Search Results for author:
Found 7 papers, 1 papers with code
The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks
In the attack, one can construct a PII association task, whereby an LLM is fine-tuned using a minuscule PII dataset, to potentially reinstate and reveal concealed PIIs.
NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning
At present, backdoor attacks attract attention as they do great harm to deep learning models.
Apple of Sodom: Hidden Backdoors in Superior Sentence Embeddings via Contrastive Learning
This paper finds that contrastive learning can produce superior sentence embeddings for pre-trained models but is also vulnerable to backdoor attacks.
Kallima: A Clean-label Framework for Textual Backdoor Attacks
Although Deep Neural Network (DNN) has led to unprecedented progress in various natural language processing (NLP) tasks, research shows that deep models are extremely vulnerable to backdoor attacks.
BadNL: Backdoor Attacks Against NLP Models
For instance, using the Word-level triggers, our backdoor attack achieves a 100% attack success rate with only a utility drop of 0. 18%, 1. 26%, and 0. 19% on three benchmark sentiment analysis datasets.
MIDAS: Multi-agent Interaction-aware Decision-making with Adaptive Strategies for Urban Autonomous Navigation
Autonomous navigation in crowded, complex urban environments requires interacting with other agents on the road.
BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements
In this paper, we perform a systematic investigation of backdoor attack on NLP models, and propose BadNL, a general NLP backdoor attack framework including novel attack methods.
