English
Related papers

Related papers: Exploiting Novel GPT-4 APIs

200 papers

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…

Cryptography and Security · Computer Science 2024-07-01 Danny Halawi , Alexander Wei , Eric Wallace , Tony T. Wang , Nika Haghtalab , Jacob Steinhardt

AI safety training and red-teaming of large language models (LLMs) are measures to mitigate the generation of unsafe content. Our work exposes the inherent cross-lingual vulnerability of these safety mechanisms, resulting from the…

Computation and Language · Computer Science 2024-01-30 Zheng-Xin Yong , Cristina Menghini , Stephen H. Bach

Along with the development of large language models (LLMs), e.g., ChatGPT, many existing approaches and tools for software security are changing. It is, therefore, essential to understand how security-aware these models are and how these…

Computers and Society · Computer Science 2023-09-20 Jingyue Li , Per Håkon Meland , Jakob Svennevik Notland , André Storhaug , Jostein Hjortland Tysse

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…

Cryptography and Security · Computer Science 2025-09-23 Brendan Murphy , Dillon Bowen , Shahrad Mohammadzadeh , Tom Tseng , Julius Broomfield , Adam Gleave , Kellin Pelrine

We introduce API Pack, a massive multi-programming language dataset containing over one million instruction-API calls for improving the API call generation capabilities of large language models. Our evaluation highlights three key findings:…

Computation and Language · Computer Science 2025-02-17 Zhen Guo , Adriana Meza Soria , Wei Sun , Yikang Shen , Rameswar Panda

Large language models (LLMs) have undergone rapid evolution and achieved remarkable results in recent times. OpenAI's ChatGPT, backed by GPT-3.5 or GPT-4, has gained instant popularity due to its strong capability across a wide range of…

Cryptography and Security · Computer Science 2023-12-12 Fangzhou Wu , Qingzhao Zhang , Ati Priya Bajaj , Tiffany Bao , Ning Zhang , Ruoyu "Fish" Wang , Chaowei Xiao

With the rapid advancement of large language models (LLMs), ensuring their safe use becomes increasingly critical. Fine-tuning is a widely used method for adapting models to downstream tasks, yet it is vulnerable to jailbreak attacks.…

Cryptography and Security · Computer Science 2025-10-10 Xiangfang Li , Yu Wang , Bo Li

Pre-trained large language models, such as GPT\nobreakdash-2 and BERT, are often fine-tuned to achieve state-of-the-art performance on a downstream task. One natural example is the ``Smart Reply'' application where a pre-trained model is…

Cryptography and Security · Computer Science 2023-09-06 Bargav Jayaraman , Esha Ghosh , Melissa Chase , Sambuddha Roy , Wei Dai , David Evans

Machine learning practitioners often fine-tune generative pre-trained models like GPT-3 to improve model performance at specific tasks. Previous works, however, suggest that fine-tuned machine learning models memorize and emit sensitive…

Machine Learning · Computer Science 2024-04-17 Albert Yu Sun , Eliott Zemour , Arushi Saxena , Udith Vaidyanathan , Eric Lin , Christian Lau , Vaikkunth Mugunthan

In this study, we evaluated the capability of Large Language Models (LLMs), particularly OpenAI's GPT-4, in detecting software vulnerabilities, comparing their performance against traditional static code analyzers like Snyk and Fortify. Our…

Software Engineering · Computer Science 2023-08-22 David Noever

Because state-of-the-art language models are expensive to train, most practitioners must make use of one of the few publicly available language models or language model APIs. This consolidation of trust increases the potency of backdoor…

Cryptography and Security · Computer Science 2023-07-28 Nikhil Kandpal , Matthew Jagielski , Florian Tramèr , Nicholas Carlini

Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in the training dataset. With cutting-edge generative models such…

Cryptography and Security · Computer Science 2023-05-01 Jiazhao Li , Yijin Yang , Zhuofeng Wu , V. G. Vinod Vydiswaran , Chaowei Xiao

Millions of users leverage generative pretrained transformer (GPT)-based language models developed by leading model providers for a wide range of tasks. To support enhanced user interaction and customization, many platforms-such as…

Cryptography and Security · Computer Science 2025-05-14 Sunday Oyinlola Ogundoyin , Muhammad Ikram , Hassan Jameel Asghar , Benjamin Zi Hao Zhao , Dali Kaafar

Command injection vulnerabilities are a significant security threat in dynamic languages like Python, particularly in widely used open-source projects where security issues can have extensive impact. With the proven effectiveness of Large…

Software Engineering · Computer Science 2025-05-22 Yuxuan Wang , Jingshu Chen , Qingyang Wang

Large language model fine-tuning APIs enable widespread model customization, yet pose significant safety risks. Recent work shows that adversaries can exploit access to these APIs to bypass model safety mechanisms by encoding harmful…

Machine Learning · Computer Science 2025-08-26 Jack Youstra , Mohammed Mahfoud , Yang Yan , Henry Sleight , Ethan Perez , Mrinank Sharma

Significant advancements have recently been made in large language models represented by GPT models. Users frequently have multi-round private conversations with cloud-hosted GPT models for task optimization. Yet, this operational paradigm…

Cryptography and Security · Computer Science 2024-10-08 Junjie Chu , Zeyang Sha , Michael Backes , Yang Zhang

We surface a new threat to closed-weight Large Language Models (LLMs) that enables an attacker to compute optimization-based prompt injections. Specifically, we characterize how an attacker can leverage the loss-like information returned…

Cryptography and Security · Computer Science 2025-05-13 Andrey Labunets , Nishit V. Pandya , Ashish Hooda , Xiaohan Fu , Earlence Fernandes

It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…

Cryptography and Security · Computer Science 2024-04-02 Yuxin Wen , Leo Marchyok , Sanghyun Hong , Jonas Geiping , Tom Goldstein , Nicholas Carlini

As large language models (LLMs) become more powerful and are deployed more autonomously, it will be increasingly important to prevent them from causing harmful outcomes. Researchers have investigated a variety of safety techniques for this…

Machine Learning · Computer Science 2024-07-24 Ryan Greenblatt , Buck Shlegeris , Kshitij Sachan , Fabien Roger

The rapid advancement of large language models (LLMs) such as GPT-4 has revolutionized the landscape of software engineering, positioning these models at the core of modern development practices. As we anticipate these models to evolve into…

Software Engineering · Computer Science 2025-06-16 Jianian Gong , Nachuan Duan , Ziheng Tao , Zhaohui Gong , Yuan Yuan , Minlie Huang
‹ Prev 1 2 3 10 Next ›