SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks

arXiv:2405.11575v1 Announce Type: cross
Abstract: Modern NLP models are often trained on public datasets drawn from diverse sources, rendering them vulnerable to data poisoning attacks. These attacks can manipulate the model's behavior in ways engineered by the attacker. One such tactic involves the implantation of backdoors, achieved by poisoning specific training instances with a textual trigger and a target class label. Several strategies have been proposed to mitigate the risks associated with backdoor attacks by identifying and removing suspected poisoned …

arxiv attacker attacks backdoor backdoors can cs.cl cs.cr data data poisoning datasets nlp poisoning poisoning attacks public representation search tactic training vulnerable