5 papers · 1 filter
Restorative Control and the Limits of Safe Model Discrimination
Micheal Myers
Restorative control seeks lasting recovery through an intervention that ends in finite time. We formulate this objective as a reach-avoid problem in which the input must bring the…
InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation
Jiachang Zhang, Min Chen, Xiao Ren +4
Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) with external knowledge but have been demonstrated to be vulnerable to corpus poisoning. Existing…
MarkSec: Capability-Aware Evaluation of Adversarial Attacks Against LLM Watermarks
Kairong Li, Zhikun Zhang, Xiao Ren +1
LLM watermarking helps trace the origin of generated text, but faces stealing attacks that recover watermark information, scrubbing attacks that remove watermark signals, and spoof…
KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models
Ce Fang, Zhikun Zhang, Min Chen +4
Large language models (LLMs) acquire a large amount of knowledge through pre-training on vast and diverse corpora. While this endows LLMs with strong capabilities in generation and…
DWBench: Holistic Evaluation of Watermark for Dataset Copyright Auditing
Xiao Ren, Xinyi Yu, Linkang Du +5
The surging demand for large-scale datasets in deep learning has heightened the need for effective copyright protection, given the risks of unauthorized use to data owners. Althoug…