuning and other adaptations, creating challenges in enforcing licensing terms and managing downstream impacts. Tracking model origins is crucial both for protecting…

Advanced Persistent Threats (APTs) pose a major cybersecurity challenge due to their stealth and ability to mimic normal system behavior, making detection particularly difficult in highly imbalanced datasets. Traditional anomaly detection…

The increasing demand for domain-specific and human-aligned Large Language Models (LLMs) has led to the widespread adoption of Supervised Fine-Tuning (SFT) techniques. SFT datasets often comprise valuable instruction-response pairs, making…

Key-Value (KV) cache memory and bandwidth increasingly dominate large language model inference cost in long-context and long-generation regimes. Architectures such as multi-head latent attention (MLA) and hybrid sliding-window attention…

As large language models are increasingly deployed in sensitive environments, fingerprinting attacks pose significant privacy and security risks. We present a study of LLM fingerprinting from both offensive and defensive perspectives. Our…

Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires…

Large Language Diffusion Models (LLDMs) benefit from a flexible decoding mechanism that enables parallelized inference and controllable generations over autoregressive models. Yet such flexibility introduces a critical challenge: inference…

Differential privacy (DP) is the de facto privacy standard against privacy leakage attacks, including many recently discovered ones against large language models (LLMs). However, we discovered that LLMs could reconstruct the altered/removed…

Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning. Recent multi-modal OOD detection leverages textual information from in-distribution (ID) class names for visual OOD detection, yet it currently…

Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagnose and correct undesirable behaviors. Mechanistic…

Customized Large Language Model (LLM) agents face a critical security threat from black-box instruction backdoors, where malicious behaviors are covertly injected through hidden system instructions. Although existing prompt-based defenses…

Large language models (LLMs) demonstrate remarkable capabilities across various tasks. However, their deployment introduces significant risks related to intellectual property. In this context, we focus on model stealing attacks, where…

Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and…

Change detection is a fundamental task in computer vision that processes a bi-temporal image pair to differentiate between semantically altered and unaltered regions. Large language models (LLMs) have been utilized in various domains for…

The widespread deployment of large language models (LLMs) has intensified concerns around intellectual property (IP) protection, as model theft and unauthorized redistribution become increasingly feasible. To address this, model…

Copyright protection for large language models is of critical importance, given their substantial development costs, proprietary value, and potential for misuse. Existing surveys have predominantly focused on techniques for tracing…

The adoption of large language models (LLMs) in many applications, from customer service chat bots and software development assistants to more capable agentic systems necessitates research into how to secure these systems. Attacks like…

Recent advances in the fingerprinting of deep neural networks detect instances of models, placed in a black-box interaction scheme. Inputs used by the fingerprinting protocols are specifically crafted for each precise model to be checked…