Related papers: FNF: Functional Network Fingerprint for Large Lang…
Deep neural networks (DNNs) are extensively employed in a wide range of application scenarios. Generally, training a commercially viable neural network requires significant amounts of data and computing resources, and it is easy for…
Large Language Model-based systems (LLM systems) are information and query processing systems that use LLMs to plan operations from natural-language prompts and feed the output of each successive step into the LLM to plan the next. This…
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…
The rising use of Large Language Models (LLMs) to create and disseminate malware poses a significant cybersecurity challenge due to their ability to generate and distribute attacks with ease. A single prompt can initiate a wide array of…
Recent explorations with commercial Large Language Models (LLMs) have shown that non-expert users can jailbreak LLMs by simply manipulating their prompts; resulting in degenerate output behavior, privacy and security breaches, offensive…
Named entity recognition is an important task when constructing knowledge bases from unstructured data sources. Whereas entity detection methods mostly rely on extensive training data, Large Language Models (LLMs) have paved the way towards…
Large Language Models (LLMs) have emerged as a popular choice in vulnerability detection studies given their foundational capabilities, open source availability, and variety of models, but have limited scalability due to extensive compute…
There are concerns that the ability of language models (LMs) to generate high quality synthetic text can be misused to launch spam, disinformation, or propaganda. Therefore, the research community is actively working on developing…
Safety alignment in large language models (LLMs) is achieved through fine-tuning mechanisms that regulate neuron activations to suppress harmful content. In this work, we propose a novel approach to induce disalignment by identifying and…
Large Language Models (LLMs) are widely adopted, but their high training cost leads many developers to fine-tune existing open-source models. While most adhere to open-source licenses, some falsely claim original training despite clear…
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…
Model fingerprinting has emerged as a promising paradigm for claiming model ownership. However, robustness evaluations of these schemes have mostly focused on benign perturbations such as incremental fine-tuning, model merging, and…
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…
Large language models (LLMs) present a dual challenge for forensic linguistics. They serve as powerful analytical tools enabling scalable corpus analysis and embedding-based authorship attribution, while simultaneously destabilising…
Recently, large language models (LLMs) have emerged as a notable field, attracting significant attention for its ability to automatically generate intelligent contents for various application domains. However, LLMs still suffer from…
Machine learning is a powerful tool for building predictive models. However, it is vulnerable to adversarial attacks. Fast Gradient Sign Method (FGSM) attacks are a common type of adversarial attack that adds small perturbations to input…
Model reuse techniques can reduce the resource requirements for training high-performance deep neural networks (DNNs) by leveraging existing models. However, unauthorized reuse and replication of DNNs can lead to copyright infringement and…
The honesty of Large Language Models (LLMs) is increasingly important for safe deployment in high-stakes domains. However, this crucial trait is severely undermined by supervised fine-tuning (SFT), a common technique for model…
The rapid advancement of large language models (LLMs) has brought significant benefits to various domains while introducing substantial risks. Despite being fine-tuned through reinforcement learning, LLMs lack the capability to discern…
The self-attention revolution allowed generative language models to scale and achieve increasingly impressive abilities. Such models - commonly referred to as Large Language Models (LLMs) - have recently gained prominence with the general…