Determining whether specific data was used in training
Newest first · 6 reviewed on this page
Search insteadHarsh Verma
As artificial intelligence becomes woven into critical applications such as healthcare, finance, autonomous systems, and cybersecurity, adversarial threats to machine learning models have grown into one of the most pressing concerns in the field. Adversarial machine learning…
Jinyu Chen, Jixiao Yang, Ziyang Zeng +3
Large Language Model (LLM)-based multi-agent systems have demonstrated remarkable capabilities across diverse applications, yet they face critical security challenges including backdoor attacks, prompt injection, and privacy leakage. Existing defense mechanisms typically address…
Xinyue Shen, Yiting Qu, Michael Backes +1
Demonstrates attacks that steal the prompts used to generate images from text-to-image models, raising IP and privacy concerns.
Vaidehi Patil, Peter Hase, Mohit Bansal
Evaluates methods for deleting sensitive information from trained LLMs, finding current unlearning approaches insufficient against determined adversaries.
Jeffrey G. Wang, Jason Wang, Marvin Li +1
Develops precise methods for detecting and extracting training data from LLMs when white-box access is available, with implications for copyright and privacy.
Bhagyajit Pingua, Deepak Murmu, Meenakshi Kandpal +4
Large language models (LLMs) have become transformative tools in areas like text generation, natural language processing, and conversational AI. However, their widespread use introduces security risks, such as jailbreak attacks, which exploit LLM’s vulnerabilities to manipulate…
Milad Nasr, Nicholas Carlini, Jonathan Hayase +7
Develops a scalable attack to extract over a gigabyte of training data from semi-open and closed models including ChatGPT, at a cost of roughly $200.
Haoran Li, Dadi Guo, Wei Fan +4
Demonstrates multi-step jailbreaking attacks to extract personal information from ChatGPT, showing how sequential prompting can bypass safety measures.
Nicholas Carlini, Florian Tramer, Eric Wallace +9
Demonstrates that large language models memorize and can be prompted to emit verbatim training data, including PII, revealing significant privacy risks.