Obfuscation attacks that jointly optimize for target behavior and for low monitor scores bypass sparse autoencoders, probes, and OOD detectors on LLMs, while performance degrades mainly on hard tasks like writing correct SQL.
A Survey on Backdoor Attack and Defense in Natural Language Processing
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources being limited. In such a situation, training data and models are exposed to the public. As a result, attackers can manipulate the training process to inject some triggers into the model, which is called backdoor attack. Backdoor attack is quite stealthy and difficult to be detected because it has little inferior influence on the model's performance for the clean samples. To get a precise grasp and understanding of this problem, in this paper, we conduct a comprehensive review of backdoor attacks and defenses in the field of NLP. Besides, we summarize benchmark datasets and point out the open issues to design credible systems to defend against backdoor attacks.
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Obfuscated Activations Bypass LLM Latent-Space Defenses
Obfuscation attacks that jointly optimize for target behavior and for low monitor scores bypass sparse autoencoders, probes, and OOD detectors on LLMs, while performance degrades mainly on hard tasks like writing correct SQL.