Document is current

Chapter History

First Online: 22 August 2024

Ethical Declarements

: Backdoor attacks pose a major risk to natural language processing by subtly manipulating model inferences. While existing defenses examine syntactic correctness and repetition, we propose a fluency-preserving perturbation method, named NURA, to clandestinely poison language models during generation rather than post-hoc. By subtly altering inputs, our approach evades rule-based detection while producing fluent poisoned texts. Through this work, we aim to raise awareness of stealthy input-aware backdoors and spur discussion on mitigation, as adversarial examples integrated during training challenge standard defenses and model auditing. Continued exploration of techniques detecting pattern shifts introduced during poisoning may help safeguard applications, emphasizing proactive consideration of diverse attack vectors throughout development to strengthen protections for real-world language systems.

Conference Information

Conference Acronym: ECML PKDD

Conference Name: Joint European Conference on Machine Learning and Knowledge Discovery in Databases

Conference City: Vilnius

Conference Country: Lithuania

Conference Year: 2024

Conference Start Date: 8 September 2024

Conference End Date: 12 September 2024

Conference Number: 24

Conference ID: ecml2024

Conference URL: https://2024.ecmlpkdd.org/